CN111161208A - Image detection method and device - Google Patents
Image detection method and device Download PDFInfo
- Publication number
- CN111161208A CN111161208A CN201911150261.0A CN201911150261A CN111161208A CN 111161208 A CN111161208 A CN 111161208A CN 201911150261 A CN201911150261 A CN 201911150261A CN 111161208 A CN111161208 A CN 111161208A
- Authority
- CN
- China
- Prior art keywords
- chip
- target
- image
- detected
- coordinate
- 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.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
- G06T7/0008—Industrial image inspection checking presence/absence
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
-
- 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
- G06T2207/30108—Industrial image inspection
- G06T2207/30148—Semiconductor; IC; Wafer
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Geometry (AREA)
- Quality & Reliability (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
本公开涉及图像处理技术领域，尤其涉及一种图像检测方法和装置。该方法根据待测目标的目标图像判断待测目标上是否存在芯片，并在待测目标上存在芯片时，通过判断芯片的坐标与参考坐标之间的偏移量来确定芯片的位置是否存在缺陷，在待测目标上未设置芯片时，通过判断待测目标上锡膏点的尺寸是否在第一预设阈值区间内来确定锡膏点的尺寸是否存在缺陷，可以快速地自动对待测目标即电子元器件进行缺陷检测，可以节省人工，提高工作效率。
The present disclosure relates to the technical field of image processing, and in particular, to an image detection method and device. The method judges whether there is a chip on the target to be tested according to the target image of the target to be tested, and when there is a chip on the target to be tested, determines whether there is a defect in the position of the chip by judging the offset between the coordinates of the chip and the reference coordinates , when no chip is set on the target to be tested, by judging whether the size of the solder paste spot on the target to be tested is within the first preset threshold range to determine whether the size of the solder paste spot is defective, the target to be tested can be quickly and automatically Defect detection of electronic components can save labor and improve work efficiency.
Description
Technical Field
The present disclosure relates to the field of image processing technologies, and in particular, to an image detection method and apparatus.
Background
The electronic components are basic components of various electronic products, and the defect screening of the electronic components is very important for the product performance of the electronic products. Along with the continuous deepening of the industrial transformation and upgrading in China, the miniaturization and chip-type trend of electronic components is increasingly remarkable, the screening mode of manual visual inspection under a microscope is gradually highlighted by the influence of objective limitations of worker experience, working time and the like, and the method is not suitable for the detection requirements of high efficiency, high precision and low cost.
Disclosure of Invention
In order to solve at least one of the above technical problems, the present disclosure provides an image detection method and apparatus.
In one aspect, an embodiment of the present disclosure provides an image detection method, including:
acquiring a target image, wherein the target image is an image of a target to be detected;
judging whether a chip is arranged on the target to be detected or not according to the target image;
if the target to be detected is provided with a chip, judging whether the offset between the coordinate of the chip and the reference coordinate is greater than or equal to a first preset threshold value; if so, determining that the chip position has a defect;
if the target to be detected is not provided with a chip, judging whether the size of the solder paste point on the target to be detected is within a first preset threshold interval or not; if not, there is a defect in determining the size of the solder paste dot.
Optionally, the determining whether a chip is disposed on the target to be detected according to the target image includes:
acquiring a first image characteristic of a first preset area in a target image;
acquiring second image characteristics of a second preset area in the first template image;
if the similarity of the first image characteristic and the second image characteristic is not smaller than a second preset threshold value, determining that a chip is arranged on the target to be detected; otherwise, determining that no chip is arranged on the target to be detected.
Optionally, the determining whether a chip is disposed on the target to be detected according to the target image includes:
acquiring a first image characteristic of a first preset area in a target image;
acquiring a third image characteristic of a third preset area in the second template image;
if the similarity of the first image characteristic and the third image characteristic is not smaller than a third preset threshold, determining that no chip is arranged on the target to be detected; otherwise, determining that the chip is arranged on the target to be detected.
Optionally, before determining whether an offset between the coordinates of the chip and the reference coordinates is greater than or equal to a first preset threshold, the method includes:
acquiring coordinates of the center of a chip under a world coordinate system;
converting the coordinate of the center of the chip into a coordinate system of a reference coordinate, or converting the reference coordinate into a world coordinate system;
calculating the offset between the coordinates of the center of the chip and the reference coordinates according to the following formula:
in the above formula, Δ R is an offset amount, x1And x2The coordinate of the center of the chip and the coordinate of the reference coordinate on the x axis in the same coordinate system, y1And y2The coordinate of the center of the chip and the coordinate of the reference coordinate on the y axis are respectively in the same coordinate system.
Optionally, before determining whether the size of the solder paste dot on the target to be detected is within a first preset threshold interval, the method includes:
acquiring position information of a solder paste point;
performing circle fitting treatment on the solder paste points;
calculating the diameter of the solder paste point;
the step of judging whether the size of the solder paste point on the target to be detected is within a first preset threshold interval includes: and judging whether the diameter of the solder paste point on the target to be detected is within a first preset threshold interval.
In another aspect, an embodiment of the present disclosure provides an image detection apparatus, including:
the device comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is configured to acquire a target image, and the target image is an image of a target to be detected;
the first judgment module is configured to judge whether a chip is arranged on the target to be detected or not according to the target image;
the second judgment module is configured to judge whether the offset between the coordinate of the chip and the reference coordinate is greater than or equal to a first preset threshold value or not if the chip is arranged on the target to be detected; if so, determining that the chip position has a defect;
the third judging module is configured to judge whether the size of the solder paste point on the target to be detected is within a first preset threshold interval or not if the chip is not arranged on the target to be detected; if not, there is a defect in determining the size of the solder paste dot.
Optionally, the first determining module includes:
the first obtaining sub-module is configured to obtain a first image feature of a first preset area in the target image;
the second obtaining submodule is configured to obtain second image characteristics of a second preset area in the first template image;
the first judgment submodule is configured to judge whether the similarity of the first image feature and the second image feature is smaller than a second preset threshold value;
the first determining submodule is configured to determine that a chip is set on the target to be detected if the similarity is not smaller than a second preset threshold; otherwise, determining that no chip is arranged on the target to be detected.
Optionally, the first determining module includes:
the first obtaining sub-module is configured to obtain a first image feature of a first preset area in the target image;
the third obtaining submodule is configured to obtain third image characteristics of a third preset area in the second template image;
a second judgment submodule configured to judge whether the similarity of the first image feature and the third image feature is smaller than a third preset threshold;
the second determining submodule is configured to determine that no chip is arranged on the target to be detected if the similarity is not smaller than a third preset threshold; otherwise, determining that the chip is arranged on the target to be detected.
Optionally, the apparatus comprises:
the second acquisition module is configured to acquire coordinates of the center of the chip under the world coordinate system;
a coordinate conversion module configured to convert coordinates of a center of the chip into a coordinate system of reference coordinates or convert the reference coordinates into a world coordinate system;
a first calculation module configured to calculate an offset between coordinates of a center of the chip and the reference coordinates according to:
in the above formula, Δ R is an offset amount, x1And x2The coordinate of the center of the chip and the coordinate of the reference coordinate on the x axis in the same coordinate system, y1And y2The coordinate of the center of the chip and the coordinate of the reference coordinate on the y axis are respectively in the same coordinate system.
In yet another aspect, the disclosed embodiments provide a non-transitory computer-readable storage medium having one or more computer-readable instructions stored therein, which, when executed by a processor of a machine vision apparatus, cause the machine vision apparatus to perform the above-mentioned image detection method.
The beneficial effects brought by the technical scheme provided by the embodiment of the disclosure at least comprise:
whether a chip exists on the target to be detected is judged according to the target image of the target to be detected, when the chip exists on the target to be detected, whether the position of the chip has a defect is determined by judging the offset between the coordinate of the chip and the reference coordinate, and when the chip is not arranged on the target to be detected, whether the size of the solder paste point on the target to be detected has a defect is determined by judging whether the size of the solder paste point is within a first preset threshold interval, so that the defect detection can be rapidly and automatically carried out on the target to be detected, namely an electronic component, the labor can be saved, and the working efficiency is improved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the disclosure and are incorporated in and constitute a part of this specification, illustrate exemplary embodiments of the disclosure and together with the description serve to explain the principles of the disclosure.
Fig. 1 is a flowchart of an image detection method provided in a first embodiment of the present disclosure;
fig. 2 is a flowchart of an image detection method provided by a second embodiment of the present disclosure;
FIG. 3 is a schematic illustration of a first template image;
FIG. 4 is a schematic illustration of a second template image;
FIG. 5 is a schematic diagram of an object to be tested with a chip mounted thereon;
FIG. 6 is a schematic diagram of a chip extracted from a target image;
FIG. 7 is a diagram illustrating the determination result of whether there is a defect in the chip position;
FIG. 8 is a schematic diagram of a target under test without a chip;
FIG. 9 is a schematic view of a solder paste dot extracted from a target image;
FIG. 10 is a diagram illustrating a result of determining whether there is a defect in the size of a solder paste dot;
fig. 11 is a schematic diagram of an image detection apparatus provided in a third embodiment of the present disclosure.
Detailed Description
The present disclosure will be described in further detail with reference to the drawings and embodiments. It is to be understood that the specific embodiments described herein are for purposes of illustration only and are not to be construed as limitations of the present disclosure. It should be further noted that, for the convenience of description, only the portions relevant to the present disclosure are shown in the drawings.
It should be noted that the embodiments and features of the embodiments in the present disclosure may be combined with each other without conflict. The present disclosure will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.
The first embodiment of the disclosure provides an image detection method, an execution subject of the method is a machine vision device, and the method is mainly applied to defect screening of electronic components. As shown in fig. 1, the method includes:
step S101, acquiring a target image, wherein the target image is an image of a target to be detected;
step S102, judging whether a chip is arranged on the target to be detected or not according to the target image;
step S103, if a chip is arranged on the target to be detected, judging whether the offset between the coordinate of the chip and the reference coordinate is greater than or equal to a first preset threshold value; if so, determining that the chip position has a defect;
step S104, if the target to be detected is not provided with a chip, judging whether the size of the solder paste point on the target to be detected is within a first preset threshold interval; if not, there is a defect in determining the size of the solder paste dot.
Optionally, the determining whether a chip is disposed on the target to be detected according to the target image includes:
acquiring a first image characteristic of a first preset area in a target image;
acquiring second image characteristics of a second preset area in the first template image;
if the similarity of the first image characteristic and the second image characteristic is not smaller than a second preset threshold value, determining that a chip is arranged on the target to be detected; otherwise, determining that no chip is arranged on the target to be detected.
Optionally, the determining whether a chip is disposed on the target to be detected according to the target image includes:
acquiring a first image characteristic of a first preset area in a target image;
acquiring a third image characteristic of a third preset area in the second template image;
if the similarity of the first image characteristic and the third image characteristic is not smaller than a third preset threshold, determining that no chip is arranged on the target to be detected; otherwise, determining that the chip is arranged on the target to be detected.
Optionally, before determining whether an offset between the coordinates of the chip and the reference coordinates is greater than or equal to a first preset threshold, the method includes:
acquiring coordinates of the center of a chip under a world coordinate system;
converting the coordinate of the center of the chip into a coordinate system of a reference coordinate, or converting the reference coordinate into a world coordinate system;
calculating the offset between the coordinates of the center of the chip and the reference coordinates according to the following formula:
in the above formula, Δ R is an offset amount, x1And x2The coordinate of the center of the chip and the coordinate of the reference coordinate on the x axis in the same coordinate system, y1And y2The coordinate of the center of the chip and the coordinate of the reference coordinate on the y axis are respectively in the same coordinate system.
Optionally, before determining whether the size of the solder paste dot on the target to be detected is within a first preset threshold interval, the method includes:
acquiring position information of a solder paste point;
performing circle fitting treatment on the solder paste points;
calculating the diameter of the solder paste point;
the step of judging whether the size of the solder paste point on the target to be detected is within a first preset threshold interval includes: and judging whether the diameter of the solder paste point on the target to be detected is within a first preset threshold interval.
According to the image detection method provided by the embodiment, whether a chip exists on the target to be detected is judged according to the target image of the target to be detected, when the chip exists on the target to be detected, whether a defect exists in the position of the chip is determined by judging the offset between the coordinate of the chip and the reference coordinate, and when the chip is not arranged on the target to be detected, whether the defect exists in the size of the solder paste point is determined by judging whether the size of the solder paste point on the target to be detected is within the first preset threshold interval, so that the defect detection can be rapidly and automatically carried out on the target to be detected, namely an electronic component, the labor can be saved, and the working efficiency is improved.
The second embodiment of the disclosure provides an image detection method, the execution subject of the method is a machine vision device, and the method is mainly applied to defect screening of electronic components. As shown in fig. 2, the method includes:
step S201, a target image is obtained, where the target image is an image of a target to be measured.
A camera is usually provided in the machine vision device, so that the target image can be directly acquired by the camera in the machine vision device. Alternatively, the target image may be acquired by another device, and then sent to the machine vision device, so that the machine vision device may analyze the image. Here, the object to be measured refers to an electronic component to be detected.
In a possible implementation manner, in order to obtain a target image capable of accurately reflecting the real situation of the target to be measured, before the target image is obtained by using a camera in the machine vision device, the camera may be calibrated. Specifically, the camera may be calibrated by a checkerboard target camera calibration method, a direct linear transformation calibration method, or an RAC-based calibration method.
Step S202, judging whether a chip is arranged on the target to be detected or not according to the target image;
since different items are detected for the target to be detected with the chip set and the target to be detected without the chip set, after the target image is acquired, it is necessary to first determine whether the chip is set on the target to be detected.
In a possible implementation manner, whether a chip is set on the target to be tested may be determined in any one of the following two manners.
The first mode is as follows:
(1) acquiring a first image characteristic of a first preset area in a target image;
(2) acquiring second image characteristics of a second preset area in the first template image;
(3) if the similarity of the first image characteristic and the second image characteristic is not smaller than a second preset threshold value, determining that a chip is arranged on the target to be detected; otherwise, determining that no chip is arranged on the target to be detected.
In this implementation manner, the first template image refers to an image of an electronic component on which a chip is already disposed, the first preset region refers to a region, in the target image, of a position on the target to be measured where the chip is disposed, and the second preset region refers to a region, in the first template image, where the chip is located. The electronic component in the first template image and the object to be measured should be the same electronic component. In practical applications, the position of the electronic component for placing the chip is usually fixed, that is, the position of the target image for placing the chip is consistent with the position of the chip in the first template image. Fig. 3 illustrates a first template image provided with a chip. In the context of figure 3 of the drawings,
the outer large box in (1) represents the pin holder and the middle small box represents the chip. The pin support is located on the electronic component and used for mounting and fixing the chip.
Therefore, whether the chip is arranged on the target to be detected or not can be judged by respectively obtaining the first image characteristic and the second image characteristic of the target image and the first template image in the first preset area and the second preset area and calculating the similarity of the first image characteristic and the second image characteristic.
The second mode is as follows:
(1) acquiring a first image characteristic of a first preset area in a target image;
(2) acquiring a third image characteristic of a third preset area in the second template image;
(3) if the similarity of the first image characteristic and the third image characteristic is not smaller than a third preset threshold, determining that no chip is arranged on the target to be detected; otherwise, determining that the chip is arranged on the target to be detected.
In this implementation manner, the second template image refers to an image of an electronic component without a chip, the first preset region refers to a region, in the target image, of a position, for setting the chip, on the target to be detected, and the third preset region refers to a region, in the electronic component, corresponding to the second template image, for setting the chip. The electronic component in the second template image and the target to be measured should be the same electronic component. Fig. 4 schematically shows a second template image without a chip. In the context of figure 4 of the drawings,
the outer large square in the middle represents a pin support, and the middle ○ represents a solder paste point, and whether a chip is arranged on the target to be detected can be judged by respectively obtaining the first image characteristic and the third image characteristic of the target image and the second template image in the first preset area and the third preset area, and calculating the similarity of the first image characteristic and the third image characteristic.
In the above two ways of determining whether there is a chip on the target to be detected, the specific values of the second preset threshold and the third preset threshold may be set by a technician before the machine vision device executes the image detection method provided in this embodiment, or before the machine vision device leaves a factory according to actual needs.
Step S203, if a chip is set on the target to be detected, determining whether an offset between the coordinate of the chip and the reference coordinate is greater than or equal to a first preset threshold.
After the chip is set on the target to be detected, as shown in fig. 5, because the chip and the pin support have an approximate rectangular structure, the minimum external rectangle of the chip can be obtained through opening and closing operation and feature extraction, that is, the chip is extracted from the frame background, and the influence of the background support and the pin support without the chip is removed. After the image features of the chip are extracted, the coordinates of the chip can be obtained, and the offset between the coordinates of the chip and the reference coordinates is calculated to judge whether the set position of the chip is qualified or not, so that whether the target to be detected has defects or not is judged. Fig. 6 shows a schematic diagram of the extracted chip. It should be noted that fig. 3-10 provided in this embodiment are only schematic diagrams illustrating the positional relationship between the chip and the lead frame or the solder paste spot and the lead frame on the target to be tested, or exemplarily illustrating the chip and the solder paste spot. In practical situations, the chip, the solder paste dot and the lead frame usually have different gray scale values in the target image of the target to be measured. Therefore, features can be extracted from the image by means of feature extraction.
In one possible implementation manner, in order to calculate the offset between the coordinates of the chip and the reference coordinates conveniently, the coordinates of the center of the chip may be obtained, and the offset between the coordinates of the center of the chip and the reference coordinates may be calculated. At this time, the reference coordinates may be coordinates of the center of the pin holder.
When the coordinates of the center of the chip are acquired, the coordinates of the center of the chip in the world coordinate system can be acquired. After the coordinates of the center of the chip are acquired, since the coordinates of the center of the chip may be different from the coordinate system used for the reference coordinates, in order to calculate the offset between the coordinates of the center of the chip and the reference coordinates, the coordinates of the center of the chip may be converted into the coordinate system of the reference coordinates, or the reference coordinates may be converted into the world coordinate system.
After the coordinate conversion is completed, the offset between the coordinates of the center of the chip and the reference coordinates can be directly calculated according to the following formula:
in the above formula, Δ R is an offset amount, x1And x2The coordinate of the center of the chip and the coordinate of the reference coordinate on the x axis in the same coordinate system, y1And y2The coordinate of the center of the chip and the coordinate of the reference coordinate on the y axis are respectively in the same coordinate system.
When the offset delta R is larger than or equal to the first preset threshold, the position of the chip arranged on the target to be detected can be determined to be offset, and the arrangement position of the chip is determined to be unqualified. Otherwise, the position of the chip set on the target to be detected is determined not to be deviated, and the set position of the chip is determined to be qualified. The specific value of the first preset threshold may be specifically set by a technician according to actual conditions. For example, the specific value of the first preset threshold may be 30 μm,40 μm, or 50 μm, etc. After judging whether there is a defect in the set position of the chip, as shown in fig. 7, the judgment result may be output. In fig. 7, a shaded □ indicates a chip having a defect at the set position.
In a possible implementation manner, after determining that the position of the chip set on the target to be measured is shifted, the offsets of the chip position on the x axis and the y axis may be respectively calculated, so as to adjust the subsequent production process according to the calculation result. Alternatively, the offset of the chip position on the x-axis and the y-axis may be directly calculated, and whether the chip position is offset may be determined according to the offset of the chip position on the x-axis and the y-axis. Wherein the offset R of the chip position on the x-axisx＝x1-x2Offset R of chip position on y-axisy＝y1-y2。
When R isxWhen the position of the chip is smaller than a second preset threshold interval, the position of the chip can be determined to be shifted to the left on the x axis, and when R is smaller than the second preset threshold interval, the position of the chip can be determined to be shifted to the left on the x axisxWhen the position of the chip is larger than a second preset threshold interval, the position of the chip can be determined to be shifted to the right on the x axis, and when R is larger than the second preset threshold intervalxWhen the position of the chip is within the second preset threshold interval, the position of the chip can be determined not to be shifted on the x-axis. For example, the second predetermined threshold interval may be [ -28,28 [ -28 [ ]]When R isxWhen the thickness is less than-28 μm, it can be determined that the position of the chip is shifted to the left in the x-axis, and when R is greater thanxWhen the thickness is larger than 28 μm, it can be determined that the position of the chip is shifted to the right in the x-axis, and when R is smaller than or equal to-28 μmxWhen the thickness is less than or equal to 28 mu m, the position of the chip can be determined not to be shifted on the x-axis.
Similarly, a third preset threshold interval may also be set. When R isyWhen the position of the chip is smaller than a third preset threshold interval, the position of the chip can be determined to be shifted upwards on the y axis, and when R is smaller than the third preset threshold intervalyWhen the position of the chip is larger than a third preset threshold interval, the position of the chip can be determined to be generated downwards on the y axisOffset when R isyWhen the position of the chip is within the second preset threshold interval, the position of the chip can be determined not to be shifted on the y axis. Wherein the third preset threshold interval may be the same as the second preset threshold interval, for example, both may be [ -28,28 [ -28 [ ]]. Alternatively, the third preset threshold interval and the second preset threshold interval may be different, for example, the third preset threshold interval may be [ -25,25 [ -25 [ ]]. In the two-dimensional coordinate system of the x-axis and the y-axis provided in this embodiment, the positive direction of the x-axis is directed to the right, and the positive direction of the y-axis is directed to the down.
After the offset of the chip position on the x-axis and the y-axis is calculated, the offset of the chip on different coordinate axes can be displayed in different manners, that is, the chips offset on different coordinate axes are displayed in different categories. For example, chips shifted to the left in the x-axis may be displayed in black shading, chips shifted to the right in the x-axis may be displayed in red shading, chips shifted to the lower in the y-axis may be displayed in blue shading, and chips shifted to the upper in the y-axis may be displayed in blue shading.
After the offset of the chip position is calculated, the error can be eliminated by carrying out detection for multiple times, or a camera with higher resolution is selected to obtain a target image, so that the error is avoided. In addition, after the offset of the chip position is obtained, the working distance and the camera focal length can be adjusted according to the requirements of working precision and efficiency to optimize the final result. For example, the distance between the camera lens and the target to be measured can be shortened or the focal length can be increased within the depth of field range of the camera, so that the area of the image acquired by the camera is reduced, and the identification precision of a single pixel point is improved. After the offset of the chip position is obtained, the detection process can be optimized by establishing a multi-type component template, a historical database and the like. For example, the detection templates of various electronic components can be established through the steps, so that the universality of the detection process is enhanced; and a historical detection record report can be added to improve the detection traceability of the detection process.
Step S204, if the target to be detected is not provided with the chip, whether the size of the solder paste point on the target to be detected is within a first preset threshold interval or not is judged.
In practical application, the shape of the solder paste points on the target to be detected is generally irregular round, and the position information of the solder paste points can be obtained first before the round fitting processing of the solder paste points, namely the solder paste points are positioned.
For example, the roundness range can be set to be 0.5-1 according to the cleanliness of the sample, the number of the pixels occupied by the solder paste points in the image coordinate system is between 2000 and 6000, that is, the roundness range is 0.56-1, the number of the pixels occupied by the solder paste points is between 2000 and 6000, and the extracted region of the solder paste points is shown in fig. 9.
After the area of the solder paste points is obtained, the area of the solder paste points may be subjected to circle fitting processing for the convenience of subsequent calculations. Then, the area of the solder paste point can be calculated through an image recognition technology, and then whether the area of the solder paste point is located in a first preset threshold interval or not is judged. If so, determining that the size of the solder paste point has no defect, otherwise, determining that the size of the solder paste point has the defect. At this time, the first preset threshold interval is an interval of the standard solder paste dot area.
The size of the solder paste dots may be [550 μm,750 μm ] when the first predetermined threshold interval is the standard solder paste dot diameter interval, or the specific value of the first predetermined threshold interval may be set by a technician as needed.
After the judgment result of the size of the solder paste dots is obtained, the production process can be improved according to the judgment result so as to ensure that the size of the solder paste dots is within the first preset threshold range as much as possible.
The image detection method provided by the embodiment of the disclosure judges whether a chip exists on the target to be detected according to the target image of the target to be detected, determines whether the position of the chip has a defect by judging the offset between the coordinate of the chip and the reference coordinate when the chip exists on the target to be detected, determines whether the size of the solder paste point on the target to be detected has a defect by judging whether the size of the solder paste point is within a first preset threshold interval when the chip is not arranged on the target to be detected, can quickly and automatically detect the defect of the target to be detected, namely an electronic component, can save labor, and improve the working efficiency.
In addition, the image detection method provided by the embodiment is mainly completed by a machine vision device, can accurately position the defects of the electronic components, and has the advantages of strong adaptability, high reliability and the like. After the defects of the electronic components are judged, the defects of the electronic components are classified and displayed in different modes, so that a basis can be better provided for the optimization of a subsequent production process.
The third embodiment of the present disclosure provides an image inspection apparatus 300, where the apparatus 300 is applied to a machine vision apparatus, and is mainly used for defect screening of electronic components. The apparatus 300 comprises:
a first obtaining module 301 configured to obtain a target image, where the target image is an image of a target to be detected;
a first judging module 302 configured to judge whether a chip is disposed on the target to be detected according to the target image;
a second judging module 303, configured to judge whether an offset between a coordinate of the chip and the reference coordinate is greater than or equal to a first preset threshold if the chip is set on the target to be detected; if so, determining that the chip position has a defect;
a third determining module 304, configured to determine whether the size of the solder paste dot on the target to be tested is within the first preset threshold interval if no chip is set on the target to be tested; if not, there is a defect in determining the size of the solder paste dot.
Optionally, the first determining module 302 includes:
a first obtaining submodule 3021 configured to obtain a first image feature of a first preset region in the target image;
a second obtaining submodule 3022 configured to obtain a second image feature of a second preset region in the first template image;
a first judging submodule 3023 configured to judge whether the similarity between the first image feature and the second image feature is smaller than a second preset threshold;
a first determining submodule 3024 configured to determine that a chip has been set on the target to be measured if the similarity is not smaller than a second preset threshold; otherwise, determining that no chip is arranged on the target to be detected.
Optionally, the first determining module 302 includes:
a first obtaining submodule 3021 configured to obtain a first image feature of a first preset region in the target image;
a third obtaining submodule 3025 configured to obtain a third image feature of a third preset region in the second template image;
a second determination submodule 3026 configured to determine whether the similarity between the first image feature and the third image feature is smaller than a third preset threshold;
a second determining submodule 3027 configured to determine that no chip is set on the target to be measured if the similarity is not smaller than a third preset threshold; otherwise, determining that the chip is arranged on the target to be detected.
Optionally, the apparatus comprises:
a second obtaining module 305 configured to obtain coordinates of a chip center in a world coordinate system;
a coordinate conversion module 306 configured to convert coordinates of a center of the chip into a coordinate system of reference coordinates or convert the reference coordinates into a world coordinate system;
a first calculation module 307 configured to calculate an offset between the coordinates of the center of the chip and the reference coordinates according to the following formula:
in the above formula, Δ R is an offset amount, x1And x2The coordinate of the center of the chip and the coordinate of the reference coordinate on the x axis in the same coordinate system, y1And y2The coordinate of the center of the chip and the coordinate of the reference coordinate on the y axis are respectively in the same coordinate system.
Optionally, the apparatus comprises:
a third obtaining module 308 configured to obtain position information of the solder paste dots;
a fitting module 309 configured to perform a circle fitting process on the solder paste points;
a second calculation module 310 configured to calculate a diameter of the solder paste dot;
the third determining module 304 is configured to determine whether the diameter of the solder paste dot on the target is within a first preset threshold interval.
Optionally, the apparatus further includes a display module 311 configured to display the determination result of the chip position and the determination result of the solder paste dot size.
The image detection device provided by the embodiment judges whether a chip exists on the target to be detected according to the target image of the target to be detected, and when the chip exists on the target to be detected, whether a defect exists in the position of the chip is determined by judging the offset between the coordinate of the chip and the reference coordinate, and when the chip is not arranged on the target to be detected, whether a defect exists in the size of a solder paste point is determined by judging whether the size of the solder paste point on the target to be detected is in a first preset threshold interval, so that the defect detection can be rapidly and automatically carried out on the target to be detected, namely an electronic component, the labor can be saved, and the working efficiency is improved.
It should be noted that, when the image detection apparatus provided in the foregoing embodiment is used to detect a defect of an object to be detected, the division of the functional modules is merely used as an example, and in practical applications, the function distribution may be completed by different functional modules according to needs, that is, the internal structure or program of the apparatus may be divided into different functional modules to complete all or part of the functions described above. In addition, the image detection apparatus and the image detection method provided by the above embodiments belong to the same concept, and specific implementation processes thereof are described in the method embodiments in detail and are not described herein again.
The fourth embodiment of the disclosure provides an image detection device, which is applied to a machine vision device and is mainly used for defect screening of electronic components. The device includes:
a processor;
a memory for storing processor-executable instructions;
wherein the processor is configured to, when executing the executable instructions, cause the machine vision apparatus to perform the image detection method described in the above embodiments.
A fifth embodiment of the present disclosure provides a non-transitory computer-readable storage medium, which may be a computer-readable storage medium contained in the memory in the above-described embodiments; or it may be a separate computer-readable storage medium not incorporated in the terminal. The computer readable storage medium has stored therein one or more computer readable instructions (programs) that, when executed by a processor of a machine vision apparatus, cause the machine vision apparatus to perform the image detection method described in the above embodiments.
In the description herein, reference to the description of the terms "one embodiment/mode," "some embodiments/modes," "example," "specific example," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment/mode or example is included in at least one embodiment/mode or example of the present disclosure. In this specification, the schematic representations of the terms used above are not necessarily intended to be the same embodiment/mode or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments/modes or examples. Furthermore, the various embodiments/aspects or examples and features of the various embodiments/aspects or examples described in this specification can be combined and combined by one skilled in the art without conflicting therewith.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present disclosure, "a plurality" means at least two, e.g., two, three, etc., unless explicitly specifically limited otherwise.
It will be understood by those skilled in the art that the foregoing embodiments are merely for clarity of illustration of the disclosure and are not intended to limit the scope of the disclosure. Other variations or modifications may occur to those skilled in the art, based on the foregoing disclosure, and are still within the scope of the present disclosure.
Claims (10)
1. An image detection method, characterized in that the method comprises:
acquiring a target image, wherein the target image is an image of a target to be detected;
judging whether a chip is arranged on the target to be detected or not according to the target image;
if the target to be detected is provided with a chip, judging whether the offset between the coordinate of the chip and the reference coordinate is greater than or equal to a first preset threshold value; if so, determining that the chip position has a defect;
if the target to be detected is not provided with a chip, judging whether the size of a solder paste point on the target to be detected is within a first preset threshold interval or not; if not, determining the size of the solder paste point has a defect.
2. The method according to claim 1, wherein the determining whether a chip is disposed on the target to be detected according to the target image comprises:
acquiring a first image characteristic of a first preset area in the target image;
acquiring second image characteristics of a second preset area in the first template image;
if the similarity of the first image characteristic and the second image characteristic is not smaller than a second preset threshold, determining that a chip is arranged on the target to be detected; otherwise, determining that no chip is arranged on the target to be detected.
3. The method according to claim 1, wherein the determining whether a chip is disposed on the target to be detected according to the target image comprises:
acquiring a first image characteristic of a first preset area in the target image;
acquiring a third image characteristic of a third preset area in the second template image;
if the similarity of the first image characteristic and the third image characteristic is not smaller than a third preset threshold, determining that no chip is arranged on the target to be detected; otherwise, determining that the chip is arranged on the target to be detected.
4. The method according to any one of claims 1 to 3, wherein before the determining whether the offset between the coordinates of the chip and the reference coordinates is greater than or equal to a first preset threshold, the method comprises:
acquiring coordinates of the center of the chip in a world coordinate system;
converting the coordinate of the center of the chip into a coordinate system of the reference coordinate, or converting the reference coordinate into a world coordinate system;
calculating an offset between the coordinates of the center of the chip and the reference coordinates according to:
in the above formula, Δ R is an offset amount, x1And x2Respectively being the coordinate of the center of the chip and the coordinate of the reference coordinate on the x axis under the same coordinate system, y1And y2The coordinate of the center of the chip and the coordinate of the reference coordinate on the y axis are respectively in the same coordinate system.
5. The method according to any one of claims 1-3, wherein before said determining whether the size of the solder paste dot on the target is within a first predetermined threshold interval, the method comprises:
acquiring position information of the solder paste points;
performing circle fitting treatment on the solder paste points;
calculating the diameter of the solder paste point;
the judging whether the size of the solder paste point on the target to be detected is within a first preset threshold interval includes: and judging whether the diameter of the solder paste point on the target to be detected is within the first preset threshold interval.
6. An image detection apparatus, characterized in that the apparatus comprises:
the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is configured to acquire a target image, and the target image is an image of a target to be detected;
the first judgment module is configured to judge whether a chip is arranged on the target to be detected or not according to the target image;
a second judgment module configured to judge whether an offset between a coordinate of a chip and a reference coordinate is greater than or equal to a first preset threshold if the chip is set on the target to be measured; if so, determining that the chip position has a defect;
the third judging module is configured to judge whether the size of the solder paste point on the target to be detected is within a first preset threshold interval or not if no chip is arranged on the target to be detected; if not, determining the size of the solder paste point has a defect.
7. The apparatus of claim 6, wherein the first determining module comprises:
a first obtaining sub-module configured to obtain a first image feature of a first preset region in the target image;
a second obtaining sub-module configured to obtain a second image feature of a second preset region in the first template image;
a first judgment sub-module configured to judge whether the similarity of the first image feature and the second image feature is smaller than a second preset threshold;
a first determining submodule configured to determine that a chip is set on the target to be measured if the similarity is not less than the second preset threshold; otherwise, determining that no chip is arranged on the target to be detected.
8. The apparatus of claim 6, wherein the first determining module comprises:
a first obtaining sub-module configured to obtain a first image feature of a first preset region in the target image;
a third obtaining sub-module configured to obtain a third image feature of a third preset region in the second template image;
a second determination sub-module configured to determine whether the similarity of the first image feature and the third image feature is smaller than a third preset threshold;
a second determining submodule configured to determine that no chip is set on the target to be measured if the similarity is not smaller than the third preset threshold; otherwise, determining that the chip is arranged on the target to be detected.
9. The apparatus according to any one of claims 6-8, wherein the apparatus comprises:
a second acquisition module configured to acquire coordinates of the chip center in a world coordinate system;
a coordinate conversion module configured to convert coordinates of the center of the chip into a coordinate system of the reference coordinates or convert the reference coordinates into a world coordinate system;
a first calculation module configured to calculate an offset between the coordinates of the chip center and the reference coordinates according to:
in the above formula, Δ R is an offset amount, x1And x2Respectively being the coordinate of the center of the chip and the coordinate of the reference coordinate on the x axis under the same coordinate system, y1And y2The coordinate of the center of the chip and the coordinate of the reference coordinate on the y axis are respectively in the same coordinate system.
10. A non-transitory computer readable storage medium having one or more computer readable instructions stored therein, which when executed by a processor of a machine vision apparatus, cause the machine vision apparatus to perform the image detection method of any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911150261.0A CN111161208A (en) | 2019-11-21 | 2019-11-21 | Image detection method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911150261.0A CN111161208A (en) | 2019-11-21 | 2019-11-21 | Image detection method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111161208A true CN111161208A (en) | 2020-05-15 |
Family
ID=70556105
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911150261.0A Pending CN111161208A (en) | 2019-11-21 | 2019-11-21 | Image detection method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111161208A (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111693546A (en) * | 2020-06-16 | 2020-09-22 | 湖南大学 | Defect detection system, method and image acquisition system |
| CN111784674A (en) * | 2020-07-02 | 2020-10-16 | 深圳明锐理想科技有限公司 | Component detection method, device, computer equipment and storage medium |
| CN112419274A (en) * | 2020-11-24 | 2021-02-26 | 英业达(重庆)有限公司 | Solder paste detection method, system, electronic device and medium |
| CN112528761A (en) * | 2020-11-24 | 2021-03-19 | 上海墨说科教设备有限公司 | Method and system for extracting specific target in image, electronic device and storage medium |
| CN114897962A (en) * | 2022-03-31 | 2022-08-12 | 联想(北京)有限公司 | An image processing method and device |
| CN115101431A (en) * | 2022-06-16 | 2022-09-23 | 成都御子辇科技有限公司 | Machine vision-based semiconductor chip manufacturing online intelligent detection and analysis system |
| CN115201667A (en) * | 2022-09-15 | 2022-10-18 | 武汉普赛斯电子技术有限公司 | Method and device for calibrating and positioning semiconductor laser chip and storage medium |
| CN115656214A (en) * | 2022-09-07 | 2023-01-31 | 环旭电子股份有限公司 | Detection method and system for chip on tray, storage medium and intelligent terminal |
| CN116559173A (en) * | 2023-04-19 | 2023-08-08 | 深圳市晶存科技有限公司 | Chip detection method, system, device and storage medium |
| CN117078747A (en) * | 2023-08-11 | 2023-11-17 | 昆山丘钛光电科技有限公司 | Method, device, medium and equipment for detecting position deviation of image sensor |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004273950A (en) * | 2003-03-11 | 2004-09-30 | Kaijo Corp | Bonding method and bonding apparatus |
| CN105185728A (en) * | 2015-06-17 | 2015-12-23 | 北京七星华创电子股份有限公司 | Image-based silicon wafer distribution state identification method and device |
| CN105701492A (en) * | 2014-11-25 | 2016-06-22 | 宁波舜宇光电信息有限公司 | Machine vision identification system and implementation method thereof |
| JP2016219659A (en) * | 2015-05-22 | 2016-12-22 | アズビル株式会社 | Image inspection device and image inspection method |
| CN106370671A (en) * | 2016-10-12 | 2017-02-01 | 浙江理工大学 | PCB (printed circuit board) component detection system and method based on machine vision |
| CN106600600A (en) * | 2016-12-26 | 2017-04-26 | 华南理工大学 | Wafer defect detection method based on characteristic matching |
| CN108802046A (en) * | 2018-06-01 | 2018-11-13 | 中国电子科技集团公司第三十八研究所 | A kind of hydrid integrated circuit component defect optical detection apparatus and its detection method |
| CN109685142A (en) * | 2018-12-25 | 2019-04-26 | 国信优易数据有限公司 | A kind of image matching method and device |
-
2019
- 2019-11-21 CN CN201911150261.0A patent/CN111161208A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004273950A (en) * | 2003-03-11 | 2004-09-30 | Kaijo Corp | Bonding method and bonding apparatus |
| CN105701492A (en) * | 2014-11-25 | 2016-06-22 | 宁波舜宇光电信息有限公司 | Machine vision identification system and implementation method thereof |
| JP2016219659A (en) * | 2015-05-22 | 2016-12-22 | アズビル株式会社 | Image inspection device and image inspection method |
| CN105185728A (en) * | 2015-06-17 | 2015-12-23 | 北京七星华创电子股份有限公司 | Image-based silicon wafer distribution state identification method and device |
| CN106370671A (en) * | 2016-10-12 | 2017-02-01 | 浙江理工大学 | PCB (printed circuit board) component detection system and method based on machine vision |
| CN106600600A (en) * | 2016-12-26 | 2017-04-26 | 华南理工大学 | Wafer defect detection method based on characteristic matching |
| CN108802046A (en) * | 2018-06-01 | 2018-11-13 | 中国电子科技集团公司第三十八研究所 | A kind of hydrid integrated circuit component defect optical detection apparatus and its detection method |
| CN109685142A (en) * | 2018-12-25 | 2019-04-26 | 国信优易数据有限公司 | A kind of image matching method and device |
Non-Patent Citations (3)
| Title |
|---|
| 王文峰等: "MATLAB计算机视觉与机器认知", vol. 2018, 31 August 2017, 北京航空航天大学出版社, pages: 101 - 103 * |
| 韩成，杨华民，蒋振刚等著: "LTE多模终端的关键技术及系统设计", vol. 2016, 30 November 2016, 北京理工大学出版社, pages: 179 - 181 * |
| 韩成，杨华民，蒋振刚等著: "基于结构光的计算机视觉", vol. 2015, 国防工业出版社, pages: 37 * |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111693546A (en) * | 2020-06-16 | 2020-09-22 | 湖南大学 | Defect detection system, method and image acquisition system |
| CN111784674A (en) * | 2020-07-02 | 2020-10-16 | 深圳明锐理想科技有限公司 | Component detection method, device, computer equipment and storage medium |
| CN112528761B (en) * | 2020-11-24 | 2023-04-07 | 上海墨说科教设备有限公司 | Method and system for extracting specific target in image, electronic device and storage medium |
| CN112528761A (en) * | 2020-11-24 | 2021-03-19 | 上海墨说科教设备有限公司 | Method and system for extracting specific target in image, electronic device and storage medium |
| CN112419274A (en) * | 2020-11-24 | 2021-02-26 | 英业达(重庆)有限公司 | Solder paste detection method, system, electronic device and medium |
| CN112419274B (en) * | 2020-11-24 | 2024-04-26 | 英业达(重庆)有限公司 | Solder paste detection method, system, electronic equipment and medium |
| CN114897962A (en) * | 2022-03-31 | 2022-08-12 | 联想(北京)有限公司 | An image processing method and device |
| CN115101431A (en) * | 2022-06-16 | 2022-09-23 | 成都御子辇科技有限公司 | Machine vision-based semiconductor chip manufacturing online intelligent detection and analysis system |
| CN115656214A (en) * | 2022-09-07 | 2023-01-31 | 环旭电子股份有限公司 | Detection method and system for chip on tray, storage medium and intelligent terminal |
| CN115201667A (en) * | 2022-09-15 | 2022-10-18 | 武汉普赛斯电子技术有限公司 | Method and device for calibrating and positioning semiconductor laser chip and storage medium |
| CN115201667B (en) * | 2022-09-15 | 2022-12-23 | 武汉普赛斯电子技术有限公司 | Method and device for calibrating and positioning semiconductor laser chip and storage medium |
| CN116559173A (en) * | 2023-04-19 | 2023-08-08 | 深圳市晶存科技有限公司 | Chip detection method, system, device and storage medium |
| CN117078747A (en) * | 2023-08-11 | 2023-11-17 | 昆山丘钛光电科技有限公司 | Method, device, medium and equipment for detecting position deviation of image sensor |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111161208A (en) | Image detection method and device | |
| US12394035B2 (en) | Weld quality inspection method, apparatus and system, and electronic device | |
| CN113240674B (en) | Coplanarity detection method based on three-dimensional point cloud and two-dimensional image fusion | |
| US12499577B2 (en) | Method and apparatus for testing stability of vision system | |
| CN106814083A (en) | Filter plate defect detecting system and its detection method | |
| CN105606620A (en) | PCBA welding spot detection method and system based on vision | |
| CN110621150B (en) | Printed circuit board assembling method and related device | |
| US10535157B2 (en) | Positioning and measuring system based on image scale | |
| CN111486787A (en) | Test positioning method and test positioning system | |
| CN117589770A (en) | PCB patch board detection method, device, equipment and medium | |
| CN116329738A (en) | Positioning method, device, electronic equipment and storage medium of circuit board target | |
| CN117058411B (en) | Method, device, medium and equipment for identifying edge appearance flaws of battery | |
| CN117571721B (en) | Method and device for detecting surface defects of circuit board bonding pad and storage medium | |
| JP2019039846A (en) | Inspection system and inspection image correction method | |
| KR20210153672A (en) | Wire shape measuring device, wire three-dimensional image generation method and wire shape measuring method | |
| EP3737217B1 (en) | Electronic component evaluation method, electronic component evaluation device, and electronic component evaluation program | |
| CN113075231A (en) | Automatic intelligent detection method and system applied to chip DB and gold wire WB | |
| CN107256835B (en) | A bump defect detection method | |
| CN111583222B (en) | Automatic positioning method for test point, automatic copper thickness detection method and system | |
| JP2008261692A (en) | Substrate inspection system and substrate inspection method | |
| CN114994508A (en) | Substrate testing system and substrate testing method | |
| CN120101645B (en) | PIN verticality defect detection method, device, equipment and storage medium | |
| CN116596893B (en) | Quick detection and positioning method for metal terminal | |
| CN121033049B (en) | Detection method based on complex chip type IPM | |
| CN120869557B (en) | A method, apparatus, equipment, and medium for measuring the optical axis tilt angle of an optical lens. |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200515 |