TW202312021A - Automatic recognizing system and automatic recognizing method for a pick-up position of a printed circuit board - Google Patents

Abstract

An automatic recognizing system and an automatic recognizing method for a pick-up position of a printed circuit board are provided. A simplifying process is executed to filter out the recognition noise in a layout drawing of a standard printed circuit board to obtain a training layout drawing, and the training layout drawing configured a pick-up position is inputted to a training model to update the training model to obtain a capacity of recognizing the same type of the standard printed circuit board. A matching process is executed on a target image of a target printed circuit board to determine a pick-up position of the target image while the target image is recognized as the standard circuit board by the training model. The present disclosure can accurately recognize the pick-up position of the target image, and implement the unmanned automatic pick-up for the printed circuit board.

Description

Automatic identification system and automatic identification method for circuit board grasping position

The invention relates to an automatic identification system and method, in particular to an automatic identification system and an automatic identification method for the grasping position of a circuit board.

In order to grasp the circuit board from the correct grasping position, a method for automatically identifying the grasping position has been proposed.

Specifically, the existing method is to manually capture a large number of images of the circuit board, use these images to perform training to generate a recognition model, and then use the recognition model to recognize the circuit board.

In the above method, because the image content collected by different people and the learning algorithm used are usually different, the accuracy of the recognition model will be uneven.

Specifically, since there are a large number of complex components on the circuit board, the flexible board is prone to deformation and reflection, and the training images captured manually usually contain a lot of noise, which reduces the accuracy of the recognition model.

In addition, the accuracy of the recognition model is closely related to the selection of the recognition region and recognition features in the training images. Inappropriate learning algorithms and improper recognition features will reduce the accuracy of the recognition model.

Therefore, the existing method for automatically identifying the grasping position of the circuit board has the above-mentioned problems caused by human factors, and a more effective solution is urgently needed to be proposed.

The main purpose of the present invention is to provide an automatic identification system and automatic identification method for the grasping position of the circuit board, which can completely eliminate the human intervention that causes the accuracy of the training model to be unstable and provide stable identification features.

In one embodiment, a method for automatic identification of a circuit board picking position includes: a) Obtaining a plurality of layout diagrams of a plurality of standard circuit boards of different types, and performing a simplification on the layout diagrams of each of the standard circuit boards processing, to obtain a training layout that eliminates identification noise; b) performing a training process on a training model based on each of the training layouts so that the training model has the ability to identify different types of the plurality of standard circuit boards, wherein Each of the training layouts is set with a grab position; c) inputting a target image of a target circuit board into the training model to perform a recognition process on the target image; and, d) identifying that the target image meets any of the criteria circuit board, a matching process is performed on the target image to determine a capture position of the target image based on the capture position of the training layout diagram of the standard circuit board; the recognition process includes: e1) the target performing a target edge analysis on the image to obtain a plurality of target component edge features of the target image; e2) calculating a target image for each of the standard circuit boards based on the target component edge features and a plurality of identification features of each of the standard circuit boards similarity score; and, e3) determining an identification result based on the standard circuit board with the highest score.

In one embodiment, an automatic identification system for picking a circuit board position includes: an image capturing device, a picking device and a control device. The image capture device is used to photograph a target circuit board to obtain a target image. The grabbing device is used for grabbing the circuit board. The control device is connected with the image capture device and the capture device, and includes a simplified module, a training module and a recognition module. The simplification module is configured to perform a simplification process on a layout of a standard circuit board to remove identification noise to obtain a training layout. The training module is set to input the training layout to a training model to enable the training model to have the ability to recognize the same type of circuit boards, wherein a grasping position is set on the training layout. The identification module inputs the target image to the training model to perform identification, and when identifying the target image as the standard circuit board, performs a matching process on the target image based on the matching training layout diagram of the standard circuit board The capture position determines a capture position of the target image. The control device is configured to control the grabbing device to grab the target circuit board based on the grabbing position of the target image.

The invention can accurately identify the grabbing position of the target image, and can realize unmanned automatic grabbing of the circuit board.

A preferred embodiment of the present invention will be described in detail below with reference to the drawings.

In order to realize automation and unmanned production line, the accuracy of automatic clamping of circuit boards is very important.

In order to accurately identify the clamping position of the circuit board (that is, the position where the circuit board and its components will not be damaged when performing clamping), the present invention proposes an automatic identification system and automatic identification method for the grasping position of the circuit board, which can be used The layout drawing trains the training model so that the training model can correctly identify such circuit boards. Moreover, the present invention uses the trained training model to identify the type of the target circuit board (that is, the physical circuit board currently to be processed), and locates the grabbing position according to the identification result.

Please refer to FIG. 1 , which is a structural diagram of an automatic identification system according to an embodiment of the present invention. The automatic identification system of this embodiment mainly includes an image capture device 11 , a capture device 12 , a storage device 13 and a control device 10 connected to the above devices.

The image capture device 11, such as a color camera, an infrared camera, a 3D camera or other optical cameras, is used to photograph the target circuit board 20 to obtain target images (such as color images, grayscale images, black and white images, 3D images, etc.).

The grabbing device 12 , such as an automated machine capable of grabbing circuit boards, is used to grab the target circuit board 20 and move it to a designated location (such as a processing location described later). The grabbing device 12 can grab the circuit board through methods including clamping (such as mechanical clamping), suction (such as magnetic force or suction force), and the like.

The storage device 13 is used for storing data. In one embodiment, the storage device 13 can store the layout diagrams 130 of various standard circuit boards. The aforementioned layout diagrams 130 are 2D images, and can be executed through the design diagrams (usually vector diagrams or three-dimensional diagrams) of various standard circuit boards. Convert to get it.

In one embodiment, the storage device 13 can store the training model 131 , such as a machine learning model or a data model that records image recognition features. The training model 131 is used to receive data training to learn the ability to recognize various standard circuit boards.

The control device 10, such as a processor, a machine control computer or a control box equipped with a processor, is used to control the operation of each device of the automatic identification system, such as executing the training mode and grasping mode described later.

Please also refer to FIG. 2 , which is a structural diagram of an automatic identification system according to an embodiment of the present invention. Compared with the embodiment of FIG. 1, the automatic identification system of this embodiment further includes processing equipment 30 connected to the control equipment 10, such as circuit board manufacturing equipment (such as welding/assembly equipment) or testing equipment (such as inspection components/contacts) device of). The processing equipment 30 is used to perform processing (such as soldering, assembly or inspection) on the target circuit board 20 placed at the processing position.

In one embodiment, the automatic identification system further includes a human-machine interface 31 connected to the control device 10, such as any combination of input/output devices such as touch screens, buttons, display screens, indicator lights, and buzzers, for providing information and interact with users.

In one embodiment, the automatic identification system further includes a communication interface 32 connected to the control device 10, such as a network interface card, a Wi-Fi module, a cellular network module, etc., which can be connected to a local area network or the Internet. .

In one embodiment, the communication interface 32 can be used to connect to the computing platform 40 (such as a cloud server or a remote host) and communicate with the computing platform 40 .

In one embodiment, the aforementioned layout diagram 130 and training model 131 can be stored in the computing platform 40, and the computing platform 40 can be used to execute the training mode described later to use the layout diagram 130 (which can be provided by the automatic identification system and obtained from the circuit board database. Or obtain it from the design drawing by itself) to perform training on the training model 131, and send the trained training model 131 to the automatic recognition system to execute the grasping mode.

In one embodiment, the automatic identification system further includes an electric device (not shown) connected to the control device 10. The electric device is used to connect to a fixed power source (such as mains) and convert the received power into the power required for the operation of the automatic identification system.

Please also refer to FIG. 3 , which is a structural diagram of a control device according to an embodiment of the present invention. In this embodiment, the control device 10 may include modules 500-510. These modules 500-510 are respectively set to implement different functions.

The photographing control module 500 is configured to control the image capture device 11 to photograph the target circuit board 20 to obtain a target image.

The simplification module 501 is set to perform simplification processing on the image to filter out the identification noise in the image and retain identification features with high identifiability, such as distinctive patterns, pattern combinations and/or pattern distribution, etc. .

In one embodiment, simplified module 501 may include modules 502-506.

The pre-processing module 502 is configured to perform pre-processing on the image, such as cropping, color space conversion, contrast emphasis, etc., so as to make the image conform to the specified format or improve the visibility.

The contour extraction module 503 is configured to recognize the contours of multiple components of the circuit board in the image.

Fragmentary element filtering module 504 is configured to filter out smaller area elements from the image. These smaller components (such as tiny copper foils or lines) are like small-area noise on the image, which cannot be used as identification features and will become noise for image identification.

The repeated element filtering module 505 is configured to identify a large number of repeated elements in the image, and filter out the repeated elements from the image. These repeating elements are repeating or similar designs in close positions, have the same or similar appearance and will affect the subsequent positioning accuracy, and are not suitable as identification features.

The zigzag component filtering module 506 is configured to identify zigzag components (such as components with multiple corners) in the image and filter the component from the image. Due to the unstable angle of the component, the bending component will affect the subsequent positioning accuracy, so it is not suitable as an identification feature.

The training module 507 is configured to execute the training mode. The training module 507 can input a training image (such as a training layout) to the training model 131 to perform a training process on the training model 131 so that it has the ability to recognize the same type of circuit board.

In one embodiment, the training image can be set with grasping positions, so that the trained training model 131 can automatically recognize the grasping positions.

The grasping control module 509 is configured to control the grasping device 12 to perform grasping on the grasping position of the target circuit board 20 based on the grasping position of the recognized target image.

In one embodiment, the grabbing control module 509 can further control the grabbing device 12 to transport the target circuit board 20 to the processing position after the grabbing is completed.

The processing control module 510 is configured to control the processing equipment 30 to process the target circuit board 20 at the processing position.

The aforementioned modules 500-510 are connected to each other (which may be electrical connection and information connection), and may be hardware modules (such as electronic circuit modules, integrated circuit modules, SoC, etc.), software modules ( For example, firmware, operating system, or application program) or a mix of software and hardware modules, without limitation.

It is worth mentioning that when the aforementioned modules are software modules (such as firmware, operating system or application program), the storage device 13 or the computing platform 40 may include a non-transitory computer-readable recording medium (not shown in the figure) ), the aforementioned non-transitory computer-readable recording medium stores a computer program 132, and the computer program 132 records a computer-executable program code. After the processor of the control device 10 or the computing platform 40 executes the aforementioned program code, it can implement Corresponding to the function of the module.

Please also refer to FIG. 4 , which is a schematic diagram of an automatic identification data flow according to an embodiment of the present invention. FIG. 4 shows the data flow of the training mode (upper figure) and the capture mode (lower figure) of an embodiment of the present invention.

As shown in the upper figure of FIG. 4 , the present invention first performs simplified processing on the layout diagram 130 of the standard circuit board to generate training data (i.e., the training layout diagram), and then inputs the training data into the training model 131 to perform training to obtain the training data identifying features. By performing training on different training data, the identification features of different standard circuit boards can be obtained, that is, the training model 131 can identify different types of circuit boards.

As shown in the lower figure of FIG. 4 , the present invention then inputs the target image of the target circuit board 20 into the trained training model 131 to identify the circuit board type of the target circuit board 20 , and obtains the corresponding circuit board type according to the identified circuit board type. Identification features (including the capture position), and finally use the obtained identification features to perform matching processing on the target image, so as to confirm the capture position of the target image by locating these identification features.

The present invention has a very high performance because it uses the training layout diagram (electronic image file obtained from the design drawing) without noise or with little noise to train the identification features, rather than the image obtained by shooting (including a large amount of noise). Identification accuracy and positioning accuracy.

Please also refer to FIG. 5 , which is a flowchart of an automatic identification method according to an embodiment of the present invention. The automatic identification method of each embodiment of the present invention can be applied to any system shown in FIGS. 1-4 and 8 .

The automatic identification method of this embodiment includes a training mode (steps S10-S11).

Step S10: The control device 10 first obtains the layout diagram 130 of the standard circuit board, and performs a simplified process on the layout diagram 130 through the simplification module 501 to filter out the recognition noise, so as to obtain a training layout diagram without the recognition noise.

The aforementioned layout diagram 130 is a 2D image showing the distribution of electronic components and circuit layout of a standard circuit board.

Step S11: The control device 10 inputs the generated training layout diagram to the training model 131 through the training module 507 to perform training processing on the training model 131, so that the training model 131 has the ability to identify the same type of circuit boards.

In one embodiment, the training layout diagram is set with grasping positions suitable for this type of circuit board, such as a position with fewer three-dimensional components, a position with fewer or no components, a position with higher toughness in the circuit board, and a position that is easy to grasp. Take the position to maintain balance in the process (such as the center of gravity or center of the circuit board), etc. When the trained training model 131 is input with the same type of circuit board image, it can recognize the grasping position suitable for the circuit board from the input image. Moreover, when grabbing the circuit board in this grabbing position, since the grabbing position has fewer components, higher toughness and/or easy balance, the probability of the grabbing action causing damage to the circuit board can be greatly reduced, such as damage can be avoided Components, damaged circuit boards, dropped circuit boards during clamping, etc.

In one embodiment, the present invention can obtain multiple layout diagrams 130 of multiple standard circuit boards of different types, and execute the above-mentioned training mode on the multiple layout diagrams 130, so that the training model 131 can simultaneously recognize different types of multiple layout diagrams. capacity of a standard circuit board.

In one embodiment, the present invention executes the training mode on multiple layout diagrams 130 of multiple standard circuit boards of multiple types, and can generate classification rules for multiple standard circuit boards, and these classification rules can be used to classify the image features of the input image Classification is performed to determine the type of board to which the input image belongs.

The automatic recognition method of this embodiment also includes a grasping mode executed after the training is completed (steps S20-S24).

Step S20: The control device 10 can firstly control the image capture device 11 through the shooting control module 500 to take pictures of the target circuit board 20 arriving at the ready position to obtain the target image, and input the target image into the training model through the identification module 508 131 to perform identification processing.

Step S21: The control device 10 determines whether the input target image conforms to any pre-established standard circuit board according to the result of the identification process.

In one embodiment, in the identification process, the training model 131 can compare the target image with the image features of each standard circuit board established in advance, and determine that the target image contains all or most of the images of any standard circuit board When the characteristics (including the shape comparison and the position comparison match), it is determined that the target circuit board 20 belongs to the standard circuit board.

In one embodiment, during the identification process, the training model 131 can extract the image features of the target image, and compare the image features with the classification rules established in advance, so as to determine the standard circuit to which the target circuit board 20 belongs through classification. plate.

If the control device 10 determines that the target image conforms to any standard circuit board, step S22 is executed; otherwise, the control device 10 executes step S24.

Step S22: The control device 10 obtains the identification-related data (such as identification features or training layout diagrams, including the grasping position) of the standard circuit board that meets the requirements, and performs matching processing on the target image and the identification-related information through the identification module 508 to determine The capture position in the target image. The capture position in the target image corresponds to the capture position of the training layout map set when executing the training mode.

In one embodiment, the identification-related data includes the arrangement relationship between identification features and grasping positions. After the control device 10 identifies these identification features from the target image, it can calculate the grasping position in the target image according to the above-mentioned arrangement relationship. Location.

In one embodiment, the recognition-related data includes a training layout with grasping positions set. After the control device 10 recognizes a plurality of recognition features from the target image, it can use these features in the training layout according to the direction, rotation angle, distance, etc., to adjust the target image (such as scaling and/or rotation), so that the target image and the training layout map present the same direction and/or size, and it can be clearly known that the capture position of the training layout map is located in the target image Corresponding position.

Step S23: According to the capture position of the determined target image, the control device 10 converts the image position into the robot coordinate position through the capture control module 509, generates a corresponding capture command, and executes the capture command to control the capture The picking device 12 grabs the target circuit board 20 from the grabbing position of the target circuit board 20 .

In one embodiment, the control device 10 can further control the grabbing device 12 to move the grabbed target circuit board 20 to the processing position of the processing device 30 .

Moreover, the control device 10 can process the target circuit board 20 at the processing position by the processing device 30 through the processing control module 510 .

If in step S21, the control device 10 determines that the target image does not conform to all standard circuit boards, then execute step S24: the control device 10 issues a warning through the man-machine interface 31 to remind the user that the identification fails.

In one embodiment, when the target image does not conform to all standard circuit boards, the control device 10 can automatically use machine learning to identify the suitable grabbing position of the target circuit board 20, such as the position with low component density, the center or The position of the center of gravity, etc., and then perform grabbing on the identified grabbing position.

In one embodiment, when the target image does not conform to all standard circuit boards, the control device 10 can be manually operated to perform the capture.

The invention can accurately identify the grabbing position of the target image, and can realize unmanned automatic grabbing of the circuit board.

Please refer to FIG. 8 , which is a schematic diagram of clamping a circuit board according to an embodiment of the present invention. In this embodiment, the grabbing device 12 includes a suction and driving device 60 and a circuit board transport device 61 connected to the control device 10 .

Firstly, the circuit board transportation device 61 can move the target circuit board 20 to the grasping range of the suction and driving device 60 (ie, the ready position 62 ). Here, the target circuit board 20 is transported by the trackless automatic transfer vehicle, and the target circuit board 20 is sent to the photographing position at a specified height by the lifting platform to trigger the image capture device 11 to capture the target image, or a conveyor belt or other circuit board transport equipment can be used instead.

Then, the suction and driving device 60 can move the suction nozzle to the preparation position 62 through a driving mechanism (such as a robot arm) to suction the target circuit board 20 and leave the preparation position 62, as shown in position 62'.

Then, the suction and driving device 60 can move to the processing position through the driving mechanism, and release the target circuit board 20 at the processing position.

Thereby, the present invention can realize unmanned automatic grabbing and placing of the circuit board.

Please refer to FIG. 5 and FIG. 6 together. FIG. 6 is a flowchart of simplified processing according to an embodiment of the present invention. Compared with the embodiment in FIG. 5 , the simplified processing of the automatic identification method in this embodiment includes the following steps S30 - S35 .

Step S30: The control device 10 obtains the layout diagram 130 of the standard circuit board.

In one embodiment, the control device 10 may first obtain the design drawing of the standard circuit board, and perform 2D conversion processing on the design drawing to obtain the 2D layout drawing.

The aforementioned design drawings can be in Gerber format or computer-aided design (CAD) format. The obtained layout map 130 can be a color, black and white or gray scale 2D image.

Next, the control device 10 may execute steps S31-S35 to filter noise from the layout diagram 13 to obtain a training layout diagram with no recognition noise or very little recognition noise.

It is worth mentioning that the following steps S31-S35 can be executed in whole or only in part, and there is no order of execution among them, and whether they are executed or not and the order of execution can be changed arbitrarily according to user's needs.

Step S31 : the control device 10 executes preprocessing on the obtained layout diagram 130 through the preprocessing module 502 , so as to make the layout diagram 130 conform to a prescribed format or improve the visibility.

Steps S32-S35 are to perform noise detection through device outline.

Step S32: the control device 10 performs contour extraction processing on the layout diagram 130 through the contour extraction module 503 to identify the outermost contour of the target circuit board 20 in the layout diagram 130 to define the range of the target circuit board 20, and further identify the target circuit Outlines of various elements of the board 20 .

In one embodiment, the aforementioned contour extraction process may include Canny Algorithm, Sobel Operator or other edge detection algorithms, without limitation.

Step S33 : The control device 10 performs a piecemeal component filtering process on the layout diagram 130 through the piecemeal component filtering module 504 to filter out patterns of components whose area is smaller than the piecemeal threshold value from the layout diagram 130 .

In one embodiment, the fragmentation threshold is determined based on the copper foil area of the target circuit board 20 and the first ratio, for example, the copper foil area multiplied by the first ratio (which may be greater than 1) is used as the fragmentation threshold.

Step S34: The control device 10 performs a repeated component filtering process on the layout drawing 130 through the repeated component processing module 505 to identify multiple repeated components whose number exceeds the repetition threshold within the specified search range, and filter out the repeated components from the layout drawing 130 A pattern of multiple elements.

In one embodiment, the repetitive component filtering process includes expanding a specified search radius outward from the center of each component as a search range.

In one embodiment, the aforementioned search radius is determined based on the side length of each element and the second ratio, for example, the side length (such as the side length of the longest side) multiplied by the second ratio (which may be greater than 1) is used as the search radius.

Step S35: The control device 10 performs zigzag component filtering processing on the layout diagram 130 through the zigzag component filtering module 506 to identify components with multiple corner points (zigzag components) from the layout diagram 130 and filter out components from the layout diagram 130 picture of.

In one embodiment, the meander element filtering process identifies elements whose number of corner points is greater than a corner point threshold as meander elements.

In one embodiment, the zigzag component filtering process is to calculate the corner point-contour point ratio (ie, the ratio of corner points to all edges) between the number of corner points and the number of contour points of a component, and Elements whose corner point-contour point ratio is greater than the third ratio (may be less than 1) are regarded as meander elements.

Please refer to FIG. 9 to FIG. 12 together. FIG. 9 is a schematic diagram of the layout of an embodiment of the present invention, FIG. 10 is a schematic diagram of the processing result of fragmentary component filtering processing according to an embodiment of the present invention, and FIG. 11 is a schematic diagram of an embodiment of the present invention. A schematic diagram of the processing result of the repetitive component filtering process in an embodiment, and FIG. 12 is a schematic diagram of the processing result of the zigzag component filtering process in an embodiment of the present invention.

As shown in FIG. 9 , there are a large number of patterns 80 of fragmented components in the original unprocessed layout diagram 70 , and these patterns 80 of fragmented components will become identification noise.

As shown in FIG. 10 , the layout diagram 71 obtained after fragmentary element filtering process has filtered fragmentary element patterns 80 , but there are a large number of repetitive element patterns 81 , which will reduce the recognition accuracy.

As shown in FIG. 11 , in the layout diagram 72 obtained after filtering the repetitive elements, the pattern 81 of the repetitive element has been filtered out, but there are a small number of patterns 82 of meandering elements, which will reduce the positioning accuracy.

As shown in FIG. 12 , the pattern 82 of the meander element has been filtered out in the layout diagram 73 obtained after the meander element filtering process, and there are no other patterns that may become noise. Therefore, the layout diagram 73 can be directly used as a training layout diagram, and the image features 830-838 (including position and shape) in the layout diagram 73 can be used to identify whether the target image belongs to the same type of circuit board (such as having the same component arrangement) and line layout).

It is worth mentioning that since different types of circuit boards usually have very different component arrangements and circuit layouts, the action of filtering the above components will not cause a decrease in the recognition accuracy, but because the recognition features are more obvious, the recognition speed can be improved with precision.

Please refer to FIGS. 9 and 12-14 together. FIG. 13 is a schematic diagram of an object image according to an embodiment of the present invention, and FIG. 14 is a schematic diagram of another object image according to an embodiment of the present invention. As shown in FIG. 12 , image features 830 - 838 of standard circuit boards can be obtained through training.

In the example shown in FIG. 13, after capturing the target image of the target circuit board, processing can be performed on the target image, such as performing pre-processing or performing contour extraction processing to extract the contours of a plurality of components to obtain a processed target image 74.

In one embodiment, simplification processing may also be performed on the target image 74 to reduce noise components.

Next, the control device 10 may perform a matching process on the image features 740-748 of the target image 74 and the image features 830-838 of the standard circuit board, and find a complete match. Thereby, the control device 10 can determine that the target circuit board is the standard circuit board shown in FIG. 9 .

In the example of FIG. 14 , after capturing another target image of another target circuit board, processing can be performed on another target image, such as performing preprocessing, contour extraction processing and/or simplification processing, to obtain another processed target image. A target image 75 .

Next, the control device 10 may perform a matching process on the image features of another target image 75 (such as a plurality of squares in FIG. 14 ) and the image features 830-838 of the standard circuit board, and find a mismatch. Thereby, the control device 10 can determine that the target circuit board does not belong to the standard circuit board shown in FIG. 9 .

Please refer to FIG. 5 and FIG. 7 together. FIG. 7 is a flowchart of training processing and recognition processing according to an embodiment of the present invention. Compared with the embodiment in FIG. 5 , the training process in this embodiment includes steps S40-S41.

Step S40: The control device 10 performs training edge analysis on the input training image (ie, the training layout image corresponding to the standard circuit board) through the training module 507 to obtain a plurality of training component edge features of the training image.

Step S41: The control device 10 calculates a plurality of identification features of the standard circuit board based on the edge features of the training components through the training module 507 .

There are many existing technologies in the field of image recognition processing for feature recognition based on image edge calculation, and the present invention applies it to circuit board feature recognition.

Compared with the embodiment of FIG. 5 , the identification process of this embodiment includes steps S50-S52.

Step S50: The control device 10 performs target edge analysis on the target image through the identification module 508 to obtain a plurality of target component edge features of the target image.

In one embodiment, the edge analysis in step S40 and step S50 may include Canny Algorithm, Sobel Operator or other edge detection algorithms, and the training edge analysis and target edge analysis may use The same or different algorithms, without limitation.

Step S51: The control device 10 calculates the similarity score of the target image to each standard circuit board based on the edge features of the target component and multiple identification features of each standard circuit board through the recognition module 508 .

Step S52: The control device 10 determines the recognition result based on the standard circuit board with the highest score through the recognition module 508, and locates the multiple components of the target image based on the corresponding similarity score.

In one embodiment, if the highest similarity score is lower than the preset score critical value, the control device 10 may determine that the identification result is all mismatches; if the highest similarity score is not lower than the preset score critical value, the control device 10 The device 10 can set the identification result to be the standard circuit board corresponding to the highest similarity score.

In one embodiment, when the identification result is all mismatches, since the standard circuit board with the highest score has the highest similarity with the target circuit board 20, the control device 10 can use the standard circuit board with the highest score to compare the target image. Multiple components are positioned.

In one embodiment, during the training process, the control device 10 may perform training edge analysis on the training image (such as a training layout map) to obtain a plurality of training sample edge points (positions) of the training image and each training sample edge point Gradient direction and center of gravity (that is, the edge feature of the training component, which is an image feature), and based on these training sampling edge points and the preset edge detection range and allowable difference range to calculate multiple training similarity scores (that is, the standard circuit board identifying features).

For example, the control device 10 can expand the edge detection range of each training sampling edge point, and set the allowable difference range of the angle of the gradient direction, and compare it with the sampling edge point and the gradient direction of a hypothetical real-time image to obtain each The distance difference and gradient difference of the training sampling edge points are used as the aforementioned training similarity score.

Moreover, in the identification processing, the control device 10 may sequentially select the identification features of each standard circuit board to perform the following processing. The control device 10 can perform target analysis on the target image to obtain multiple target sampling edge points (positions) of the target image and the gradient direction of each target sampling edge point (that is, the edge feature of the target element, which is an image feature), and calculate the target sampling edge The predicted center of gravity corresponding to the point, compare multiple training similarity scores with multiple predicted gravity similarity scores corresponding to multiple predicted centers of gravity (similarity scores can be obtained by summing or averaging multiple similar scores for multiple centers of gravity), to compare The similarity of the target image to the image characteristics of the standard board.

Moreover, the control device 10 may further use the predicted center of gravity whose score is higher than the score threshold as the center of gravity of the corresponding training image, thereby achieving comparison, matching and positioning of multiple image features between the target image and the training image.

In an embodiment, the control device 10 can filter out some target sampling edge points based on a plurality of target sampling edge points and their gradient directions (the allowable difference range of the angle of the gradient direction can be further referred to), and calculate the Predict the center of gravity.

The above descriptions are only preferred specific examples of the present invention, and are not intended to limit the patent scope of the present invention. Therefore, all equivalent changes made by using the content of the present invention are all included in the scope of the present invention in the same way. Chen Ming.

10: Control equipment

11: Image capture device

12: Grabbing equipment

13: Storage equipment

130: Layout diagram

131:Training model

132: Computer program

20: Target board

30: Processing equipment

31: Man-machine interface

32: Communication interface

40:Computing platform

500: Shooting control module

501: Simplify the module

502: Preprocessing module

503:Contour extraction module

504: Fragmentary component filter module

505: Duplicate component filter module

506: Zigzag element filter module

507:Training module

508: Identification module

509: Grabbing Control Module

510: Processing control module

60: Suction and drive equipment

61: Circuit board transportation equipment

62, 62': position

70-73: layout diagram

74, 75: target image

740-748, 830-838: image characteristics

80-82: pattern

S10-S11: training steps

S20-S24: grabbing steps

S30-S35: simplified steps

S40-S41: training processing steps

S50-S52: Identification processing steps

FIG. 1 is a structural diagram of an automatic identification system according to an embodiment of the present invention.

FIG. 2 is a structural diagram of an automatic identification system according to an embodiment of the present invention.

FIG. 3 is a structural diagram of a control device according to an embodiment of the present invention.

FIG. 4 is a schematic diagram of an automatically identified data flow according to an embodiment of the present invention.

FIG. 5 is a flowchart of an automatic identification method according to an embodiment of the present invention.

Figure 6 is a flowchart of a simplified process according to one embodiment of the present invention.

FIG. 7 is a flowchart of training processing and recognition processing according to an embodiment of the present invention.

FIG. 8 is a schematic diagram of clamping a circuit board according to an embodiment of the present invention.

FIG. 9 is a schematic outline diagram of a layout diagram of an embodiment of the present invention.

FIG. 10 is a schematic diagram of processing results of fragmentary component filtering processing according to an embodiment of the present invention.

FIG. 11 is a schematic diagram of processing results of repeated element filtering processing according to an embodiment of the present invention.

FIG. 12 is a schematic diagram of processing results of meander element filtering processing according to an embodiment of the present invention.

FIG. 13 is a schematic diagram of an object image according to an embodiment of the present invention.

FIG. 14 is a schematic diagram of another target image according to an embodiment of the present invention.

S10-S11: training steps

S20-S24: grabbing steps

Claims (14)

An automatic identification method for a circuit board grasping position, comprising: a) obtaining a plurality of layout diagrams of a plurality of standard circuit boards of different types, and performing a simplification process on the layout diagrams of each of the standard circuit boards, to obtain a training layout diagram for eliminating identification noise; b) performing a training process on a training model based on each of the training layout diagrams to enable the training model to have the ability to identify different types of the plurality of standard circuit boards, wherein each of the training layout diagrams is set with a grasping position; c) inputting a target image of a target circuit board into the training model to perform a recognition process on the target image; and d) when identifying that the target image matches any of the standard circuit boards, performing a matching process on the target image to determine a capture of the target image based on the capture position of the training layout diagram of the standard circuit board that matches Location; Among them, the identification process includes: e1) performing a target edge analysis on the target image to obtain a plurality of target component edge features of the target image; e2) calculating a similarity score of the target image to each of the standard circuit boards based on the plurality of target component edge features and the plurality of identification features of each of the standard circuit boards; and e3) Determine an identification result based on the standard circuit board with the highest score. The method for automatically identifying the picking position of a circuit board as described in Claim 1, wherein the simplified process includes a step f1) performing a contour extraction process on the layout to identify a plurality of components of the target circuit board in the layout Outline. The automatic identification method of the circuit board grasping position as described in claim 2, wherein the simplified process includes at least one of the following steps: f2) performing a fragment filtering process on the layout to filter out the components from the layout having an area smaller than a fragment threshold; f3) performing a duplicate component filtering process on the layout diagram to identify duplicate components within a search range whose number exceeds a duplicate threshold, and filter out the duplicate components from the layout diagram; and f4) performing a zigzag component filtering process on the layout graph to identify the component with multiple corners, and filter the component from the layout graph. The method for automatically identifying the grab position of the circuit board as described in claim 3, wherein the fragmentation threshold is determined based on the copper foil area of the target circuit board and a first ratio; Wherein, the repeated component filtering process includes expanding a search radius outward from the center of each component as the search range, and the search radius is determined based on a side length of each component and a second ratio; Wherein, the zigzag element filtering process is to filter the element whose number of corner points is larger than a corner point threshold or a corner-to-contour point ratio between the number of corner points and the number of contour points is greater than a third ratio. The method for automatic identification of the grasping position of the circuit board as described in claim 1, wherein the training process includes: g1) performing a training edge analysis on the training layout to obtain training element edge features of the training layout; and g2) Calculating the identification features of the standard circuit board based on the edge features of the training components. The automatic identification method for the grasping position of the circuit board as described in claim 5, wherein the training process further includes: h1) performing the training edge analysis to obtain the positions, gradient directions, and centers of gravity of a plurality of training sampling edge points of the training layout graph as edge features of the plurality of training elements; and h2) Calculate a plurality of training similarity scores based on the plurality of training sample edge points, an edge detection range and an allowable difference range, as the plurality of identification features. The automatic identification method for the grasping position of the circuit board as described in claim 1, wherein the identification process further includes: e4) Locating the components of the target image with the highest similarity score of the standard circuit board. The automatic identification method for the grasping position of the circuit board as described in claim item 7, wherein the identification processing further includes: i1) performing the target edge analysis to obtain a plurality of target sampling edge points of the target image and a gradient direction of each of the target sampling edge points as edge features of the plurality of target components; and i2) Calculate a predicted center of gravity of each target sampling edge point based on the position and gradient direction of each of the target sampling edge points, compare multiple training similarity scores with multiple center of gravity similarity scores corresponding to the multiple predicted centers of gravity, and based on the Center of gravity similarity scores determine the similarity score for the standard circuit board. An automatic identification system for a circuit board grasping position, comprising: An image capture device, used to photograph a target circuit board to obtain a target image; a gripping device for gripping circuit boards; and A control device, connected to the image capture device and the capture device, including: a simplification module configured to perform a simplification process on a layout diagram of a standard circuit board to obtain a training layout diagram by removing identification noise; A training module, which is set to input the training layout to a training model so that the training model has the ability to identify the same type of circuit board, wherein a grasping position is set on the training layout; A recognition module that inputs the target image to the training model to perform recognition, and when recognizing the target image as the standard circuit board, performs a matching process on the target image based on the training layout diagram of the standard circuit board The capture position of determines a capture position of the target image; Wherein, the control device is configured to control the grabbing device to grab the target circuit board based on the grabbing position of the target image. The automatic identification system for the grasping position of the circuit board as described in claim 9, wherein the control device further includes: an outline extraction module configured to identify outlines of components of the target circuit board in the layout; and an odds and ends filter module configured to filter out the components from the layout with an area smaller than an odds and ends threshold, wherein the odds and ends threshold is determined based on a first ratio of copper foil area of the target circuit board . The automatic identification system for the grasping position of the circuit board as described in claim 9, wherein the control device further includes: an outline extraction module configured to identify outlines of components of the target circuit board in the layout; and a duplicate component filtering module configured to identify duplicate components within a search range exceeding a duplicate threshold in the layout, and filter out the duplicate components from the layout; Wherein, the repeated component filtering module is further set to expand a search radius outward from the center of each component as the search range, and the search radius is determined based on a side length of each component and a second ratio. The automatic identification system for the grasping position of the circuit board as described in claim 9, wherein the control device further includes: an outline extraction module configured to identify outlines of components of the target circuit board in the layout; and a zigzag component filtering module configured to identify the component with multiple corners in the layout and filter the component from the layout; Wherein, the zigzag element filtering module is further set to filter the number of corner points greater than a corner point threshold or a corner point-contour point ratio between the number of corner points and the number of contour points is greater than a third ratio of the component. The automatic recognition system of the circuit board picking position as described in claim 9, wherein the training module is further configured to perform a training edge analysis on the training layout to obtain a plurality of training component edge features of the training layout, and calculating a plurality of identification features based on the plurality of edge features of the training elements. The automatic identification system for the grasping position of the circuit board as described in claim 9, wherein the identification module is further configured to perform edge analysis on the target image to obtain multiple target component edge features of the target image, based on the multiple Compute a similarity score of the target image to each of the standard circuit boards based on the edge features of the target component and multiple identification features of each of the standard circuit boards, determine an identification result based on the standard circuit board with the highest score, and use the corresponding similarity score to locate multiple elements of the target image.

Images