CN116612476B - Chip character detection method and device, computer equipment and storage medium - Google Patents
Chip character detection method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN116612476B CN116612476B CN202310892133.3A CN202310892133A CN116612476B CN 116612476 B CN116612476 B CN 116612476B CN 202310892133 A CN202310892133 A CN 202310892133A CN 116612476 B CN116612476 B CN 116612476B
- Authority
- CN
- China
- Prior art keywords
- image
- character
- points
- golden template
- template image
- 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.)
- Active
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 41
- 238000003860 storage Methods 0.000 title claims abstract description 11
- 238000012360 testing method Methods 0.000 claims abstract description 81
- 238000000034 method Methods 0.000 claims abstract description 17
- 238000007781 pre-processing Methods 0.000 claims abstract description 10
- 238000004590 computer program Methods 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 claims description 7
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 claims description 3
- 239000010931 gold Substances 0.000 claims description 3
- 229910052737 gold Inorganic materials 0.000 claims description 3
- 238000004519 manufacturing process Methods 0.000 abstract description 8
- 230000001737 promoting effect Effects 0.000 abstract 1
- 238000010586 diagram Methods 0.000 description 20
- 238000009826 distribution Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 239000004065 semiconductor Substances 0.000 description 3
- 230000008569 process Effects 0.000 description 2
- XUIMIQQOPSSXEZ-UHFFFAOYSA-N Silicon Chemical compound [Si] XUIMIQQOPSSXEZ-UHFFFAOYSA-N 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000007639 printing Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/14—Image acquisition
- G06V30/1444—Selective acquisition, locating or processing of specific regions, e.g. highlighted text, fiducial marks or predetermined fields
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/16—Image preprocessing
- G06V30/162—Quantising the image signal
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/18—Extraction of features or characteristics of the image
- G06V30/1801—Detecting partial patterns, e.g. edges or contours, or configurations, e.g. loops, corners, strokes or intersections
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a method and a device for detecting chip characters, computer equipment and a storage medium, and belongs to the technical field of chip production testing. Aiming at the problems of low detection accuracy and the like caused by fuzzy distortion of characters in the chip character detection in the prior art, the invention acquires the number of foreground white points on a preprocessed golden template image after preprocessing the golden template image and a character test image, calculates and acquires the difference points between the preprocessed golden template image and the preprocessed character test image, further selects the number of effective points, and traverses a coordinate linked list array to judge the fluctuation of the effective points on an edge image and count the fluctuation times, thereby judging whether the character test image is a character normal image or not by utilizing the number of the obtained effective points, the fluctuation times and the number of the foreground white points, realizing rapid and accurate detection of chip characters, improving the recognition efficiency of the chip characters, promoting chip production and test equipment to realize automatic detection, and improving the quality of chip products.
Description
Technical Field
The present invention relates to the field of chip production testing technology, and more particularly, to a method and apparatus for detecting chip characters, a computer device, and a storage medium.
Background
The semiconductor electronic component is widely applied to various electrical and electronic products and communication systems, and the characters on the plastic package body of the semiconductor electronic component not only contain information such as the type and the model of the component, but also contain related information such as the polarity, so that the character detection on the plastic package body is an indispensable procedure in the production process of the semiconductor electronic component. Chips, also known as microcircuits, microchips, integrated circuits, refer to silicon chips containing integrated circuits, which are small in size and often part of a computer or other electronic device. The identification of the chip is characterized in that due to different production merchants, different shooting angles, different illumination angles, different printing batches and the like, characters on the chip are not uniform in fonts, and the phenomenon of distortion and blurring of the characters often occurs, so that the difficulty and the accuracy of detecting the characters of the chip are increased.
Through searching, chinese patent application, application number 202210135731.1, publication day 2022, 3 and 15, discloses a chip surface character detection system. The system comprises a character recognition device, a first conveying device, a second conveying device and a control device. The control device is used for controlling the first conveying device to convey the chip to the recognition area of the character recognition device according to the preset conveying rate. The control device is also used for controlling the character recognition device to acquire a first image of the characters on the upper surface of the chip of the recognition area according to the preset recognition rate. The character recognition device is used for sequentially carrying out image binarization processing and image segmentation on the first image to obtain a plurality of character areas, and respectively matching the plurality of character areas with a preset character template to determine surface character detection information of the chip. The control device is used for controlling the second conveying device to convey the chip to the target position according to the surface character detection information. However, this system does not take into consideration that if there is a problem such as blurring and warping of the chip character, the chip character cannot be detected accurately and quickly.
Disclosure of Invention
1. Technical problem to be solved
Aiming at the problems of low detection accuracy and the like of chip characters caused by fuzzy distortion and irregularity of the characters in the chip character detection in the prior art, the invention provides a chip character detection method, a chip character detection device, computer equipment and a storage medium, which can realize rapid and accurate detection of chip characters, have strong pertinence and effectively improve chip production and test efficiency.
2. Technical proposal
The aim of the invention is achieved by the following technical scheme.
A chip character detection method comprises the following steps:
collecting character images, wherein the character images comprise character normal images and character test images, and obtaining golden template images through the character normal images;
preprocessing a golden template image and a character test image respectively to obtain a preprocessed golden template image and a preprocessed character test image, searching a front Jing Baidian on the preprocessed golden template image, and counting the number of foreground white points;
calculating to obtain difference points between the preprocessed golden template image and the preprocessed character test image, selecting effective points in the difference points, and counting the number of the effective points;
acquiring an edge image of the golden template image, obtaining a coordinate linked list array through edge point coordinates of the edge image, traversing the coordinate linked list array to judge the fluctuation of the effective point on the edge image, and counting the fluctuation times;
judging whether the character test image is a character normal image or not according to the number of the effective points, the fluctuation times and the number of the foreground white points, and outputting a detection result.
Further, traversing the coordinate linked list array along the edge direction of the edge image, and judging the number of the effective points of each edge point coordinate in the neighborhood of the edge point coordinate and whether the effective points are in the outline of the golden template image; and setting the effective point to be positive outside the outline of the golden template image, and judging the volatility of the effective point at the edge of the golden template image when the effective point is negative on the outline of the golden template image and in the outline of the golden template image.
Further, a calculation formula for judging whether the character test image is a character normal image is as follows:
wherein, percentage represents output result value, nun _flucs represents fluctuation times, valid_points represents effective point number, and Nums_of_previous represents foreground white point number on the preprocessed golden template.
Further, the normal images of the characters are processed through the differential model to obtain golden template images, and the calculation formula is as follows:
wherein I is temp Representing golden template image, n representing normal number of images of character, i representing natural number, X i A one-dimensional vector representing normal image stretching of the ith character.
Further, the preprocessing refers to that after binarization processing is performed on the golden template image and the character test image, holes inside chip characters and noise points outside the chip characters in the golden template image and the character test image are removed.
Further, difference points between the preprocessed golden template image and the preprocessed character test image are obtained through exclusive OR operation, and an operation formula is as follows:
wherein a represents a preprocessed golden template image, b represents a preprocessed character test image, and the pad represents an exclusive or operation.
Further, a sliding window is created, the outermost layer of pixels of the sliding window are selected to carry out continuity judgment on the difference points, a threshold value is set, and if the number of continuous difference points is larger than the threshold value, the difference points are effective points.
A chip character detection apparatus comprising:
the input module is used for acquiring character images, wherein the character images comprise character normal images and character test images, and gold template images are obtained through the character normal images;
the detection module is used for respectively preprocessing the golden template image and the character test image to obtain a preprocessed golden template image and a preprocessed character test image, searching a front Jing Baidian on the preprocessed golden template image, and counting the number of foreground white points; calculating to obtain difference points between the preprocessed golden template image and the preprocessed character test image, selecting effective points in the difference points, and counting the number of the effective points; acquiring an edge image of the golden template image, obtaining a coordinate linked list array through edge point coordinates of the edge image, traversing the coordinate linked list array to judge the fluctuation of the effective point on the edge image, and counting the fluctuation times;
and the output module is used for judging whether the character test image is a character normal image or not according to the number of the effective points, the fluctuation times and the number of the foreground white points and outputting a detection result.
A computer device comprising a memory, a processor, the memory having stored thereon a computer program executable on the processor, the processor implementing the method as described above when executing the computer program.
A computer readable storage medium having stored thereon a computer program which when executed by a processor performs the method described above.
3. Advantageous effects
Compared with the prior art, the invention has the advantages that:
according to the chip character detection method, the device, the computer equipment and the storage medium, the gold template image and the character test image are processed to obtain the foreground white point, the effective point and the fluctuation times, so that whether the character test image is a character normal image or not is judged, the chip characters are detected rapidly and accurately, the recognition efficiency of the chip characters is remarkably improved, the chip production and testing equipment is promoted, the automatic detection is realized, and the quality of chip products is further improved.
Drawings
FIG. 1 is a flow chart of a method for detecting characters on a chip according to an embodiment of the invention;
FIG. 2 is a normal diagram of a character according to an embodiment of the present invention;
FIG. 3 is a character test chart according to an embodiment of the present invention;
FIG. 4 is a diagram of a golden template according to an embodiment of the present invention;
FIG. 5 is a difference diagram between a normal character diagram and a golden template diagram according to an embodiment of the present invention;
FIG. 6 is a difference diagram of a character test diagram and a golden template diagram according to an embodiment of the present invention;
FIG. 7 is a diagram of a valid point in a character normal map according to an embodiment of the present invention;
FIG. 8 is a diagram of a valid dot in a character test chart according to an embodiment of the present invention;
FIG. 9 is an edge view of a golden template image according to an embodiment of the present invention;
FIG. 10 is a diagram showing the distribution of valid points in the outline of a golden template diagram in a character normal diagram according to an embodiment of the present invention;
FIG. 11 is a diagram showing the distribution of the effective points in the outline of the golden template diagram in the character test diagram according to the embodiment of the present invention;
FIG. 12 is a fluctuation image of a character normal map according to an embodiment of the present invention;
fig. 13 is a fluctuation image of a character test chart according to an embodiment of the present invention.
Detailed Description
The invention will now be described in detail with reference to the drawings and the accompanying specific examples.
Examples
As shown in fig. 1, a method for detecting a chip character according to this embodiment is provided. Collecting character images, wherein the character images comprise character normal images and character test images, and obtaining golden template images through the character normal images; preprocessing a golden template image and a character test image respectively to obtain a preprocessed golden template image and a preprocessed character test image, searching a front Jing Baidian on the preprocessed golden template image, and counting the number of foreground white points; calculating to obtain difference points between the preprocessed golden template image and the preprocessed character test image, selecting effective points in the difference points, and counting the number of the effective points; acquiring an edge image of the golden template image, obtaining a coordinate linked list array through edge point coordinates of the edge image, traversing the coordinate linked list array to judge the fluctuation of the effective point on the edge image, and counting the fluctuation times; judging whether the character test image is a character normal image or not according to the number of the effective points, the fluctuation times and the number of the foreground white points, and outputting a detection result.
In particular, in the present embodiment, first, character images including a character normal image and a character test image are acquired. As shown in fig. 2, a character normal image, as shown in fig. 3, is a character test image. Further, a golden template image is obtained through the character normal image. Specifically, when the differential model is trained by using the obtained character normal image, the gray scale deviation of each pixel point in the character normal image is required to be calculated, so that when the character normal image is trained, the character normal image is required to be aligned, rotation and displacement are avoided, and the accuracy of the differential model is prevented from being influenced. In this embodiment, the differential model used is a prior art. Further, as shown in fig. 4, the golden template image is obtained by processing the normal image of the character through the differential model, and the calculation formula is as follows:
wherein I is temp Representing golden template image, n representing normal number of images of character, i representing natural number, X i A one-dimensional vector representing normal image stretching of the ith character.
Further, the golden template image and the character test image are preprocessed respectively. In this embodiment, preprocessing refers to performing binarization processing on the golden template image and the character test image, and the region of interest image in the golden template image and the character test image can be obtained through binarization processing, so as to further exclude noise interference in the golden template image and the character test image. It should be noted that, the golden template image and the character test image after binarization processing are still interfered by holes inside the chip characters and random noise points outside the chip characters on the shape and the characteristics of the chip characters. Thus, for the noise point outside the chip character, a current point is set, whether the foreground white point exists in the field of the chip character is judged, if the foreground white point exists in the field, the current point is considered to be an isolated point, and the isolated point is deleted. Note that, in this embodiment, the front Jing Baidian refers to the chip character target of interest in the golden template image and the character test image. And establishing a zero matrix which is equal to the character test image in size for the holes in the chip characters, setting a current point, and filling pixels around the current point if the current point is a foreground white point so as to eliminate the holes. It should be noted that, in practical application, the diameter of the hole inside the chip character will not exceed 4 pixels, so that 4 pixels are optimally filled around the current point. After the golden template image and the character test image are preprocessed respectively, searching the front Jing Baidian on the preprocessed golden template image, and counting the number of foreground white points. It should be noted that, the foreground white point on the preprocessed golden template image is fixed and does not generate distortion change in detection.
Further, difference points between the preprocessed golden template image and the preprocessed character test image are obtained through calculation, effective points in the difference points are selected, and the number of the effective points is counted. Specifically, a difference point between the preprocessed golden template image and the preprocessed character test image is obtained through exclusive or operation, and an operation formula is as follows:
wherein a represents a preprocessed golden template image, b represents a preprocessed character test image, and the pad represents an exclusive or operation. As shown in fig. 5, the difference map of the character normal image and the golden template image after the exclusive or operation is shown in fig. 6, the difference map of the character test image and the golden template image after the exclusive or operation is shown. Further, a sliding window is created, the outermost layer of pixels of the sliding window are selected to carry out continuity judgment on the difference points, a threshold value is set, and if the number of continuous difference points is larger than the threshold value, the difference points are effective points. In this embodiment, the size of the set threshold is one third of the size of the sliding window. If the sliding window size is 5 pixels×5 pixels for 25 pixels, the threshold is rounded, and the threshold is set to 8 pixels. It should be noted that, in this embodiment, creating a sliding window is the prior art. As shown in fig. 7, the valid dot pattern in the character normal image, as shown in fig. 8, the valid dot pattern in the character test image.
Further, as shown in fig. 9, an edge image of the golden template image is obtained, a coordinate linked list array is obtained through edge point coordinates of the edge image, the fluctuation of the effective point on the edge image is judged through traversing the coordinate linked list array, and the fluctuation times are counted. Specifically, an edge image of the outermost layer of the golden template image is obtained, a rectangular coordinate system is established, and coordinates of all edge points on the edge image are obtained. Firstly, determining an edge initial point, in this embodiment, preferably, selecting the minimum point on the abscissa as the edge initial point, and searching the number of edge points along each edge point, wherein the searching direction can be clockwise or anticlockwise, and recording the coordinates of the edge points, thereby obtaining the coordinate linked list array. Further, traversing the coordinate linked list array along the edge direction of the edge image, and judging the number of the effective points of each edge point coordinate in the neighborhood and whether the effective points are in the outline of the golden template image. As shown in fig. 10, the distribution diagram of the effective points in the golden template image outline in the character normal image is shown in fig. 11, and the distribution diagram of the effective points in the golden template image outline in the character test image is shown in fig. 11. Further, the effective point is set to be positive outside the outline of the golden template image, the effective point is set to be negative on the outline of the golden template image and in the outline of the golden template image, and the fluctuation of the effective point at the edge of the golden template image is judged. In this embodiment, the rectangular coordinate system is established to judge the fluctuation conditions of the character normal image and the character test image on the golden template image outline and in the golden template image outline, so as to count the fluctuation times. As shown in fig. 12, the wave diagram of the effective point in the golden template image edge in the character normal image is shown in fig. 13, and the wave diagram of the effective point in the character test image is shown in the golden template image edge. According to the fluctuation peak-valley value, the fluctuation times of the effective points in the normal character image at the edge of the golden template image are less, and the fluctuation times of the effective points in the character test image at the edge of the golden template image are more.
Finally, judging whether the character test image is a character normal image or not according to the number of effective points, the fluctuation times and the number of foreground white points of the preprocessed golden template image, wherein the calculation formula is as follows:
wherein, percentage represents output result value, nun _flucs represents fluctuation times, valid_points represents effective point number, and Nums_of_previous represents foreground white point number of the preprocessed golden template image. Since the foreground white point value on the preprocessed golden template image is fixed, when detecting whether the character test image is a character normal image, only the effective points and the fluctuation times in the difference points between the preprocessed golden template image and the preprocessed character test image need to be counted. Further, in this embodiment, the percentage value is set to 1, so it is known that when the percentage is greater than or equal to 1, the input character test image is not a character normal image, and the chip characters on the character test image are fuzzy distortion or irregular characters; when the percentage is less than 1, the chip character on the input character test image is a normal character.
Therefore, the chip character detection method provided by the embodiment can be used for rapidly and accurately detecting the chip characters, the recognition efficiency of the chip characters is remarkably improved, chip production and test equipment is promoted to realize automatic detection, and the quality of chip products is further improved.
The embodiment also provides a chip character detection device, which comprises an input module, a detection module and an output module. The input module acquires character images, wherein the character images comprise character normal images and character test images, and golden template images are obtained through the character normal images. The detection module is used for respectively preprocessing the golden template image and the character test image to obtain a preprocessed golden template image and a preprocessed character test image, searching a front Jing Baidian on the preprocessed golden template image, and counting the number of foreground white points; calculating to obtain difference points between the preprocessed golden template image and the preprocessed character test image, selecting effective points in the difference points, and counting the number of the effective points; acquiring an edge image of the golden template image, obtaining a coordinate linked list array through edge point coordinates of the edge image, traversing the coordinate linked list array to judge the fluctuation of the effective point on the edge image, and counting the fluctuation times. And the output module judges whether the character test image is a character normal image or not according to the number of the effective points, the fluctuation times and the number of the foreground white points and outputs a detection result. The chip character detection device provided in this embodiment can implement any one of the chip character detection methods, and a specific working process of the chip character detection device may refer to a corresponding process in the chip character detection method embodiment. The method and apparatus provided in this embodiment may be implemented in other manners. For example, the device embodiments described above are merely illustrative; for example, the division of a module is merely a logical function division, and there may be another division manner when actually implemented, for example, a plurality of units or components may be combined or may be integrated into another system, or some features may be omitted or not performed. In addition, the connections or communications shown or discussed as being between or among each other may be indirect coupling or communications via interfaces, devices, or elements, or may be electrical, mechanical, or other forms of connection.
The embodiment also provides computer equipment. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the method of chip character detection when executing the computer program.
The present embodiment also provides a computer-readable storage medium. A computer-readable storage medium having stored thereon a computer program which, when executed by a processor, performs a chip character detection method as described in the present embodiment. Wherein a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device; program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
The foregoing has been described schematically the invention and embodiments thereof, which are not limiting, but are capable of other specific forms of implementing the invention without departing from its spirit or essential characteristics. The drawings are also intended to depict only one embodiment of the invention, and therefore the actual construction is not intended to limit the claims, any reference number in the claims not being intended to limit the claims. Therefore, if one of ordinary skill in the art is informed by this disclosure, a structural manner and an embodiment similar to the technical scheme are not creatively designed without departing from the gist of the present invention, and all the structural manners and the embodiment are considered to be within the protection scope of the present patent. In addition, the word "comprising" does not exclude other elements or steps, and the word "a" or "an" preceding an element does not exclude the inclusion of a plurality of such elements. The various elements recited in the product claims may also be embodied in software or hardware. The terms first, second, etc. are used to denote a name, but not any particular order.
Claims (8)
1. A chip character detection method comprises the following steps:
collecting character images, wherein the character images comprise character normal images and character test images, and obtaining golden template images through the character normal images;
preprocessing a golden template image and a character test image respectively to obtain a preprocessed golden template image and a preprocessed character test image, searching a front Jing Baidian on the preprocessed golden template image, and counting the number of foreground white points;
calculating to obtain difference points between the preprocessed golden template image and the preprocessed character test image, creating a sliding window, selecting the outermost layer of pixels of the sliding window to carry out continuity judgment on the difference points, setting a threshold value, if the number of continuous difference points is larger than the threshold value, taking the difference points as effective points, selecting the effective points in the difference points, and counting the number of the effective points;
acquiring an edge image of the golden template image, obtaining a coordinate linked list array through edge point coordinates of the edge image, traversing the coordinate linked list array to judge the fluctuation of the effective point on the edge image, and counting the fluctuation times; traversing the coordinate linked list array along the edge direction of the edge image, judging the number of effective points of each edge point coordinate in the neighborhood of the edge point coordinate and whether the effective points are in the golden template image contour, setting the effective points to be positive outside the golden template image contour, setting the effective points to be negative on the golden template image contour and in the golden template image contour, and judging the fluctuation of the effective points at the edge of the golden template image;
judging whether the character test image is a character normal image or not according to the number of the effective points, the fluctuation times and the number of the foreground white points, and outputting a detection result.
2. The method for detecting a character on a chip according to claim 1, wherein the calculation formula for judging whether the character test image is a character normal image is as follows:
wherein, percentage represents output result value, nun _flucs represents fluctuation times, valid_points represents effective point number, and Nums_of_previous represents foreground white point number on the preprocessed golden template.
3. The method for detecting chip characters according to claim 1, wherein the golden template image is obtained by processing the normal image of the character by a differential model, and the calculation formula is as follows:
wherein I is temp Representing golden template image, n representing normal number of images of character, i representing natural number, X i A one-dimensional vector representing normal image stretching of the ith character.
4. The method for detecting chip characters according to claim 1, wherein the preprocessing is to remove holes inside chip characters and noise points outside chip characters in the golden template image and the character test image after binarizing the golden template image and the character test image respectively.
5. The method for detecting characters on a chip according to claim 4, wherein the difference point between the preprocessed golden template image and the preprocessed character test image is obtained by exclusive or operation, and the operation formula is:
wherein a represents a preprocessed golden template image, b represents a preprocessed character test image, and the pad represents an exclusive or operation.
6. A chip character detection device, comprising:
the input module is used for acquiring character images, wherein the character images comprise character normal images and character test images, and gold template images are obtained through the character normal images;
the detection module is used for respectively preprocessing the golden template image and the character test image to obtain a preprocessed golden template image and a preprocessed character test image, searching a front Jing Baidian on the preprocessed golden template image, and counting the number of foreground white points; calculating to obtain difference points between the preprocessed golden template image and the preprocessed character test image, creating a sliding window, selecting the outermost layer of pixels of the sliding window to carry out continuity judgment on the difference points, setting a threshold value, if the number of continuous difference points is larger than the threshold value, taking the difference points as effective points, selecting the effective points in the difference points, and counting the number of the effective points; acquiring an edge image of the golden template image, obtaining a coordinate linked list array through edge point coordinates of the edge image, traversing the coordinate linked list array to judge the fluctuation of the effective point on the edge image, and counting the fluctuation times; traversing the coordinate linked list array along the edge direction of the edge image, judging the number of effective points of each edge point coordinate in the neighborhood of the edge point coordinate and whether the effective points are in the golden template image contour, setting the effective points to be positive outside the golden template image contour, setting the effective points to be negative on the golden template image contour and in the golden template image contour, and judging the fluctuation of the effective points at the edge of the golden template image;
and the output module is used for judging whether the character test image is a character normal image or not according to the number of the effective points, the fluctuation times and the number of the foreground white points and outputting a detection result.
7. A computer device comprising a memory, a processor, the memory having stored thereon a computer program executable on the processor, characterized in that the processor implements the method of any of the preceding claims 1-5 when executing the computer program.
8. A computer readable storage medium having stored thereon a computer program, characterized in that the computer program when executed by a processor performs the method of any of the preceding claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310892133.3A CN116612476B (en) | 2023-07-20 | 2023-07-20 | Chip character detection method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310892133.3A CN116612476B (en) | 2023-07-20 | 2023-07-20 | Chip character detection method and device, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116612476A CN116612476A (en) | 2023-08-18 |
| CN116612476B true CN116612476B (en) | 2023-09-22 |
Family
ID=87675054
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310892133.3A Active CN116612476B (en) | 2023-07-20 | 2023-07-20 | Chip character detection method and device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116612476B (en) |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4331955A (en) * | 1980-08-07 | 1982-05-25 | Eltra Corporation | Method and apparatus for smoothing outlines |
| JPS59231682A (en) * | 1983-06-13 | 1984-12-26 | Nippon Telegr & Teleph Corp <Ntt> | Character discriminating device |
| JPH08185478A (en) * | 1994-12-28 | 1996-07-16 | Nippon Digital Kenkyusho:Kk | Character recognition device |
| JPH10289311A (en) * | 1997-04-15 | 1998-10-27 | Toppan Printing Co Ltd | Check method and device for printed matter |
| JP2005182838A (en) * | 2005-01-26 | 2005-07-07 | Axissoft Corp | System, program and method for processing external character |
| JP2008238795A (en) * | 2007-03-29 | 2008-10-09 | Seiko Epson Corp | Recorder, control method of recorder and control program |
| CN103278113A (en) * | 2013-02-27 | 2013-09-04 | 中国林业科学研究院木材工业研究所 | Method for rapidly measuring surface roughness of timber in non-contact manner |
| CN104392205A (en) * | 2014-10-24 | 2015-03-04 | 浙江力石科技股份有限公司 | Abnormal vehicle license plate recognition method and system |
| CN105865512A (en) * | 2016-05-18 | 2016-08-17 | 合肥图迅电子科技有限公司 | Double-end character visual inspection system |
| CN108229483A (en) * | 2018-01-11 | 2018-06-29 | 中国计量大学 | Based on the doorplate pressed characters identification device under caffe and soft triggering |
| CN112763513A (en) * | 2021-01-26 | 2021-05-07 | 广东奥普特科技股份有限公司 | Character defect detection method |
| CN113433068A (en) * | 2021-07-02 | 2021-09-24 | 合肥图迅电子科技有限公司 | Detection device for detecting chip characters covered by film |
| CN114152214A (en) * | 2021-12-03 | 2022-03-08 | 武汉汉宁轨道交通技术有限公司 | Method, device and system for detecting loss of steel rail profile |
| WO2022150857A1 (en) * | 2021-01-10 | 2022-07-14 | Pauna Raluca | Apparatus and a method of reading and interpreting the image of a medical special investigations test |
| CN114913534A (en) * | 2022-07-19 | 2022-08-16 | 北京嘉沐安科技有限公司 | Block chain-based network security abnormal image big data detection method and system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7149356B2 (en) * | 2002-07-10 | 2006-12-12 | Northrop Grumman Corporation | System and method for template matching of candidates within a two-dimensional image |
-
2023
- 2023-07-20 CN CN202310892133.3A patent/CN116612476B/en active Active
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4331955A (en) * | 1980-08-07 | 1982-05-25 | Eltra Corporation | Method and apparatus for smoothing outlines |
| JPS59231682A (en) * | 1983-06-13 | 1984-12-26 | Nippon Telegr & Teleph Corp <Ntt> | Character discriminating device |
| JPH08185478A (en) * | 1994-12-28 | 1996-07-16 | Nippon Digital Kenkyusho:Kk | Character recognition device |
| JPH10289311A (en) * | 1997-04-15 | 1998-10-27 | Toppan Printing Co Ltd | Check method and device for printed matter |
| JP2005182838A (en) * | 2005-01-26 | 2005-07-07 | Axissoft Corp | System, program and method for processing external character |
| JP2008238795A (en) * | 2007-03-29 | 2008-10-09 | Seiko Epson Corp | Recorder, control method of recorder and control program |
| CN103278113A (en) * | 2013-02-27 | 2013-09-04 | 中国林业科学研究院木材工业研究所 | Method for rapidly measuring surface roughness of timber in non-contact manner |
| CN104392205A (en) * | 2014-10-24 | 2015-03-04 | 浙江力石科技股份有限公司 | Abnormal vehicle license plate recognition method and system |
| CN105865512A (en) * | 2016-05-18 | 2016-08-17 | 合肥图迅电子科技有限公司 | Double-end character visual inspection system |
| CN108229483A (en) * | 2018-01-11 | 2018-06-29 | 中国计量大学 | Based on the doorplate pressed characters identification device under caffe and soft triggering |
| WO2022150857A1 (en) * | 2021-01-10 | 2022-07-14 | Pauna Raluca | Apparatus and a method of reading and interpreting the image of a medical special investigations test |
| CN112763513A (en) * | 2021-01-26 | 2021-05-07 | 广东奥普特科技股份有限公司 | Character defect detection method |
| CN113433068A (en) * | 2021-07-02 | 2021-09-24 | 合肥图迅电子科技有限公司 | Detection device for detecting chip characters covered by film |
| CN114152214A (en) * | 2021-12-03 | 2022-03-08 | 武汉汉宁轨道交通技术有限公司 | Method, device and system for detecting loss of steel rail profile |
| CN114913534A (en) * | 2022-07-19 | 2022-08-16 | 北京嘉沐安科技有限公司 | Block chain-based network security abnormal image big data detection method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116612476A (en) | 2023-08-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11854173B2 (en) | System and method for finding lines in an image with a vision system | |
| US6674904B1 (en) | Contour tracing and boundary detection for object identification in a digital image | |
| CN109426789B (en) | Hand and image detection method and system, hand segmentation method, storage medium and device | |
| US6751361B1 (en) | Method and apparatus for performing fixturing in a machine vision system | |
| CN112991374B (en) | Canny algorithm-based edge enhancement method, canny algorithm-based edge enhancement device, canny algorithm-based edge enhancement equipment and storage medium | |
| CN113538491B (en) | Edge identification method, system and storage medium based on self-adaptive threshold | |
| CN110475078B (en) | Camera exposure time adjusting method and terminal equipment | |
| CN114612410A (en) | Novel clothing detects device | |
| CN113362238A (en) | Test image processing method and device, electronic equipment and storage medium | |
| CN116612476B (en) | Chip character detection method and device, computer equipment and storage medium | |
| CN113160223A (en) | Contour determination method, contour determination device, detection device and storage medium | |
| CN115690104B (en) | Wafer crack detection method and device and storage medium | |
| CN108648229B (en) | Human back feature point extraction method based on Kinect camera | |
| CN111667429B (en) | Target positioning correction method for inspection robot | |
| CN112750143B (en) | Method for extracting morphological characteristics of stem flexible fish based on extremum method | |
| CN111476770B (en) | Slag detection method, device, equipment and medium based on image processing | |
| CN110298799B (en) | PCB image positioning correction method | |
| CN114022449A (en) | Image processing method and system in billiard game | |
| CN108256525B (en) | Guide rail target position detection method based on image processing | |
| CN112967303B (en) | Image edge detection and edge precision verification method thereof | |
| CN117830336B (en) | Polygonal contour detection method and device based on line scanning camera imaging | |
| JP2008181261A (en) | Method and device for extracting contour line of object | |
| CN116012323A (en) | Image definition calculation method, image processing model training method and device | |
| CN116863463A (en) | Egg assembly line rapid identification and counting method | |
| CN117011596A (en) | Circle identification and circle center positioning method and device for visual measurement of structural movement |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |