CN111260569A - Method and device for correcting image inclination, electronic equipment and storage medium - Google Patents
Method and device for correcting image inclination, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN111260569A CN111260569A CN202010027521.1A CN202010027521A CN111260569A CN 111260569 A CN111260569 A CN 111260569A CN 202010027521 A CN202010027521 A CN 202010027521A CN 111260569 A CN111260569 A CN 111260569A
- Authority
- CN
- China
- Prior art keywords
- image
- processed
- text line
- circumscribed rectangle
- text
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/80—Geometric correction
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/14—Image acquisition
- G06V30/146—Aligning or centring of the image pick-up or image-field
- G06V30/1475—Inclination or skew detection or correction of characters or of image to be recognised
- G06V30/1478—Inclination or skew detection or correction of characters or of image to be recognised of characters or characters lines
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30176—Document
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Character Input (AREA)
Abstract
The application discloses a method and a device for correcting image inclination, electronic equipment and a storage medium, and relates to the field of image processing. The specific implementation scheme is as follows: according to the circumscribed rectangles of the text lines in the image to be processed, carrying out rotation processing on the image to be processed to obtain an initial correction image of the image to be processed, wherein the circumscribed rectangles of the text lines in the initial correction image are vertical or parallel to the horizontal direction; and if the direction of the characters in the text line in the initial correction image is not upright, performing rotation processing on the initial correction image to obtain a correction image of the image to be processed, wherein the direction of the characters in the text line in the correction image is upright. In the application, after the image is rotated according to the circumscribed rectangle of the text line, the image can be rotated by multiples of 90 degrees according to the text direction in the image, so that the text direction in the rotated image is upright.
Description
Technical Field
The present application relates to the field of image processing technologies, and in particular, to a method and an apparatus for correcting an image tilt, an electronic device, and a storage medium.
Background
In business scenes of enterprise claiming, product purchasing and the like, a user often needs to submit enterprise, organization or personal identification materials for identity authentication. These identification materials typically include images of various certificates of employment issued by legal or socially recognized authorities, i.e., quality images, such as images of certificates of business licenses, organizational code certificates, corporate certificates, civil non-enterprise certificates, food handling licenses, human resource service licenses, law firm licenses, and the like. The authentication server extracts key information in the qualification image uploaded by the user and compares the information in the qualification image with official data to perform identity authentication. The qualification images are uploaded by users through photographing, and 0-360 degrees of inclination may exist, and the inclination of the images can generate great interference on the accuracy of the information in the extracted images.
In the prior art, the authentication server usually performs overall contour extraction based on all pixel blocks on the image to generate a circumscribed rectangle of the contour, and performs tilt correction on the image according to the tilt angle of the circumscribed rectangle.
However, the method can only perform tilt correction within plus and minus 45 degrees based on the circumscribed rectangle, and does not support tilt correction of multiples of 90 degrees, which causes that characters in the corrected image are perpendicular to the horizontal direction, resulting in failure of tilt correction.
Disclosure of Invention
The application provides a method and a device for correcting image tilt, electronic equipment and a storage medium, which can realize tilt correction of 90-degree multiple of an image, so that the character direction of the corrected image is upright.
The present application provides, in a first aspect, a method for image tilt correction, including: according to the circumscribed rectangles of the text lines in the image to be processed, carrying out rotation processing on the image to be processed to obtain an initial correction image of the image to be processed, wherein the circumscribed rectangles of the text lines in the initial correction image are vertical or parallel to the horizontal direction; and if the direction of the characters in the text line in the initial correction image is not upright, performing rotation processing on the initial correction image to obtain a correction image of the image to be processed, wherein the direction of the characters in the text line in the correction image is upright.
In this embodiment, after the image is rotated according to the circumscribed rectangle of the text line in the image to be processed, the image may be further rotated by a large angle according to the direction of the characters in the rotated image, so that the direction of the characters in the rotated image is upright.
In a possible design, the method includes that a plurality of circumscribed rectangles of the text line in the image to be processed are provided, and the rotating process is performed on the image to be processed according to the circumscribed rectangles of the text line in the image to be processed to obtain an initial corrected image of the image to be processed, and includes: acquiring the minimum angle among included angles of a circumscribed rectangle of each text line in the image to be processed and the horizontal direction and the vertical direction; taking the minimum angle with the largest number as a first rotation angle; and rotating the image to be processed by the first rotation angle to obtain the initial correction image.
In a possible design, before obtaining a minimum angle of included angles between a circumscribed rectangle of each text line in the image to be processed and a horizontal direction and a vertical direction, the method further includes: carrying out contour detection on the binary image of the image to be processed to obtain a target contour of a text line, wherein the area of the target contour is within a preset area range, and the length-width ratio of the target contour is within a preset proportion range; and generating a circumscribed rectangle of the target outline, wherein the circumscribed rectangle of the target outline is the circumscribed rectangle of the text line in the image to be processed.
In the design, a preset area range and a preset proportion range of the foreground region capable of filtering the non-text lines are set, so that the acquired target contours are all the contours of the text lines.
In one possible design, before performing contour detection on the binarized image of the image to be processed, the method includes: compressing the image to be processed to a preset size; carrying out binarization processing on the compressed image to obtain a binarized image; and carrying out corrosion expansion processing on the foreground region in the binary image according to a preset expansion corrosion factor so as to obtain the binary image of the image to be processed.
In the design, in view of the correlation between the size of the binarized image and the expansion corrosion factor, the image to be processed is compressed to the preset size, so that the complex operation of selecting a proper expansion corrosion factor for binarized images with different sizes can be avoided, and the preset expansion corrosion factor is suitable for the binarized image with the size, so that the effect of well distinguishing the foreground region from the background region can be achieved.
In one possible design, after the generating the circumscribed rectangle of the target contour, the method further includes: determining the central position of the image to be processed; and filtering the circumscribed rectangle with the distance from the central position of the image to be processed being larger than a first preset distance.
In the design, the non-important text lines (text lines far away from the central position of the image to be processed) can be filtered, and the circumscribed rectangle with the distance from the central position of the image to be processed being smaller than the first preset distance is adopted for processing, so that the accuracy of image inclination correction can be improved.
In a possible design, if the direction of the text in the text line in the initial corrected image is not upright, performing rotation processing on the initial corrected image to obtain a corrected image of the image to be processed, includes: taking a circumscribed rectangle of the text line within a second preset distance range from the center position of the initial correction image as a target circumscribed rectangle; acquiring an included angle between the text direction and the horizontal direction of the text line in the target circumscribed rectangle; taking the included angle with the largest number as a second rotation angle; and rotating the initial correction image by the second rotation angle to obtain the correction image.
In this design, the image may be further rotated by a large angle according to the direction of the characters in the rotated image, so that the direction of the characters in the rotated image is upright.
In one possible design, before the step of taking a bounding rectangle of the text line within a second preset distance range from the center position of the initial corrected image as the target bounding rectangle, the step further includes: and determining the central position of the image to be processed according to the abscissa and the ordinate of the circumscribed rectangle.
In a possible design, before performing rotation processing on the image to be processed according to the circumscribed rectangle of the text line in the image to be processed, the method includes: and receiving the image to be processed input by a user.
In a possible design, the image to be processed is a qualified image, and after obtaining the corrected image of the image to be processed, the method further includes: identifying qualification information in the corrected image; and authenticating the qualification information in the corrected image and outputting a qualification authentication result.
In the design, since the application can perform the inclination correction of the image to be processed by a multiple of 90 degrees, the identification accuracy of the qualification information in the embodiment can be improved, and the accuracy of the qualification authentication result can be further improved.
A second aspect of the present application provides an apparatus for image tilt correction, comprising:
the processing module is used for performing rotation processing on the image to be processed according to the external rectangle of the text line in the image to be processed to obtain an initial correction image of the image to be processed, the external rectangle of the text line in the initial correction image is vertical or parallel to the horizontal direction, and if the direction of characters in the text line in the initial correction image is not upright, the initial correction image is performed with rotation processing to obtain a correction image of the image to be processed, and the direction of characters in the text line in the correction image is upright.
Optionally, a plurality of circumscribed rectangles of the text line in the image to be processed are provided.
Correspondingly, the processing module is specifically configured to obtain a minimum angle among included angles between a circumscribed rectangle of each text line in the image to be processed and the horizontal direction and the vertical direction; taking the minimum angle with the largest number as a first rotation angle; and rotating the image to be processed by the first rotation angle to obtain the initial correction image.
Optionally, the processing module is further configured to perform contour detection on the binarized image of the image to be processed to obtain a target contour of the text line, where an area of the target contour is within a preset area range, and an aspect ratio of the target contour is within a preset proportion range; and generating a circumscribed rectangle of the target outline, wherein the circumscribed rectangle of the target outline is the circumscribed rectangle of the text line in the image to be processed.
Optionally, the processing module is further configured to compress the image to be processed to a preset size; carrying out binarization processing on the compressed image to obtain a binarized image; and carrying out corrosion expansion processing on the foreground region in the binary image according to a preset expansion corrosion factor so as to obtain the binary image of the image to be processed.
Optionally, the processing module is further configured to determine a center position of the image to be processed; and filtering the circumscribed rectangle with the distance from the central position of the image to be processed being larger than a first preset distance.
Optionally, the processing module is specifically configured to take a circumscribed rectangle of the text line within a second preset distance range from the center position of the initial corrected image as a target circumscribed rectangle; acquiring an included angle between the text direction and the horizontal direction of the text line in the target circumscribed rectangle; taking the included angle with the largest number as a second rotation angle; and rotating the initial correction image by the second rotation angle to obtain the correction image.
Optionally, the processing module is specifically configured to determine a center position of the image to be processed according to an abscissa and an ordinate of the circumscribed rectangle.
And the transceiving module is used for receiving the image to be processed input by the user.
Optionally, the processing module is further configured to identify qualification information in the corrected image; and authenticating the qualification information in the corrected image and outputting a qualification authentication result.
The beneficial effects of the image tilt correction apparatus provided by the second aspect and the possible designs can be referred to the beneficial effects of the first aspect and the possible designs, which are not described herein again.
A third aspect of the present application provides an electronic device comprising: at least one processor and memory; the memory stores computer-executable instructions; the at least one processor executes computer-executable instructions stored by the memory to cause the electronic device to perform the method of image tilt correction of the first aspect described above.
A fourth aspect of the present application provides a computer-readable storage medium having stored thereon computer-executable instructions that, when executed by a processor, implement the method of image tilt correction of the first aspect described above.
Other effects of the above-described alternative will be described below with reference to specific embodiments.
Drawings
The drawings are included to provide a better understanding of the present solution and are not intended to limit the present application. Wherein:
FIG. 1 is a first diagram illustrating a variation of a qualification image in the prior art;
FIG. 2 is a diagram illustrating a variation of a qualification image in the prior art;
FIG. 3 is a third diagram illustrating a variation of a qualification image in the prior art;
FIG. 4 is a flowchart illustrating a first embodiment of a method for image tilt correction according to the present disclosure;
FIG. 5 is a schematic diagram of a corrected image provided herein;
FIG. 6 is a schematic flow chart of the present application for obtaining an initial calibration image;
FIG. 7 is a schematic flow chart of acquiring a corrected image according to the present disclosure;
fig. 8 is a flowchart illustrating a second embodiment of a method for image tilt correction according to the present application;
FIG. 9 is a schematic diagram of the interface change of the image tilt correction apparatus provided in the present application;
FIG. 10 is a schematic structural diagram of an apparatus for image tilt correction provided in the present application;
fig. 11 is a schematic structural diagram of an electronic device provided in the present application.
Detailed Description
The following description of the exemplary embodiments of the present application, taken in conjunction with the accompanying drawings, includes various details of the embodiments of the application for the understanding of the same, which are to be considered exemplary only. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present application. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
In the process of uploading and authenticating the qualification images, the uploaded qualification images may have a tilt in view of the fact that the qualification images are uploaded by the user through photographing. Since image tilt can have an effect on identifying information in the qualifying image, tilt correction of the qualifying image is required.
Fig. 1 is a first diagram illustrating a variation of a qualification image in the prior art. As shown in fig. 1 (a), the qualification image is inclined at 60 degrees from the horizontal direction and at 30 degrees from the vertical direction. In the prior art, the overall contour is extracted based on all pixel blocks on an image, a circumscribed rectangle of the contour is generated, and the image is subjected to tilt correction according to the tilt angle of the circumscribed rectangle. Illustratively, if the qualification image is wholly or partially taken as an outline, the dotted line in fig. 1 is a circumscribed rectangle of the outline. Correspondingly, the rotation angle of the qualification image can be determined according to the included angle between the circumscribed rectangle and the horizontal direction or the vertical direction, so as to perform inclination correction on the qualification image. For example, if the included angle between the circumscribed rectangle and the horizontal direction is 60 degrees and the included angle between the circumscribed rectangle and the vertical direction is 30 degrees, the qualification image may be rotated by 30 degrees toward the vertical direction, so that the qualification image is parallel to the vertical direction. Thereby making the text in the rotated qualification image upright (i.e. the text line is parallel to the horizontal direction and not inverted), as shown in fig. 1 (b). It should be understood that the rotation angle of the qualifying image is the smaller of the angles to the horizontal or to the vertical so that the rotation processing of the image has as little effect as possible on the original qualifying image.
As described above with reference to fig. 1, the characters in the rotated qualification image can be erected, and the information recognition accuracy can be improved. Fig. 2 is a schematic diagram illustrating a variation of a qualification image in the prior art. As shown in fig. 2 (a), if the included angle between the circumscribed rectangle and the horizontal direction is determined to be 30 degrees and the included angle between the circumscribed rectangle and the vertical direction is determined to be 60 degrees, the qualification image can be rotated by 30 degrees toward the horizontal direction, so that the qualification image is parallel to the horizontal direction. Correspondingly, the characters in the qualification image can be made to be non-upright and vertical to the horizontal direction, as shown in (b) of fig. 1. At this time, the characters in the rotated qualification image are not upright, thereby influencing the identification of the information in the qualification image.
Alternatively, fig. 3 is a schematic diagram of a variation of a qualification image in the prior art. As shown in fig. 3 (a), the qualification image is inclined at 60 degrees to the horizontal direction and 30 degrees to the vertical direction. And correspondingly, the included angle between the external rectangle and the horizontal direction is 60 degrees, and the included angle between the external rectangle and the vertical direction is 30 degrees, so that the qualification image can be rotated by 30 degrees towards the vertical direction, and the qualification image is parallel to the vertical direction. However, although the text line in the rotated qualified image is parallel to the horizontal direction, the text direction is inverted and not upright, as shown in (b) of fig. 3, and the rotated qualified image also affects the recognition of the information in the qualified image.
As shown in fig. 1 to 3, in the prior art, only tilt correction within plus and minus 45 degrees is performed, and tilt correction of multiples of 90 degrees is not supported, which may cause non-upright characters in the corrected images in fig. 2 and 3, which may result in failure of tilt correction, further affecting information recognition.
The reason for influencing the recognition of information in the prior art is that the characters in the tilt-corrected image are inverted or perpendicular to the horizontal direction. In order to make the characters in the image after the tilt correction stand upright so as to facilitate the identification of information, the application provides a scheme for further rotating the image after the tilt correction based on the character direction, so that the characters in the image after the rotation stand upright, and the purpose of correcting the tilt of the image by 90-degree multiples is realized.
It should be understood that the method for image tilt correction provided in the present application is not only suitable for tilt correction of qualified images, but also suitable for tilt correction of images containing text. Optionally, the tilt correction method for an image to be processed in this embodiment may be applied to a scene in which a user needs to perform tilt correction on a captured image, or may also be applied to a scene in which an image uploaded by the user is subjected to tilt correction first and then to further processing, where the "further processing" may be to identify information in the image, or to perform scanning version and PDF version conversion on the image.
The following describes the method for correcting image tilt provided by the present application with reference to specific embodiments. Fig. 4 is a flowchart illustrating a first embodiment of a method for image tilt correction according to the present application. The main body of execution of the method flow shown in fig. 4 may be the image tilt correction device, which may be implemented by any software and/or hardware. As shown in fig. 4, the method for correcting image tilt provided by this embodiment may include:
s401, according to the circumscribed rectangles of the text lines in the image to be processed, rotation processing is carried out on the image to be processed, an initial correction image of the image to be processed is obtained, and the circumscribed rectangles of the text lines in the initial correction image are perpendicular to or parallel to the horizontal direction.
It should be understood that the circumscribed rectangle of the text line in the image to be processed in this embodiment may be the smallest circumscribed rectangle of the text line in the image to be processed. Optionally, the manner of determining the minimum bounding rectangle of the text line in the image to be processed may be: and carrying out binarization processing on the image to be processed, further acquiring a foreground region and a background region of the image to be processed, further carrying out contour extraction on the foreground region, and generating a circumscribed rectangle of the contour, namely the circumscribed rectangle of the text line in the image to be processed.
In this embodiment, the image to be processed may be rotated according to an included angle between a circumscribed rectangle of a text line in the image to be processed and the horizontal direction and the vertical direction, so as to obtain an initial corrected image of the image to be processed. Wherein, the circumscribed rectangle of the text line in the initial correction image is vertical or parallel to the horizontal direction.
Optionally, in order to reduce the influence of the rotation processing on the image to be processed, in this embodiment, a smaller angle among included angles between a circumscribed rectangle of the text line in the image to be processed and the horizontal direction and the vertical direction may be determined, so as to rotate the image to be processed. For example, if the included angle between the circumscribed rectangle of the text line in the image to be processed and the horizontal direction is 20 degrees and the included angle between the circumscribed rectangle of the text line in the image to be processed and the vertical direction is 80 degrees, the image to be processed may be rotated by 20 degrees to obtain an initial corrected image, and the circumscribed rectangle of the text line in the initial corrected image is parallel to the horizontal direction.
Illustratively, as shown in (b) of fig. 1 to 3, the circumscribed rectangle of the text line in the initial corrected image in the present embodiment is perpendicular or parallel to the horizontal direction.
S402, if the direction of the characters in the text line in the initial correction image is not upright, rotating the initial correction image to obtain a correction image of the image to be processed, wherein the direction of the characters in the text line in the correction image is upright.
In this embodiment, the rotation process may be performed on the initial corrected image if the direction of the characters in the text line in the initial corrected image is not vertical by identifying the direction of the characters in the text line in the initial corrected image. Alternatively, the orientation of the text in the lines of text in the initial corrected image may be identified by Optical Character Recognition (OCR) techniques.
It should be understood that, in the present embodiment, the OCR technology is not directly used to recognize the character direction in the text line in the image to be processed, but the character direction in the text line in the initial corrected image is recognized, and the rotation is further performed on the basis of the initial corrected image because the recognition accuracy of the OCR technology for the character directions of 0 degree, 90 degrees, 180 degrees, and 270 degrees is higher than that of the character directions of common angles (e.g., 1 degree-89 degrees, 91 degrees-179 degrees, etc.).
In this embodiment, when it is determined that the direction of the text in the text line in the initial corrected image is not upright, the initial corrected image may be rotated to obtain a corrected image of the image to be processed. Wherein, the text direction of the text line in the corrected image obtained by rotation is upright.
For example, as shown in (b) of fig. 1, it may be determined that the direction of the text in the text line in the initial corrected image is upright, and the direction of the text in the text line in (b) of fig. 2 and 3 is not upright, by using the OCR technology, the (b) of fig. 2 and 3 (i.e., the initial corrected image) is rotated to obtain the corrected image. Fig. 5 is a schematic diagram of a corrected image provided in the present application. As shown in fig. 5, the text line in the rotated image (b) in fig. 2 and 3 has an upright text direction.
The method for correcting the image inclination provided by the embodiment comprises the following steps: according to the circumscribed rectangles of the text lines in the image to be processed, carrying out rotation processing on the image to be processed to obtain an initial correction image of the image to be processed, wherein the circumscribed rectangles of the text lines in the initial correction image are vertical or parallel to the horizontal direction; and if the direction of the characters in the text line in the initial correction image is not upright, performing rotation processing on the initial correction image to obtain a correction image of the image to be processed, wherein the direction of the characters in the text line in the correction image is upright. According to the method, after the image is rotated according to the circumscribed rectangle of the text line in the image to be processed, the image can be further rotated by a large angle according to the character direction in the rotated image, so that the character direction in the rotated image is upright.
On the basis of the above-described embodiment, a description is given below of how to acquire an initial correction image and a correction image of an image to be processed.
Fig. 6 is a schematic flowchart of the process for obtaining an initial corrected image according to the present application. As shown in fig. 6, the S401 may include:
s4011, obtaining a minimum angle among included angles between a circumscribed rectangle of each text line in the image to be processed and the horizontal direction and the vertical direction.
In this embodiment, a plurality of circumscribed rectangles of the text line in the image to be processed are obtained, and the minimum angle among the included angles between the circumscribed rectangle of each text line and the horizontal direction and the vertical direction is obtained. In this embodiment, an included angle between the circumscribed rectangle of each text line and the horizontal direction and an included angle between the circumscribed rectangle of each text line and the vertical direction may be set, and further, a minimum angle among the included angles between the circumscribed rectangle of each text line and the horizontal direction and the vertical direction may be determined.
For example, taking the circumscribed rectangle of a text line as an example, the included angles between the circumscribed rectangle of the text line and the horizontal direction and the included angles between the circumscribed rectangle of the text line and the vertical direction are respectively 30 degrees and 60 degrees, and then the minimum angle between the circumscribed rectangle of the text line and the included angles between the circumscribed rectangle of the text line and the horizontal direction and the vertical direction is determined to be 30 degrees.
S4012, the smallest angle with the largest number is used as the first rotation angle.
Accordingly, the minimum angle among the included angles between the circumscribed rectangle of each text line and the horizontal direction and the vertical direction can be obtained, and the minimum angle with the largest number is taken as the first rotation angle in the present embodiment.
Illustratively, if the number of the minimum angles is 10, and the number of the minimum angles is 1, 30 degrees may be used as the first rotation angle.
And S4013, rotating the image to be processed by a first rotation angle to obtain an initial correction image.
In this embodiment, after the first rotation angle is determined, the image to be processed may be rotated by the first rotation angle to obtain an initial corrected image.
For example, if the included angle with the horizontal direction is 30 degrees, which is the first rotation angle, the image to be processed may be rotated 30 degrees beyond the horizontal direction, so as to obtain an initial corrected image in which the circumscribed rectangle of the text line is parallel to the horizontal direction.
Optionally, before S4011, may further include;
s4014, performing contour detection on the binary image of the image to be processed, and acquiring a target contour of the text line, wherein the area of the target contour is within a preset area range, and the length-width ratio of the target contour is within a preset proportion range.
In this embodiment, the image to be processed may be compressed to a preset size, and then the compressed image may be binarized to obtain a binarized image. The purpose of compressing the image to be processed to the preset size is to process the binary image by adopting a preset expansion corrosion factor. Due to the expansion corrosion of the binary image, the foreground region and the background region can be effectively distinguished by adopting a proper expansion corrosion factor. In order to avoid complex operation of selecting a proper expansion corrosion factor for binarized images with different sizes, in the embodiment, an image to be processed is compressed to a preset size, and after the binarized image is formed, the binarized image can be processed by adopting a preset expansion corrosion factor, so that the operation of selecting the proper expansion corrosion factor can be avoided, the preset expansion corrosion factor is suitable for the binarized image with the size, and a good effect of distinguishing a foreground area from a background area can be achieved.
Further, contour detection can be performed on the binary image of the image to be processed, and a target contour of the text line can be obtained. It should be noted that, when performing contour detection on the binarized image of the image to be processed, contours of a plurality of text lines may be obtained, in this embodiment, the area and the aspect ratio of the contour of each text line are obtained, and the contour of the text line whose area is within a preset area range and aspect ratio is within a preset proportion range is taken as a target contour.
In this embodiment, the purpose of setting the preset area range and the preset proportion range is to filter the foreground region of the non-text line. For example, the qualification image may include images such as a user's head portrait and a frame, and these objects are not text detection objects, and the directions of these objects cannot be determined by using the OCR technology, so these interference objects are filtered in this embodiment. For example, the aspect ratio of the frame is large, the area of the user head portrait is large, and the foreground region of the non-text line can be filtered by adopting the setting.
S4015, generating a circumscribed rectangle of the target outline, wherein the circumscribed rectangle of the target outline is the circumscribed rectangle of the text line in the image to be processed.
Optionally, in this embodiment, the non-important text lines may be further filtered in the circumscribed rectangle, and the circumscribed rectangle of the important text lines is retained. The center position of the image to be processed can be determined, and then the circumscribed rectangle with the distance from the center position of the image to be processed being larger than the first preset distance is filtered. It should be understood that the circumscribed rectangle having a distance from the center position of the image to be processed greater than the first preset distance is an insignificant text line. In this embodiment, a distance from a circumscribed rectangle of the target contour to a center position of the image to be processed is smaller than a first preset distance.
In this embodiment, the manner of determining the center position of the image to be processed may specifically adopt the following formula one and formula two:
wherein X is the abscissa of the central position of the image to be processed, Y is the ordinate of the central position of the image to be processed, n is the number of circumscribed rectangles of the text lines, i is greater than or equal to 0 and less than or equal to n, and XiMean value of the abscissa, y, of a circumscribed rectangle of any one line of textiIs the mean of the ordinate of the circumscribed rectangle of any one line of text.
The distance from the circumscribed rectangle of each text line to the center position of the image to be processed can be obtained according to the following formula three:
wherein d isiIs the distance from the circumscribed rectangle of any one text line to the center position of the image to be processed.
It should be understood that the circumscribed rectangle of the target outline in the present embodiment is the circumscribed rectangle of the text line in the image to be processed in the above embodiment.
Optionally, fig. 7 is a schematic flowchart of a process for acquiring a corrected image according to the present application. As shown in fig. 7, the S402 may include:
s4021, taking the circumscribed rectangle of the text line within a second preset distance range from the center position of the initial corrected image as a target circumscribed rectangle.
In this embodiment, the center position of the image to be processed may be determined according to the abscissa and the ordinate of the circumscribed rectangle. Optionally, in this embodiment, the center position of the image to be processed may be obtained according to the same manner as in the above formula one and formula two.
Further, the distance from the circumscribed rectangle of the text line to the center position of the initial corrected image may be obtained according to the formula three, and the circumscribed rectangle of the text line within a second preset distance range from the center position of the initial corrected image may be used as the target circumscribed rectangle in this embodiment.
S4022, acquiring an included angle between the text direction and the horizontal direction of the text line in the target circumscribed rectangle.
In this embodiment, an OCR technology may be adopted to obtain an included angle between a text direction and a horizontal direction of a text line in a circumscribed rectangle of a target. The included angle may be 90 degrees, 180 degrees, 270 degrees.
S4023, taking the included angle with the largest number as a second rotation angle.
In this embodiment, the largest number of included angles is taken as the second rotation angle. Illustratively, if the number of included angles is 1 in the 90-degree range and the number of included angles is 10 in the 180-degree range, 180 degrees is taken as the second rotation angle.
S4024, rotating the initial corrected image by a second rotation angle to obtain a corrected image.
In this embodiment, the initial corrected image is rotated by a second rotation angle to obtain a corrected image with upright text direction.
The method for image tilt correction provided by the present application is further described in detail below with reference to fig. 8. Fig. 8 is a flowchart illustrating a second embodiment of a method for image tilt correction according to the present application. As shown in fig. 8, the method for correcting image tilt provided by the present embodiment may include:
s801, receiving an image to be processed input by a user.
The image in this embodiment may be a qualified image. When the user needs to verify the qualified image, the to-be-processed image can be uploaded to the image tilt correction device. And correspondingly. The means for image tilt correction may receive the image to be processed.
Fig. 9 is a schematic view of an interface change of the image tilt correction apparatus provided in the present application. Illustratively, the interface has an upload control displayed thereon, as shown at 901 in fig. 9. And the user can upload the image to be processed by clicking or selecting the uploading control in other operation modes. It should be understood that fig. 9 illustrates an example in which the apparatus for image tilt correction is a smartphone.
S802, according to the circumscribed rectangles of the text lines in the image to be processed, the image to be processed is rotated to obtain an initial correction image of the image to be processed, and the circumscribed rectangles of the text lines in the initial correction image are vertical or parallel to the horizontal direction.
And S803, if the direction of the characters in the text line in the initial corrected image is not upright, performing rotation processing on the initial corrected image to obtain a corrected image of the image to be processed, wherein the direction of the characters in the text line in the corrected image is upright.
It should be understood that, in this embodiment, the implementation manners in S802 to S803 may specifically refer to the descriptions related to S401 to S402 in the foregoing embodiments, and are not described herein again.
S804, identifying the qualification information in the corrected image, authenticating the qualification information in the corrected image, and outputting a qualification authentication result.
In this embodiment, the image after the tilt correction, i.e., the corrected image, may be identified to identify the qualification information in the corrected image. The qualification information may be data of the user or the enterprise represented in the corrected image, such as a user name, an identification number, a residence address, an enterprise name, an enterprise unified social credit code, and the like. In this embodiment, details of identifying the qualification information in the corrected image are not repeated, and specific reference may be made to the related description of the identification method in the prior art.
The qualification information in the corrected image is authenticated, namely the qualification information in the corrected image is compared with officially stored data. And after the comparison is completed, a qualification authentication result can be output. And if the qualification information in the corrected image is not consistent with the officially stored data, the qualification authentication result is authentication failure.
For example, if the qualification authentication result is that the authentication is successful, the interface 901 may jump to the interface 902, and a text prompt message of "authentication is successful" is displayed on the interface 902. Optionally, the interface 902 may be also displayed with an uploaded image to be processed in front, as shown in the interface 903.
In this embodiment, the qualification information in the image to be processed input by the user may be authenticated after performing tilt correction on the image to be processed, and in view of the fact that the tilt correction of the image to be processed by a multiple of 90 degrees may be performed in this embodiment, the identification accuracy of the qualification information in this embodiment may be improved, and the accuracy of the qualification authentication result may be further improved.
Fig. 10 is a schematic structural diagram of an image tilt correction apparatus provided in the present application. As shown in fig. 10, the image tilt correction 1000 includes: a processing module 1001 and a transceiver module 1002.
The processing module 1001 is configured to perform rotation processing on the image to be processed according to the circumscribed rectangle of the text line in the image to be processed to obtain an initial corrected image of the image to be processed, where the circumscribed rectangle of the text line in the initial corrected image is perpendicular to or parallel to the horizontal direction, and if the direction of the text in the text line in the initial corrected image is not upright, perform rotation processing on the initial corrected image to obtain a corrected image of the image to be processed, where the direction of the text in the corrected image is upright.
Optionally, a plurality of circumscribed rectangles of the text lines in the image to be processed are provided.
Correspondingly, the processing module 1001 is specifically configured to obtain a minimum angle among included angles between a circumscribed rectangle of each text line in the image to be processed and the horizontal direction and the vertical direction; taking the minimum angle with the largest number as a first rotation angle; and rotating the image to be processed by a first rotation angle to obtain an initial correction image.
Optionally, the processing module 1001 is further configured to perform contour detection on the binary image of the image to be processed, to obtain a target contour of the text line, where an area of the target contour is within a preset area range, and an aspect ratio of the target contour is within a preset proportion range; and generating a circumscribed rectangle of the target outline, wherein the circumscribed rectangle of the target outline is the circumscribed rectangle of the text line in the image to be processed.
Optionally, the processing module 1001 is further configured to compress the image to be processed to a preset size; carrying out binarization processing on the compressed image to obtain a binarized image; and carrying out corrosion expansion processing on the foreground region in the binary image according to a preset expansion corrosion factor so as to obtain the binary image of the image to be processed.
Optionally, the processing module 1001 is further configured to determine a center position of the image to be processed; and filtering the circumscribed rectangle with the distance from the central position of the image to be processed being larger than a first preset distance.
Optionally, the processing module 1001 is specifically configured to take a circumscribed rectangle of the text line within a second preset distance range from the center position of the initial corrected image as a target circumscribed rectangle; acquiring an included angle between the text direction and the horizontal direction of a text line in a target circumscribed rectangle; taking the included angle with the largest number as a second rotation angle; and rotating the initial correction image by a second rotation angle to obtain a correction image.
Optionally, the processing module 1001 is specifically configured to determine a center position of the image to be processed according to an abscissa and an ordinate of the circumscribed rectangle.
The transceiving module 1001 is configured to receive an image to be processed input by a user.
Optionally, the processing module 1001 is further configured to identify qualification information in the corrected image; and authenticating the qualification information in the corrected image and outputting a qualification authentication result.
The principle and technical effect of the image tilt correction apparatus provided in this embodiment are similar to those of the image tilt correction method, and are not described herein again.
According to an embodiment of the present application, an electronic device and a readable storage medium are also provided.
Fig. 11 is a schematic structural diagram of an electronic device provided in the present application. As shown in fig. 11, is a block diagram of an electronic device of a method of image tilt correction according to an embodiment of the present application. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the present application that are described and/or claimed herein.
As shown in fig. 11, the electronic apparatus includes: one or more processors 1101, a memory 1102, and interfaces for connecting the various components, including a high speed interface and a low speed interface. The various components are interconnected using different buses and may be mounted on a common motherboard or in other manners as desired. The processor may process instructions for execution within the electronic device, including instructions stored in or on the memory to display graphical information of a GUI on an external input/output apparatus (such as a display device coupled to the interface). In other embodiments, multiple processors and/or multiple buses may be used, along with multiple memories and multiple memories, as desired. Also, multiple electronic devices may be connected, with each device providing portions of the necessary operations (e.g., as a server array, a group of blade servers, or a multi-processor system). In fig. 11, a processor 1101 is taken as an example.
The memory 1102 is a non-transitory computer readable storage medium as provided herein. Wherein the memory stores instructions executable by at least one processor to cause the at least one processor to perform the method of image tilt correction provided herein. The non-transitory computer readable storage medium of the present application stores computer instructions for causing a computer to perform the method of image tilt correction provided herein.
The memory 1102, which is a non-transitory computer readable storage medium, may be used to store non-transitory software programs, non-transitory computer executable programs, and modules, such as program instructions/modules corresponding to the method of image tilt correction in the embodiments of the present application. The processor 1101 executes various functional applications of the server and data processing, i.e., a method of image tilt correction in the above-described method embodiments, by running non-transitory software programs, instructions, and modules stored in the memory 1102.
The memory 1102 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created according to use of an electronic device for performing the method for image tilt correction, and the like. Further, the memory 1102 may include high speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, the memory 1102 optionally includes memory located remotely from the processor 1101, which may be connected via a network to an electronic device for performing the method of image tilt correction. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The electronic device of the method of image tilt correction may further include: an input device 1103 and an output device 1104. The processor 1101, the memory 1102, the input device 1103 and the output device 1104 may be connected by a bus or other means, and are exemplified by being connected by a bus in fig. 11.
The input device 1103 may receive input numeric or character information and generate key signal inputs related to user settings and function controls of the electronic apparatus for performing the method of image tilt correction, such as a touch screen, a keypad, a mouse, a track pad, a touch pad, a pointer, one or more mouse buttons, a track ball, a joystick, or the like. The output devices 1104 may include a display device, auxiliary lighting devices (e.g., LEDs), tactile feedback devices (e.g., vibrating motors), and the like. The display device may include, but is not limited to, a Liquid Crystal Display (LCD), a Light Emitting Diode (LED) display, and a plasma display. In some implementations, the display device can be a touch screen.
Various implementations of the systems and techniques described here can be realized in digital electronic circuitry, integrated circuitry, application specific ASICs (application specific integrated circuits), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.
These computer programs (also known as programs, software applications, or code) include machine instructions for a programmable processor, and may be implemented using high-level procedural and/or object-oriented programming languages, and/or assembly/machine languages. As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, apparatus, and/or device (e.g., magnetic discs, optical disks, memory, Programmable Logic Devices (PLDs)) used to provide machine instructions and/or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal used to provide machine instructions and/or data to a programmable processor.
To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), Wide Area Networks (WANs), and the Internet.
The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other.
It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present application may be executed in parallel, sequentially, or in different orders, and the present invention is not limited thereto as long as the desired results of the technical solutions disclosed in the present application can be achieved.
The above-described embodiments should not be construed as limiting the scope of the present application. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims (12)
1. A method of image tilt correction, comprising:
according to the circumscribed rectangles of the text lines in the image to be processed, carrying out rotation processing on the image to be processed to obtain an initial correction image of the image to be processed, wherein the circumscribed rectangles of the text lines in the initial correction image are vertical or parallel to the horizontal direction;
and if the direction of the characters in the text line in the initial correction image is not upright, performing rotation processing on the initial correction image to obtain a correction image of the image to be processed, wherein the direction of the characters in the text line in the correction image is upright.
2. The method according to claim 1, wherein the text line in the image to be processed is multiple, and the rotating the image to be processed according to the circumscribed rectangle of the text line in the image to be processed to obtain the initial corrected image of the image to be processed comprises:
acquiring the minimum angle among included angles of a circumscribed rectangle of each text line in the image to be processed and the horizontal direction and the vertical direction;
taking the minimum angle with the largest number as a first rotation angle;
and rotating the image to be processed by the first rotation angle to obtain the initial correction image.
3. The method according to claim 2, wherein before obtaining the minimum angle of the horizontal direction and the vertical direction of the bounding rectangle of the text line in each of the images to be processed, the method further comprises:
carrying out contour detection on the binary image of the image to be processed to obtain a target contour of a text line, wherein the area of the target contour is within a preset area range, and the length-width ratio of the target contour is within a preset proportion range;
and generating a circumscribed rectangle of the target outline, wherein the circumscribed rectangle of the target outline is the circumscribed rectangle of the text line in the image to be processed.
4. The method according to claim 3, wherein before the contour detection of the binarized image of the image to be processed, the method comprises:
compressing the image to be processed to a preset size;
carrying out binarization processing on the compressed image to obtain a binarized image;
and carrying out corrosion expansion processing on the foreground region in the binary image according to a preset expansion corrosion factor so as to obtain the binary image of the image to be processed.
5. The method of claim 3, wherein after the generating the circumscribed rectangle of the target contour, further comprising:
determining the central position of the image to be processed;
and filtering the circumscribed rectangle with the distance from the central position of the image to be processed being larger than a first preset distance.
6. The method according to any one of claims 1 to 5, wherein if the direction of the text in the text line in the initial corrected image is not upright, performing rotation processing on the initial corrected image to obtain a corrected image of the image to be processed comprises:
taking a circumscribed rectangle of the text line within a second preset distance range from the center position of the initial correction image as a target circumscribed rectangle;
acquiring an included angle between the text direction and the horizontal direction of the text line in the target circumscribed rectangle;
taking the included angle with the largest number as a second rotation angle;
and rotating the initial correction image by the second rotation angle to obtain the correction image.
7. The method according to claim 6, wherein before the step of taking the circumscribed rectangle of the text line within a second preset distance range from the center position of the initial corrected image as the target circumscribed rectangle, the step of further comprises:
and determining the central position of the image to be processed according to the abscissa and the ordinate of the circumscribed rectangle.
8. The method according to claim 1, wherein before performing rotation processing on the image to be processed according to the circumscribed rectangle of the text line in the image to be processed, the method comprises:
and receiving the image to be processed input by a user.
9. The method according to claim 1, wherein the image to be processed is a qualified image, and after obtaining the corrected image of the image to be processed, the method further comprises:
identifying qualification information in the corrected image;
and authenticating the qualification information in the corrected image and outputting a qualification authentication result.
10. An apparatus for image tilt correction, comprising:
the processing module is used for performing rotation processing on the image to be processed according to the external rectangle of the text line in the image to be processed to obtain an initial correction image of the image to be processed, and performing rotation processing on the initial correction image to obtain a correction image of the image to be processed if the direction of characters in the text line in the initial correction image is not upright, wherein the external rectangle of the text line in the initial correction image is vertical or parallel to the horizontal direction, and the direction of characters in the text line in the correction image is upright.
11. An electronic device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-9.
12. A non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of any one of claims 1-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010027521.1A CN111260569B (en) | 2020-01-10 | 2020-01-10 | Image tilt correction method, image tilt correction device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010027521.1A CN111260569B (en) | 2020-01-10 | 2020-01-10 | Image tilt correction method, image tilt correction device, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111260569A true CN111260569A (en) | 2020-06-09 |
| CN111260569B CN111260569B (en) | 2023-09-01 |
Family
ID=70946859
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010027521.1A Active CN111260569B (en) | 2020-01-10 | 2020-01-10 | Image tilt correction method, image tilt correction device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111260569B (en) |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111767859A (en) * | 2020-06-30 | 2020-10-13 | 北京百度网讯科技有限公司 | Method, apparatus, electronic device, and computer-readable storage medium for image correction |
| CN111783761A (en) * | 2020-06-30 | 2020-10-16 | 苏州科达科技股份有限公司 | Certificate text detection method and device and electronic equipment |
| CN111832561A (en) * | 2020-07-03 | 2020-10-27 | 深圳思谋信息科技有限公司 | Character sequence recognition method, device, equipment and medium based on computer vision |
| CN111914836A (en) * | 2020-07-08 | 2020-11-10 | 浙江大华技术股份有限公司 | Identity card information extraction method, device, equipment and medium |
| CN112150380A (en) * | 2020-09-22 | 2020-12-29 | 北京百度网讯科技有限公司 | Method and device for correcting image, electronic equipment and readable storage medium |
| CN112241737A (en) * | 2020-11-12 | 2021-01-19 | 瞬联软件科技（北京）有限公司 | Character image correction method and device |
| CN112766266A (en) * | 2021-01-29 | 2021-05-07 | 云从科技集团股份有限公司 | Text direction correction method, system and device based on staged probability statistics |
| CN112926579A (en) * | 2021-03-05 | 2021-06-08 | 中国工商银行股份有限公司 | Text image correction method, text image correction device, computer system and readable storage medium |
| CN113420762A (en) * | 2021-07-01 | 2021-09-21 | 京东科技控股股份有限公司 | Image processing method, system, electronic equipment and storage medium |
| CN114140794A (en) * | 2021-11-26 | 2022-03-04 | 北京比特易湃信息技术有限公司 | General image correction method based on OCR |
| CN114267046A (en) * | 2021-12-31 | 2022-04-01 | 上海合合信息科技股份有限公司 | Method and device for orientation correction of document image |
| CN115050037A (en) * | 2021-02-25 | 2022-09-13 | 华为技术有限公司 | Card text recognition method, device and storage medium |
| CN115457559A (en) * | 2022-08-19 | 2022-12-09 | 上海通办信息服务有限公司 | Method, device and equipment for intelligently correcting text and license pictures |
| WO2023010546A1 (en) * | 2021-08-06 | 2023-02-09 | 时善乐 | Image correction system and method therefor |
| CN116152820A (en) * | 2022-10-10 | 2023-05-23 | 马上消费金融股份有限公司 | Image correction method and device, model training method, text recognition method |
| CN118747899A (en) * | 2024-06-28 | 2024-10-08 | 南京市智慧医疗投资运营服务有限公司 | Method and system for recognizing detailed expense list based on OCR and LLM |
| US12555261B2 (en) | 2022-11-24 | 2026-02-17 | L&T Technology Services Limited | Method and system for detecting and correcting orientation of document images |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH11338973A (en) * | 1998-05-22 | 1999-12-10 | Fujitsu Ltd | Document image correction apparatus and document image correction method |
| US6804414B1 (en) * | 1998-05-01 | 2004-10-12 | Fujitsu Limited | Image status detecting apparatus and document image correcting apparatus |
| CN106295638A (en) * | 2016-07-29 | 2017-01-04 | 北京小米移动软件有限公司 | Certificate image sloped correcting method and device |
| CN110188747A (en) * | 2019-04-28 | 2019-08-30 | 广州华多网络科技有限公司 | A kind of sloped correcting method of text image, device and image processing equipment |
| CN110647882A (en) * | 2019-09-20 | 2020-01-03 | 上海眼控科技股份有限公司 | Image correction method, device, equipment and storage medium |
-
2020
- 2020-01-10 CN CN202010027521.1A patent/CN111260569B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6804414B1 (en) * | 1998-05-01 | 2004-10-12 | Fujitsu Limited | Image status detecting apparatus and document image correcting apparatus |
| JPH11338973A (en) * | 1998-05-22 | 1999-12-10 | Fujitsu Ltd | Document image correction apparatus and document image correction method |
| CN106295638A (en) * | 2016-07-29 | 2017-01-04 | 北京小米移动软件有限公司 | Certificate image sloped correcting method and device |
| CN110188747A (en) * | 2019-04-28 | 2019-08-30 | 广州华多网络科技有限公司 | A kind of sloped correcting method of text image, device and image processing equipment |
| CN110647882A (en) * | 2019-09-20 | 2020-01-03 | 上海眼控科技股份有限公司 | Image correction method, device, equipment and storage medium |
Cited By (31)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111783761A (en) * | 2020-06-30 | 2020-10-16 | 苏州科达科技股份有限公司 | Certificate text detection method and device and electronic equipment |
| CN111767859A (en) * | 2020-06-30 | 2020-10-13 | 北京百度网讯科技有限公司 | Method, apparatus, electronic device, and computer-readable storage medium for image correction |
| WO2022002262A1 (en) * | 2020-07-03 | 2022-01-06 | 深圳思谋信息科技有限公司 | Character sequence recognition method and apparatus based on computer vision, and device and medium |
| CN111832561A (en) * | 2020-07-03 | 2020-10-27 | 深圳思谋信息科技有限公司 | Character sequence recognition method, device, equipment and medium based on computer vision |
| JP7429307B2 (en) | 2020-07-03 | 2024-02-07 | 深▲セン▼思謀信息科技有限公司 | Character string recognition method, device, equipment and medium based on computer vision |
| CN111832561B (en) * | 2020-07-03 | 2021-06-08 | 深圳思谋信息科技有限公司 | Character sequence recognition method, device, equipment and medium based on computer vision |
| JP2023523745A (en) * | 2020-07-03 | 2023-06-07 | 深▲セン▼思謀信息科技有限公司 | Character string recognition method, apparatus, equipment and medium based on computer vision |
| CN111914836A (en) * | 2020-07-08 | 2020-11-10 | 浙江大华技术股份有限公司 | Identity card information extraction method, device, equipment and medium |
| CN111914836B (en) * | 2020-07-08 | 2024-09-03 | 浙江大华技术股份有限公司 | Method, device, equipment and medium for extracting identity card information |
| CN112150380A (en) * | 2020-09-22 | 2020-12-29 | 北京百度网讯科技有限公司 | Method and device for correcting image, electronic equipment and readable storage medium |
| CN112150380B (en) * | 2020-09-22 | 2024-04-16 | 北京百度网讯科技有限公司 | Method, device, electronic device and readable storage medium for correcting image |
| CN112241737B (en) * | 2020-11-12 | 2024-01-26 | 瞬联软件科技（北京）有限公司 | Text and image correction method and device |
| WO2022100698A1 (en) * | 2020-11-12 | 2022-05-19 | 瞬联软件科技（北京）有限公司 | Text image correction method and apparatus |
| CN112241737A (en) * | 2020-11-12 | 2021-01-19 | 瞬联软件科技（北京）有限公司 | Character image correction method and device |
| CN112766266B (en) * | 2021-01-29 | 2021-12-10 | 云从科技集团股份有限公司 | Text direction correction method, system and device based on staged probability statistics |
| CN112766266A (en) * | 2021-01-29 | 2021-05-07 | 云从科技集团股份有限公司 | Text direction correction method, system and device based on staged probability statistics |
| CN115050037A (en) * | 2021-02-25 | 2022-09-13 | 华为技术有限公司 | Card text recognition method, device and storage medium |
| CN112926579B (en) * | 2021-03-05 | 2025-07-29 | 中国工商银行股份有限公司 | Text image correction method, device, computer system and readable storage medium |
| CN112926579A (en) * | 2021-03-05 | 2021-06-08 | 中国工商银行股份有限公司 | Text image correction method, text image correction device, computer system and readable storage medium |
| CN113420762A (en) * | 2021-07-01 | 2021-09-21 | 京东科技控股股份有限公司 | Image processing method, system, electronic equipment and storage medium |
| CN113420762B (en) * | 2021-07-01 | 2024-02-06 | 京东科技控股股份有限公司 | Image processing method, system, electronic equipment and storage medium |
| GB2623688A (en) * | 2021-08-06 | 2024-04-24 | Shan Le Shih | Image correction system and method therefor |
| WO2023010546A1 (en) * | 2021-08-06 | 2023-02-09 | 时善乐 | Image correction system and method therefor |
| CN114140794A (en) * | 2021-11-26 | 2022-03-04 | 北京比特易湃信息技术有限公司 | General image correction method based on OCR |
| CN114267046A (en) * | 2021-12-31 | 2022-04-01 | 上海合合信息科技股份有限公司 | Method and device for orientation correction of document image |
| CN115457559A (en) * | 2022-08-19 | 2022-12-09 | 上海通办信息服务有限公司 | Method, device and equipment for intelligently correcting text and license pictures |
| CN115457559B (en) * | 2022-08-19 | 2024-01-16 | 上海通办信息服务有限公司 | Method, device and equipment for intelligently correcting texts and license pictures |
| CN116152820A (en) * | 2022-10-10 | 2023-05-23 | 马上消费金融股份有限公司 | Image correction method and device, model training method, text recognition method |
| US12555261B2 (en) | 2022-11-24 | 2026-02-17 | L&T Technology Services Limited | Method and system for detecting and correcting orientation of document images |
| CN118747899A (en) * | 2024-06-28 | 2024-10-08 | 南京市智慧医疗投资运营服务有限公司 | Method and system for recognizing detailed expense list based on OCR and LLM |
| CN118747899B (en) * | 2024-06-28 | 2026-01-30 | 南京市智慧医疗投资运营服务有限公司 | A Method and System for Recognizing Expense Details Based on OCR and LLM |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111260569B (en) | 2023-09-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111260569A (en) | Method and device for correcting image inclination, electronic equipment and storage medium | |
| CN112149636B (en) | Method, device, electronic device and storage medium for detecting target object | |
| CN111523468B (en) | Human key point recognition method and device | |
| JP7389824B2 (en) | Object identification method and device, electronic equipment and storage medium | |
| US9058536B1 (en) | Image-based character recognition | |
| US10452953B2 (en) | Image processing device, image processing method, program, and information recording medium | |
| US10943107B2 (en) | Simulating image capture | |
| US11700417B2 (en) | Method and apparatus for processing video | |
| US20220215507A1 (en) | Image stitching | |
| CN112241716B (en) | Method and device for generating training samples | |
| US11200414B2 (en) | Process for capturing content from a document | |
| CN111524165B (en) | Target tracking method and device | |
| CN109118233B (en) | Authentication method and device based on face recognition | |
| CN112149583A (en) | Smoke detection method, terminal device and storage medium | |
| WO2015074405A1 (en) | Methods and devices for obtaining card information | |
| CN111507924B (en) | Video frame processing method and device | |
| CN111523292B (en) | Method and device for obtaining image information | |
| JP2017120455A (en) | Information processing device, program and control method | |
| CN111552829A (en) | Method and apparatus for analyzing image material | |
| CN111709979A (en) | Method, apparatus, electronic device and storage medium for image alignment | |
| US9330310B2 (en) | Methods and devices for obtaining card information | |
| US10356318B1 (en) | Long document capture on mobile devices | |
| CN112991179B (en) | Method, apparatus, device and storage medium for outputting information | |
| CN117061875A (en) | Intelligent teller machine camera pose adjusting method and device, electronic equipment and medium | |
| CN112101368A (en) | Character image processing method, device, equipment and medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |