CN103702024B - Image processing apparatus and image processing method - Google Patents

Abstract

The present invention provides an image processing device, comprising: an image acquisition unit, used to acquire any stored image; a correction judgment unit, used to judge whether there is an area to be corrected in the stored image; an image correction unit, used to A perfect area corresponding to the area to be corrected is extracted from the re-taken image to replace the area to be corrected. The invention also proposes a corresponding image processing method. Through the technical solution of the present invention, the unsatisfactory part in the image can be replaced by way of supplementary shooting, so as to obtain an image meeting the user's requirement.

Description

Image processing device and image processing method

technical field

The present invention relates to the technical field of image processing, and in particular, to an image processing device and an image processing method.

Background technique

When a user uses a camera device to take pictures, such as a camera, mobile phone, tablet computer, etc., due to the shaking of the photographer's body, the movement of the subject's limbs, etc., or due to reasons such as poor shooting environment, the captured image may be Among them, although there are no problems in most areas, there are various unsatisfactory conditions such as unclearness, discontinuity, and image distortion in a small number of areas.

After the above situation occurs, users often can only re-shoot the entire image, but good shooting opportunities are always fleeting. If you want to shoot the same scene again, you may even have to wait for a long time, which will affect the user experience .

Therefore, how to correct the captured image to eliminate the unsatisfactory area without re-shooting the entire image has become a technical problem to be solved urgently.

Contents of the invention

Based on the above problems, the present invention proposes a new image processing technology, which can replace unsatisfactory parts in the image by way of supplementary shooting, so as to obtain an image that meets the needs of users.

In view of this, the present invention proposes an image processing device, comprising: an image acquisition unit for acquiring any stored image; a correction judging unit for judging whether there is an area to be corrected in the stored image; image correction A unit, configured to extract a perfect area corresponding to the area to be corrected from the retaken image to replace the area to be corrected.

In this technical solution, when it is not easy to re-shoot all the shooting elements in the stored image, especially when the shooting objects in the stored image are not easy to be shot and need to wait for a long time, etc., through Detects the area to be corrected in the stored image and replaces it with the perfect area in the recaptured image, so that only part of the area needs to be corrected, while other parts of the stored image do not need to be modified, and there is no need to retake the entire image image, and can obtain an image that satisfies the user by partially correcting the stored image.

Wherein, the number of regions to be corrected on each stored image may be one or multiple, and the size of each region to be corrected and the number of photographing elements contained therein are not limited.

In the above technical solution, preferably, further comprising: an area selection unit, configured to receive an area selection instruction, and use the area selected on the stored image according to the area selection instruction as the area to be corrected; or according to The area selection instruction executes an element selection operation on the stored image, and uses the area including the selected shooting element as the area to be corrected.

In this technical solution, in one case, the user can select an area on the stored image, so that the selected area is used as the area to be corrected. Specifically, the user can directly draw a gesture track and form a selection area from the gesture track as the area to be corrected; or, the terminal can provide some preset graphics, such as rectangles, circles, etc., and the user can drag these The position of the graphics and the size of these graphics are changed, so that the corresponding area of these graphics on the stored image is used as the area to be corrected.

In another case, the user can select the shooting element on the stored image, for example, click on the shooting element on the stored image, then by identifying the shooting element on the stored image, the clicked element can be determined. Capture elements and corresponding areas to be corrected.

It should be noted that the shooting element can be a scene or object, such as a person or a building, or a certain part of the scene or object, such as the human eye part or the door frame part of the building, etc., which can be adjusted according to the actual situation. selection and accuracy.

In any of the above technical solutions, preferably, it includes: an element identification unit, configured to identify the captured elements on the stored image; a boundary judging unit, configured to detect the boundaries of the captured elements, and determine whether the captured elements Whether the characteristic attribute of the boundary of the element meets the preset attribute requirement; wherein, when the photographing element does not meet the preset attribute requirement, the correction judging unit takes the area containing the photographing element as the to-be-corrected area.

In this technical solution, the unfavorable conditions that may exist in the shooting elements, such as the blurring, discontinuity, and ghosting of the shooting elements caused by the shake of the photographer or the movement of the shooting elements at the moment of shooting, will be reflected in the On the boundary feature of the photographing element, through the boundary detection of the photographing element and the judgment of the characteristic attribute of the boundary, more unfavorable conditions can be identified, and corresponding regions to be corrected can be generated.

In any of the above technical solutions, preferably, the feature attributes include: continuity and/or clarity of boundaries.

In this technical solution, when the boundary is discontinuous, there may be ghosting, blurring, etc. of the shooting element; the definition of the boundary can be obtained by detecting the width of the boundary. For example, when blurring occurs, the boundary width of the shooting element may be Larger, and may present such as color gradients, etc., which can be used to generate the corresponding area to be corrected.

In any of the above technical solutions, preferably, further comprising: an image comparison unit, configured to compare the stored image with the current image received by the image sensor of the image processing device when the stored image is captured. The images are compared; wherein, when the correction judging unit determines that there is an inconsistency between the stored image and the current image, the correction judging unit takes the area containing the same photographic element as the area to be corrected.

In this technical solution, the stored image may be an image that has been taken previously, or it may refer to an image that has just been taken, and the photographer still maintains a photographing posture. In the latter case, the terminal can use the The stored image is compared with the image received by the image sensor, and if there is a difference, it indicates that there may be situations such as blurred photographed elements, ghosting, etc., and a corresponding area to be corrected can be formed.

In any of the above technical solutions, preferably, further comprising: an element search unit, configured to search for the element in the image received by the image sensor of the image processing device in the case of receiving an instruction for confirming to retake the image The shooting elements in the area to be corrected; the prompting unit is used to give corresponding prompt information according to the search result; the element comparison unit is used to find the shooting elements in the area to be corrected by the element search unit , comparing the found photographing elements with the original photographing elements in the region to be corrected; wherein, the prompting unit is further configured to give corresponding prompt information according to the comparison result.

In this technical solution, if re-shooting is required, the photographer can be reminded by identifying the image received by the image sensor and finding out the shooting elements contained therein. Wherein, if the image received by the current image sensor does not contain the shooting elements in the area to be corrected, the photographer is prompted to change the shooting object; if the image received by the current image sensor contains the shooting elements in the area to be corrected, the photographer is prompted to take pictures to avoid shooting mistakes. Wherein, the prompt information may include any one or more of text, sound, and image.

As a more preferred way, for example, the photographing elements in the image sensor can be identified, and the boundary shape of the photographing elements in the area to be corrected is displayed in the image received by the image sensor, thus prompting the user that the photographing element has been captured Elements can be used for shooting operations.

At the same time, for the same shooting element, there are still differences in shooting angle, shooting position, focal length parameters, etc. Therefore, by comparing the stored image with the real-time image received by the image sensor, and giving prompt information according to the comparison result, For example, the user is prompted to adjust the shooting angle, adjust the angle, etc., so as to ensure that the re-shot image can be better integrated with the stored image, and ensure that the correction of the area to be corrected will not affect the overall coordination of the stored image.

Wherein, when prompting, only the shooting parameters corresponding to the stored images may be prompted, or the difference between the shooting parameters of the stored images and the current shooting parameters may be prompted, and corresponding adjustment suggestions may be directly given based on the above differences . The prompting method may also include any one or more of text, sound, and image.

The present invention also proposes an image processing method, including: acquiring any stored image; if there is an area to be corrected in the stored image, extracting a perfect area corresponding to the area to be corrected from the re-shot image , to replace the area to be corrected.

In this technical solution, when it is not easy to re-shoot all the shooting elements in the stored image, especially when the shooting objects in the stored image are not easy to be shot and need to wait for a long time, etc., through Detects the area to be corrected in the stored image and replaces it with the perfect area in the recaptured image, so that only part of the area needs to be corrected, while other parts of the stored image do not need to be modified, and there is no need to retake the entire image image, and can obtain an image that satisfies the user by partially correcting the stored image.

Wherein, the number of regions to be corrected on each stored image may be one or multiple, and the size of each region to be corrected and the number of photographing elements contained therein are not limited.

In any of the above technical solutions, preferably, it includes: receiving an area selection instruction, using the area selected on the stored image according to the area selection instruction as the area to be corrected; or according to the area selection instruction. An element selection operation is performed on the stored image, and an area including the selected shooting element is used as the area to be corrected.

In this technical solution, in one case, the user can select an area on the stored image, so that the selected area is used as the area to be corrected. Specifically, the user can directly draw a gesture track and form a selection area from the gesture track as the area to be corrected; or, the terminal can provide some preset graphics, such as rectangles, circles, etc., and the user can drag these The position of the graphics and the size of these graphics are changed, so that the corresponding area of these graphics on the stored image is used as the area to be corrected.

In another case, the user can select the shooting element on the stored image, for example, click on the shooting element on the stored image, then by identifying the shooting element on the stored image, the clicked element can be determined. Capture elements and corresponding areas to be corrected.

It should be noted that the shooting element can be a scene or object, such as a person or a building, or a certain part of the scene or object, such as the human eye part or the door frame part of the building, etc., which can be adjusted according to the actual situation. selection and accuracy.

In any of the above technical solutions, preferably, it includes: identifying the captured elements on the stored image; detecting the boundaries of the captured elements, and judging whether the characteristic attributes of the boundaries of the captured elements meet preset attributes Requirement; if not satisfied, the area containing the photographing element is taken as the area to be corrected.

In this technical solution, the unfavorable conditions that may exist in the shooting elements, such as the blurring, discontinuity, and ghosting of the shooting elements caused by the shake of the photographer or the movement of the shooting elements at the moment of shooting, will be reflected in the On the boundary feature of the photographing element, through the boundary detection of the photographing element and the judgment of the characteristic attribute of the boundary, more unfavorable conditions can be identified, and corresponding regions to be corrected can be generated.

In any of the above technical solutions, preferably, the feature attributes include: continuity and/or clarity of boundaries.

In this technical solution, when the boundary is discontinuous, there may be ghosting, blurring, etc. of the shooting element; the definition of the boundary can be obtained by detecting the width of the boundary. For example, when blurring occurs, the boundary width of the shooting element may be Larger, and may present such as color gradients, etc., which can be used to generate the corresponding area to be corrected.

In any of the above technical solutions, preferably, it includes: when the stored image is captured, comparing the stored image with the current image received by the image sensor of the shooting device; When the stored image is inconsistent with the current image, the area including the same photographic element is used as the area to be corrected.

In this technical solution, the stored image may be an image that has been taken previously, or it may refer to an image that has just been taken, and the photographer still maintains a photographing posture. In the latter case, the terminal can use the The stored image is compared with the image received by the image sensor, and if there is a difference, it indicates that there may be situations such as blurred photographed elements, ghosting, etc., and a corresponding area to be corrected can be formed.

In any of the above technical solutions, preferably, further comprising: when receiving an instruction for confirming to retake the image, searching for the photographing element in the area to be corrected in the image received by the image sensor of the photographing device, and according to the search As a result, corresponding prompt information is given; when the photographing elements in the area to be corrected are found, compare the found photographing elements with the original photographing elements in the area to be corrected, and according to the comparison result, give corresponding prompt information.

In this technical solution, if re-shooting is required, the photographer can be reminded by identifying the image received by the image sensor and finding out the shooting elements contained therein. Wherein, if the image received by the current image sensor does not contain the shooting elements in the area to be corrected, the photographer is prompted to change the shooting object; if the image received by the current image sensor contains the shooting elements in the area to be corrected, the photographer is prompted to take pictures to avoid shooting mistakes. Wherein, the prompt information may include any one or more of text, sound, and image.

As a more preferred way, for example, the photographing elements in the image sensor can be identified, and the boundary shape of the photographing elements in the area to be corrected is displayed in the image received by the image sensor, thus prompting the user that the photographing element has been captured Elements can be used for shooting operations.

At the same time, for the same shooting element, there are still differences in shooting angle, shooting position, focal length parameters, etc. Therefore, by comparing the stored image with the real-time image received by the image sensor, and giving prompt information according to the comparison result, For example, the user is prompted to adjust the shooting angle, adjust the angle, etc., so as to ensure that the re-shot image can be better integrated with the stored image, and ensure that the correction of the area to be corrected will not affect the overall coordination of the stored image.

Wherein, when prompting, only the shooting parameters corresponding to the stored images may be prompted, or the difference between the shooting parameters of the stored images and the current shooting parameters may be prompted, and corresponding adjustment suggestions may be directly given based on the above differences . The prompting method may also include any one or more of text, sound, and image.

Through the above technical solution, the unsatisfactory part in the image can be replaced by way of supplementary shooting, so as to obtain an image meeting the user's needs.

Description of drawings

Fig. 1 shows a schematic block diagram of an image processing device according to an embodiment of the present invention;

Fig. 2 shows a schematic flowchart of an image processing method according to an embodiment of the present invention;

3 to 8 show schematic diagrams of implementing image correction through region replacement according to an embodiment of the present invention.

detailed description

In order to understand the above-mentioned purpose, features and advantages of the present invention more clearly, the present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that, in the case of no conflict, the embodiments of the present application and the features in the embodiments can be combined with each other.

In the following description, many specific details are set forth in order to fully understand the present invention. However, the present invention can also be implemented in other ways different from those described here. Therefore, the protection scope of the present invention is not limited by the specific details disclosed below. EXAMPLE LIMITATIONS.

Fig. 1 shows a schematic block diagram of an image processing device according to an embodiment of the present invention.

As shown in FIG. 1 , the image processing device 100 according to the embodiment of the present invention includes: an image acquisition unit 102 for acquiring any stored image; a correction judgment unit 104 for judging whether there is The region to be corrected: an image correction unit 106, configured to extract a perfect region corresponding to the region to be corrected from the re-taken image to replace the region to be corrected.

In this technical solution, when it is not easy to re-shoot all the shooting elements in the stored image, especially when the shooting objects in the stored image are not easy to be shot and need to wait for a long time, etc., through Detects the area to be corrected in the stored image and replaces it with the perfect area in the recaptured image, so that only part of the area needs to be corrected, while other parts of the stored image do not need to be modified, and there is no need to retake the entire image image, and can obtain an image that satisfies the user by partially correcting the stored image.

Wherein, the number of regions to be corrected on each stored image may be one or multiple, and the size of each region to be corrected and the number of photographing elements contained therein are not limited.

In the above technical solution, preferably, it includes: a mode switching unit 108, configured to enter the image correction mode according to the received mode switching instruction; an area selection unit 110, configured to enter the image correction mode according to the received area selection instruction. The region to be corrected is determined on the stored image.

In this technical solution, by setting different modes, it is helpful to avoid false touches, especially for touch screen terminals, which helps to reduce the occurrence of false operations. Among them, the mode switching instruction can be issued manually by the user, for example, the user can issue the instruction by clicking a virtual button on the screen, drawing a preset gesture track on the screen, etc.; the mode switching instruction can also be issued by the terminal itself For example, after each image capture is completed, the captured image will be displayed on the terminal screen, then the image correction mode can be entered by default at this time.

By receiving an area selection instruction issued by the user, the user can independently check the stored image to determine whether there is an area to be corrected, so as to realize the selection of the area to be corrected.

In any of the above technical solutions, preferably, the area selection unit 110 is configured to: use the area selected on the stored image according to the area selection instruction as the area to be corrected; The instruction executes an element selection operation on the stored image, and uses the area containing the selected shooting element as the area to be corrected.

In this technical solution, in one case, the user can select an area on the stored image, so that the selected area is used as the area to be corrected. Specifically, the user can directly draw a gesture track and form a selection area from the gesture track as the area to be corrected; or, the terminal can provide some preset graphics, such as rectangles, circles, etc., and the user can drag these The position of the graphics and the size of these graphics are changed, so that the corresponding area of these graphics on the stored image is used as the area to be corrected.

In another case, the user can select the shooting element on the stored image, for example, click on the shooting element on the stored image, then by identifying the shooting element on the stored image, the clicked element can be determined. Capture elements and corresponding areas to be corrected.

It should be noted that the shooting element can be a scene or object, such as a person or a building, or a certain part of the scene or object, such as the human eye part or the door frame part of the building, etc., which can be adjusted according to the actual situation. selection and accuracy.

In any of the above technical solutions, preferably, it includes: an element identification unit 112, configured to identify the captured elements on the stored image; a boundary judging unit 114, configured to detect the boundaries of the captured elements, and determine the Whether the characteristic attribute of the boundary of the photographed element meets the preset attribute requirements; wherein, the correction judgment unit 104 takes the area containing the photographed element as the Describe the area to be corrected.

In this technical solution, the unfavorable conditions that may exist in the shooting elements, such as the blurring, discontinuity, and ghosting of the shooting elements caused by the shake of the photographer or the movement of the shooting elements at the moment of shooting, will be reflected in the On the boundary feature of the photographing element, through the boundary detection of the photographing element and the judgment of the characteristic attribute of the boundary, more unfavorable conditions can be identified, and corresponding regions to be corrected can be generated.

In any of the above technical solutions, preferably, the feature attributes include: continuity and/or clarity of boundaries.

In this technical solution, when the boundary is discontinuous, there may be ghosting, blurring, etc. of the shooting element; the definition of the boundary can be obtained by detecting the width of the boundary. For example, when blurring occurs, the boundary width of the shooting element may be Larger, and may present such as color gradients, etc., which can be used to generate the corresponding area to be corrected.

In any of the above technical solutions, preferably, it further includes: an image comparison unit 116, configured to compare the stored image with the image received by the image sensor of the image processing device when the stored image is captured. The current image is compared; wherein, when the correction judging unit 104 determines that there is an inconsistency between the stored image and the current image, the correction judging unit 104 takes an area containing the same imaging element as the area to be corrected.

In this technical solution, the stored image may be an image that has been taken previously, or it may refer to an image that has just been taken, and the photographer still maintains a photographing posture. In the latter case, the terminal can use the The stored image is compared with the image received by the image sensor, and if there is a difference, it indicates that there may be situations such as blurred photographed elements, ghosting, etc., and a corresponding area to be corrected can be formed.

In any of the above technical solutions, preferably, further comprising: an element labeling unit 118, configured to mark the region to be corrected and/or the region to be corrected in the stored image when it is determined that the region to be corrected exists Mark the shooting elements in the area to be corrected.

In this technical solution, by marking the area to be corrected and/or the shooting elements therein, it is helpful to prompt the user, so that the image can be improved as much as possible by means of correction. There are many ways to mark, such as displaying a preset icon at the position that needs to be marked, or displaying the boundary of the area to be corrected and/or the shooting elements in the stored image, or through other text, sound, image and so on to remind users. Of course, the above-mentioned methods such as displaying borders are not necessarily edits to the stored image itself, but can be used as a display method in the case of viewing or previewing, such as using it as a superimposed image on the stored image. Layers display patterns, etc.

In any of the above technical solutions, preferably, further comprising: an element search unit 120, configured to search for an element in the image received by the image sensor of the image processing device 100 in the case of receiving an instruction to confirm that the image is retaken. The shooting elements in the area to be corrected; the prompting unit 122, configured to give corresponding prompting information according to the search result.

In this technical solution, if re-shooting is required, the photographer can be reminded by identifying the image received by the image sensor and finding out the shooting elements contained therein. Wherein, if the image received by the current image sensor does not contain the shooting elements in the area to be corrected, the photographer is prompted to change the shooting object; if the image received by the current image sensor contains the shooting elements in the area to be corrected, the photographer is prompted to take pictures to avoid shooting mistakes. Wherein, the prompt information may include any one or more of text, sound, and image.

As a more preferred way, for example, the photographing elements in the image sensor can be identified, and the boundary shape of the photographing elements in the area to be corrected is displayed in the image received by the image sensor, thus prompting the user that the photographing element has been captured Elements can be used for shooting operations.

In any of the above technical solutions, preferably, further comprising: an element comparing unit 124, configured to compare the found photographing element with The original photographed elements in the area to be corrected are compared; wherein, the prompt unit 122 is further configured to give corresponding prompt information according to the comparison result.

In this technical solution, for the same shooting element, there are still differences in shooting angle, shooting position, focal length parameters, etc. Prompt information, such as reminding the user to adjust the shooting angle, adjust the angle, etc., so as to ensure that the re-taken image can be better integrated with the stored image, and ensure that after the correction of the area to be corrected, the overall coordination of the stored image will not be affected. sex affects.

Wherein, when prompting, only the shooting parameters corresponding to the stored images may be prompted, or the difference between the shooting parameters of the stored images and the current shooting parameters may be prompted, and corresponding adjustment suggestions may be directly given based on the above differences . The prompting method may also include any one or more of text, sound, and image.

Fig. 2 shows a schematic flowchart of an image processing method according to an embodiment of the present invention.

As shown in FIG. 2 , the image processing method according to the embodiment of the present invention includes: step 202, acquiring any stored image; step 204, if there is an area to be corrected in the stored image, then Extracting a perfect region corresponding to the region to be corrected to replace the region to be corrected.

In this technical solution, when it is not easy to re-shoot all the shooting elements in the stored image, especially when the shooting objects in the stored image are not easy to be shot and need to wait for a long time, etc., through Detects the area to be corrected in the stored image and replaces it with the perfect area in the recaptured image, so that only part of the area needs to be corrected, while other parts of the stored image do not need to be modified, and there is no need to retake the entire image image, and can obtain an image that satisfies the user by partially correcting the stored image.

Wherein, the number of regions to be corrected on each stored image may be one or multiple, and the size of each region to be corrected and the number of photographing elements contained therein are not limited.

In the above technical solution, preferably, it includes: entering the image correction mode according to the received mode switching instruction; and determining the region to be corrected on the stored image according to the received region selection instruction.

In this technical solution, by setting different modes, it is helpful to avoid false touches, especially for touch screen terminals, which helps to reduce the occurrence of false operations. Among them, the mode switching instruction can be issued manually by the user, for example, the user can issue the instruction by clicking a virtual button on the screen, drawing a preset gesture track on the screen, etc.; the mode switching instruction can also be issued by the terminal itself For example, after each image capture is completed, the captured image will be displayed on the terminal screen, then the image correction mode can be entered by default at this time.

By receiving an area selection instruction issued by the user, the user can independently check the stored image to determine whether there is an area to be corrected, so as to realize the selection of the area to be corrected.

In any of the above-mentioned technical solutions, preferably, it includes: taking the area selected on the stored image according to the area selection instruction as the area to be corrected; or selecting the stored image according to the area selection instruction An element selection operation is performed, and an area including the selected shooting element is used as the area to be corrected.

In this technical solution, in one case, the user can select an area on the stored image, so that the selected area is used as the area to be corrected. Specifically, the user can directly draw a gesture track and form a selection area from the gesture track as the area to be corrected; or, the terminal can provide some preset graphics, such as rectangles, circles, etc., and the user can drag these The position of the graphics and the size of these graphics are changed, so that the corresponding area of these graphics on the stored image is used as the area to be corrected.

In another case, the user can select the shooting element on the stored image, for example, click on the shooting element on the stored image, then by identifying the shooting element on the stored image, the clicked element can be determined. Capture elements and corresponding areas to be corrected.

It should be noted that the shooting element can be a scene or object, such as a person or a building, or a certain part of the scene or object, such as the human eye part or the door frame part of the building, etc., which can be adjusted according to the actual situation. selection and accuracy.

In any of the above technical solutions, preferably, it includes: identifying the captured elements on the stored image; detecting the boundaries of the captured elements, and judging whether the characteristic attributes of the boundaries of the captured elements meet preset attributes Requirement; if not satisfied, the area containing the photographing element is taken as the area to be corrected.

In this technical solution, the unfavorable conditions that may exist in the shooting elements, such as the blurring, discontinuity, and ghosting of the shooting elements caused by the shake of the photographer or the movement of the shooting elements at the moment of shooting, will be reflected in the On the boundary feature of the photographing element, through the boundary detection of the photographing element and the judgment of the characteristic attribute of the boundary, more unfavorable conditions can be identified, and corresponding regions to be corrected can be generated.

In any of the above technical solutions, preferably, the feature attributes include: continuity and/or clarity of boundaries.

In this technical solution, when the boundary is discontinuous, there may be ghosting, blurring, etc. of the shooting element; the definition of the boundary can be obtained by detecting the width of the boundary. For example, when blurring occurs, the boundary width of the shooting element may be Larger, and may present such as color gradients, etc., which can be used to generate the corresponding area to be corrected.

In any of the above technical solutions, preferably, it includes: when the stored image is captured, comparing the stored image with the current image received by the image sensor of the shooting device; When the stored image is inconsistent with the current image, the area including the same photographic element is used as the area to be corrected.

In this technical solution, the stored image may be an image that has been taken previously, or it may refer to an image that has just been taken, and the photographer still maintains a photographing posture. In the latter case, the terminal can use the The stored image is compared with the image received by the image sensor, and if there is a difference, it indicates that there may be situations such as blurred photographed elements, ghosting, etc., and a corresponding area to be corrected can be formed.

In any of the above technical solutions, preferably, further comprising: if there is the region to be corrected, marking the region to be corrected and/or the shooting elements in the region to be corrected in the stored image .

In this technical solution, by marking the area to be corrected and/or the shooting elements therein, it is helpful to prompt the user, so that the image can be improved as much as possible by means of correction. There are many ways to mark, such as displaying a preset icon at the position that needs to be marked, or displaying the boundary of the area to be corrected and/or the shooting elements in the stored image, or through other text, sound, image and so on to remind users. Of course, the above-mentioned methods such as displaying borders are not necessarily edits to the stored image itself, but can be used as a display method in the case of viewing or previewing, such as using it as a superimposed image on the stored image. Layers display patterns, etc.

In any of the above technical solutions, preferably, further comprising: when receiving an instruction for confirming to retake the image, searching for the shooting elements in the area to be corrected in the image received by the image sensor of the shooting device; according to the search result , give the corresponding prompt information.

In this technical solution, if re-shooting is required, the photographer can be reminded by identifying the image received by the image sensor and finding out the shooting elements contained therein. Wherein, if the image received by the current image sensor does not contain the shooting elements in the area to be corrected, the photographer is prompted to change the shooting object; if the image received by the current image sensor contains the shooting elements in the area to be corrected, the photographer is prompted to take pictures to avoid shooting mistakes. Wherein, the prompt information may include any one or more of text, sound, and image.

As a more preferred way, for example, the photographing elements in the image sensor can be identified, and the boundary shape of the photographing elements in the area to be corrected is displayed in the image received by the image sensor, thus prompting the user that the photographing element has been captured Elements can be used for shooting operations.

In any of the above technical solutions, preferably, further comprising: when the photographing elements in the area to be corrected are found, comparing the found photographing elements with the original photographing elements in the area to be corrected; As a result, a corresponding prompt message is given.

In this technical solution, for the same shooting element, there are still differences in shooting angle, shooting position, focal length parameters, etc. Prompt information, such as reminding the user to adjust the shooting angle, adjust the angle, etc., so as to ensure that the re-taken image can be better integrated with the stored image, and ensure that after the correction of the area to be corrected, the overall coordination of the stored image will not be affected. sex affects.

Wherein, when prompting, only the shooting parameters corresponding to the stored images may be prompted, or the difference between the shooting parameters of the stored images and the current shooting parameters may be prompted, and corresponding adjustment suggestions may be directly given based on the above differences . The prompting method may also include any one or more of text, sound, and image.

The technical solution of the image processing based on the present invention will be described in detail below with reference to FIG. 3 to FIG. 8 , wherein FIG. 3 to FIG. 8 show schematic diagrams of implementing image correction through region replacement according to an embodiment of the present invention.

When using a terminal to take photos, such as cameras, mobile phones, tablet phones, tablet computers, etc., due to the instability of the photographer when holding the terminal, or the instantaneous movement of the object being photographed, etc., the photos often appear blurred and ghosting And so on, making the photos unsatisfactory.

Re-shooting is of course an option; but sometimes the shooting scene contains a lot of shooting elements, and the combined state of these shooting elements at that time may not be very easy to reproduce, and in addition to some unsatisfactory parts in the image , other parts may still be desirable, so the present invention hopes to avoid reshooting the entire image by only replacing some unsatisfactory parts in the image.

For example, as shown in FIG. 3 , after using the terminal to shoot, the obtained image is displayed on the terminal desktop. Wherein, due to the movement of the upper limbs of the animal in the image at the moment of shooting, the consequences of ghosting and blurring are formed in the image, then this part of the image constitutes the area to be corrected 302, which needs to be supplemented by shooting this part. Implement replacement.

Based on the above technical solutions and objectives, the implementation process of the solutions will be introduced in detail below from several relevant aspects and in combination with specific implementation modes.

1. Select an area

Embodiment one

In order to reduce the calculation amount of the terminal and better meet the user's own needs, it is obvious that the user should select and determine the location of the region to be corrected 302 by himself.

As shown in Figure 4, in one case, the user can directly select the image that needs to be corrected, such as drawing a corresponding gesture track 304 on the image, then the terminal will directly generate the image shown in Figure 3 based on the gesture track 304. The region to be corrected 302 is shown.

Of course, the user can directly draw the gesture trajectory 304 forming a closed figure as shown in FIG. not shown), then the area formed by the line segment, the right border of the screen, and the lower border of the screen is the area to be corrected 302 as shown in FIG. 3 .

In another case, the user does not need to draw the gesture track 304 as shown in FIG. 4, but as shown in FIG. After one graphic, drag it to the area to be corrected, and adjust the size of the graphic, then the finally obtained area graphic 306 corresponds to the area to be corrected 302 as shown in FIG. 3 .

Embodiment two

Based on some detection or identification algorithms, the terminal can also realize automatic identification and acquisition of the region to be corrected 302 in the image.

In one case, a boundary detection algorithm can be used. When the shooting element in the image appears blurred due to shaking, shaking, etc., there are some preset characteristics in the feature attribute of the boundary of the shooting element. For example, as shown in FIG. 6 , for situations such as “blurring”, it will cause the boundary of the captured element to be identified to become wider, that is, the value of the boundary width 308 in FIG. 6 becomes larger, for example, greater than the boundary width of other captured elements in the image, or It is larger than the border width of other parts of the same shooting element, or larger than the preset width threshold, or the difference with the border width of the same shooting element or other shooting elements is larger than the preset threshold, etc.

The judgment method based on the border width 308 is actually one of the judgment methods for whether the border is clear; in fact, other different judgment methods such as whether the border is continuous can also be used to judge whether the shooting elements in the image need Correction is performed for automatic judgment.

In another case (not shown in the figure), in addition to the judgment based on the boundary algorithm, automatic judgment of the terminal may also be realized based on other characteristics of the photographed object. For example, by presetting the preset conditions of each characteristic attribute of the photographed element in the image, and judging whether the real-time condition of the corresponding characteristic attribute in the current image satisfies the preset condition, it is determined whether correction is required.

Specifically, for example, for the relatively common situation of "blinking" in taking pictures, that is, the person in the image "blinks" at the moment of shooting, resulting in the state of "closed eyes" of the person in the captured image. Thus, the determination of the "closed eyes" situation is involved here.

First, based on the currently mature "face recognition" algorithm, determine the "face" in the image; then, based on the preset feature parameters for the "eyes", such as the upper middle part of the "face", left and right One each, black, etc. (for example only), identifying whether there is an object matching the above characteristics on this "face". If it exists, it means that there is no image problem. If it does not exist, there may be a "blinking" situation, and the terminal directly takes the user's "face" part or the user as a whole as the image to be corrected as shown in Figure 3. Area 302.

2. Determine the object

Based on the above-mentioned first embodiment, since the user manually selects, the region 302 to be corrected as shown in Figure 3 can be directly generated; and based on the above-mentioned second embodiment, that is, when the terminal automatically judges, it involves the area to be corrected The specific shooting elements included in the area 302.

For example, for the image shown in FIG. 3 , assuming that the upper limbs of the animal in the image are blurred, when the image is recaptured, only the blurred upper limbs can be photographed, or the entire animal can be recaptured.

For example, as shown in FIG. 7 , the photographing element 310A includes the whole of the animal shown in FIG. 3 , while the photographing element 310B is only the upper limb of the animal shown in FIG. 3 . By reacquiring the photographing element 310B, the correction of the original image shown in FIG. 3 is reduced as much as possible; and by recapturing the photographing element 310A, when the blurred upper limb of the animal affects other parts, it can be minimized. impact, and helps to ensure the overall coordination of the animal being photographed.

3. Tips for shooting

As shown in FIG. 8, when the user determines that it is necessary to take a new shot, the terminal can check the original shot element 312 in the area to be corrected 302 shown in FIG. may not be displayed), and compared with the current shooting element 314 in the image received by the current image sensor to determine whether the two match in shooting angle, distance, light, white balance, focal length and other shooting parameters. If there is a difference, you can Give certain hints to the user. For example, in FIG. 8 , by displaying prompt information 316 on the terminal interface, the user is prompted to move in a corresponding direction so that the current photographing element 314 coincides with the original photographing element 312 .

Of course, there are many specific prompting methods. For example, the original shooting element 312 and the current shooting element 314 can also be displayed on the terminal at the same time, and when the two overlap, the user will be given a corresponding prompt, such as flashing, warning, vibration Wait.

At the same time, for the above-mentioned shooting parameters, for the part that the terminal can adjust by itself, the terminal can perform automatic adjustment as much as possible, so as to reduce the manual operation of the user and reduce the complexity of the operation.

Finally, when the shooting parameters are consistent or matched, or when the user thinks it is appropriate, re-shooting is performed, and the terminal automatically intercepts the perfect area corresponding to the area to be corrected 302 shown in FIG. 3 from the re-shot image , use the perfect area to replace the area to be corrected 302, and use the obtained image as the final processed image.

The technical solution of the present invention has been described in detail above in conjunction with the accompanying drawings. The present invention proposes an image processing device and an image processing method, which can replace the unsatisfactory parts of the image by way of supplementary shooting, so as to obtain the required image.

The above descriptions are only preferred embodiments of the present invention, and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and changes. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention shall be included within the protection scope of the present invention.

Claims (8)

1. a kind of image processing apparatus, it is characterised in that including：

Image acquisition unit, for obtaining any storage image；

Amendment judging unit, for judging to whether there is positive region to be repaired in the storage image；

Image correction unit, region is improved for being extracted from the image for re-shooting corresponding to the positive region to be repaired, with Replace the positive region to be repaired；

Elemental recognition unit, for identifying the shooting element in the storage image；

Border judging unit, for detecting the border of the shooting element, and judges the feature category on the border of the shooting element Whether property meets default attribute specification；

Wherein, the amendment judging unit, will be comprising institute in the case where the shooting element is unsatisfactory for default attribute specification The region for shooting element is stated as the positive region to be repaired.

2. image processing apparatus according to claim 1, it is characterised in that also include：

Area selecting unit, for receiving area selection instruction, and will store figure according to regional choice instruction described The region chosen on picture is used as the positive region to be repaired；

Or element selection operation is performed to the storage image according to regional choice instruction, and by comprising selected bat The region of element is taken the photograph as the positive region to be repaired.

3. image processing apparatus according to claim 1, it is characterised in that also include：

Image comparing unit, for when shooting obtains the storage image, will be at the storage image and described image The present image received in the imageing sensor for managing device is compared；

Wherein, it is determined that there is same shooting element in the storage image and the present image in the amendment judging unit In it is inconsistent when, using comprising the same region for shooting element as the positive region to be repaired.

4. image processing apparatus according to any one of claim 1 to 3, it is characterised in that also include：

Element searching unit, in the case where the instruction for confirming to re-shoot image is received, being filled in described image treatment The shooting element in the positive region to be repaired is searched in the image that the imageing sensor put is received；

Tip element, for according to lookup result, providing corresponding prompt message；

Element comparing unit, for finding the positive region to be repaired in the element searching unit in shooting element situation Under, the shooting element that will be found is compared with the original shooting element in the positive region to be repaired；

Wherein, the Tip element is additionally operable to according to comparative result, provides corresponding prompt message.

5. a kind of image processing method, it is characterised in that including：

Obtain any storage image；

If there is positive region to be repaired in the storage image, extracted corresponding to described to be modified from the image for re-shooting Region is improved in region, replacing the positive region to be repaired；

Identify the shooting element in the storage image；

Detection is described to shoot the border of element, and judges whether the characteristic attribute on the border of the shooting element meets default category Property require；

If it is not satisfied, then using the region comprising the shooting element as the positive region to be repaired.

6. image processing method according to claim 5, it is characterised in that including：

Receiving area selection instruction, will be according to the regional choice region chosen in the storage image of instruction as institute State positive region to be repaired；

Or element selection operation is performed to the storage image according to regional choice instruction, and by comprising selected bat The region of element is taken the photograph as the positive region to be repaired.

7. image processing method according to claim 5, it is characterised in that including：

When shooting obtains the storage image, will be received in the imageing sensor of the storage image with capture apparatus Present image be compared；

If it is same shooting element it is inconsistent in the storage image and the present image when, will be comprising the same shooting The region of element is used as the positive region to be repaired.

8. the image processing method according to any one of claim 5 to 7, it is characterised in that also include：

When receive confirm to re-shoot the instruction of image when, searched in the image that receives of imageing sensor of capture apparatus Shooting element in the positive region to be repaired, and according to lookup result, provide corresponding prompt message；And

When the shooting element in finding the positive region to be repaired, in the shooting element that will be found and the positive region to be repaired Original shooting element be compared, and according to comparative result, provide corresponding prompt message.