WO2023109557A1 - 连接器件检测方法、电子设备及存储介质 - Google Patents

连接器件检测方法、电子设备及存储介质 Download PDF

Info

Publication number
WO2023109557A1
WO2023109557A1 PCT/CN2022/136705 CN2022136705W WO2023109557A1 WO 2023109557 A1 WO2023109557 A1 WO 2023109557A1 CN 2022136705 W CN2022136705 W CN 2022136705W WO 2023109557 A1 WO2023109557 A1 WO 2023109557A1
Authority
WO
WIPO (PCT)
Prior art keywords
pin
image
connecting device
pins
group
Prior art date
Application number
PCT/CN2022/136705
Other languages
English (en)
French (fr)
Inventor
关涛
梅君君
葛成伟
Original Assignee
中兴通讯股份有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 中兴通讯股份有限公司 filed Critical 中兴通讯股份有限公司
Publication of WO2023109557A1 publication Critical patent/WO2023109557A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0004—Industrial image inspection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/044—Recurrent networks, e.g. Hopfield networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G06N3/0455—Auto-encoder networks; Encoder-decoder networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/0475—Generative networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/11—Region-based segmentation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20084—Artificial neural networks [ANN]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20112—Image segmentation details
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30108—Industrial image inspection
    • G06T2207/30164—Workpiece; Machine component

Definitions

  • the embodiments of the present application relate to the communication field, and in particular to a method for detecting a connecting device, an electronic device, and a storage medium.
  • the electronics industry needs various connecting devices, and connecting devices are needed to form a whole between various electronic devices.
  • the connecting device may have defects during the production process or assembly process, causing the electronic product to not work properly. Some defects may cause damage to the connecting device during the assembly process of the product, resulting in irreparable damage. Defective connecting devices may also affect other devices during production and operation, resulting in product damage and loss. Therefore, it is necessary to inspect the connecting devices in multiple links of the production process, and pick out defective connecting devices for maintenance or discarding.
  • the inspection of connecting devices is mainly carried out manually.
  • multiple pin groups on the connecting device there are multiple pin groups on the connecting device, and multiple pin groups contain multiple pins. These pins are arranged densely, and manual inspection is easy to miss, and the speed of manual inspection is low, and the inspection standards are not uniform, so it is not suitable for A large number of electronic product production processes.
  • connection device detection method for example, to provide a connection device detection method, electronic equipment and storage medium, which can automatically and efficiently detect defects of the connection device.
  • an embodiment of the present application provides a method for detecting a connecting device, the connecting device includes a plurality of pin groups, and the pin group includes a plurality of pins, the method includes: according to the preset connection The pin information of the device is detected on the image of the connected device to be tested, and the position of the pin and the position of the pin group are obtained; the expected position of the pin is determined according to the pre-acquired image rotation angle, the pin information and the position of the pin group ; performing defect detection on the connecting device according to the pin information, the pin position, and the expected position of the pin.
  • an embodiment of the present application also provides an electronic device, including: at least one processor; and a memory connected to the at least one processor in communication; wherein, the memory stores information that can be used by the at least one processor Instructions executed by a processor, the instructions are executed by the at least one processor, so that the at least one processor can execute the connection device detection method described in the above embodiments.
  • the embodiment of the present application also proposes a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the method for detecting a connecting device described in the above embodiment is implemented.
  • a connection device detection method, electronic equipment and storage medium proposed in the present application process the image of the connection device according to the preset plug-in information, and can automatically calculate and obtain the position of the pin and the position of the pin group for various types of pins. Then, the expected position of each pin is determined according to the pre-acquired connection device angle, pin information and pin group position, taking into account the problem of the image shooting angle of the connection device, and by obtaining the rotation angle of the connection device, the scope of application of this method can be made wider Finally, the defect detection of the connected device can be completed according to the pin information, pin position and expected position of the pin. The whole method has low environmental requirements, wide application range and high detection efficiency.
  • Fig. 1 is a flow chart 1 of a connecting device detection method provided by an embodiment of the present application
  • Fig. 2a is a schematic diagram of a single pin structure of a connecting device provided by an embodiment of the present application
  • Fig. 2b is a schematic diagram of the composite pin structure of the connecting device provided by the embodiment of the present application.
  • FIG. 3 is the second flow chart of the connecting device detection method provided by the embodiment of the present application.
  • Fig. 4 is a flow chart three of the connection device detection method provided by the embodiment of the present application.
  • FIG. 5 is a schematic structural diagram of an electronic device provided in an embodiment of the present application.
  • connection device detection method as shown in Figure 1, including:
  • Step 101 Detect the image of the connection device to be tested according to the preset pin information of the connection device, and obtain the position of the pin and the position of the group of pins.
  • the preset pin information of the connecting device can be obtained from the image of the connecting device to be tested, or can be obtained from the information provided by the manufacturer of the connecting device.
  • the preset pin information of the connecting device includes pin size, pin type, pin group type, pin shape, pin group size, and the like.
  • Pin types include single type, compound type, etc.
  • pin group type refers to the arrangement of pins
  • pin shapes include round pins, flat pins, etc.
  • Figure 2a is a single-type pin
  • Figure 2b is a composite pin
  • the pin type is single type
  • the pin group type is horizontal 6 vertical 9
  • the pin shape is flat
  • the pin size is the length and width of each flat pin
  • the pin group size is the length and width of a pin group consisting of 54 pins.
  • the pin type is compound type
  • the pin group type is 6 horizontal and 4 vertical. It should be noted that when the pin type is compound type, the pins include a border (the concave part in Figure 2b) and the middle pin (two dots in the frame), the shape of the pin refers to the shape of the middle pin.
  • the shape of the middle pin is a round pin
  • the size of the pin includes the entire pin composed of the frame and the middle pin.
  • the size of the needle, the size of the frame and the size of the middle needle, and the size of the pin group is the length and width of the pin group composed of 24 pins.
  • the pin information is not limited to the above information, and the specific content of each piece of information can be adjusted according to the specific pin type and configuration.
  • Step 102 determine the expected position of the pin according to the pre-acquired image rotation angle, pin information and pin group position.
  • connection device may not be completely aligned with the shooting device, and there may be a certain rotation angle, resulting in the obtained connection device
  • the position of the connected device in the device image is skewed, which affects the accuracy of the subsequent defect detection results. Therefore, the image rotation angle needs to be determined in advance. According to the image rotation angle, pin information and pin position, the expected position of the pin can be determined.
  • the expected position can be understood as the correct position that the pin should exist according to the production design standard, such as: determining the pin type of a certain connecting device It is a single type, the pin group type is 6 horizontal and 4 vertical, the pins are round pins, the size of the pins is 2 diameters of the round pins, and the size of the pin group is 10 long and 6 wide. According to the production design standard of the connecting device, In a pin group with a length of 10 and a width of 6, 24 circular pins need to be designed, and each pin is evenly arranged, then the expected position of each pin can be calculated.
  • the production design standard of the connecting device In a pin group with a length of 10 and a width of 6, 24 circular pins need to be designed, and each pin is evenly arranged, then the expected position of each pin can be calculated.
  • the expected position of the pin can be the coordinates of the center point of the pin, or the location area of the pin, and can also include both the coordinates of the center point of the pin and the location area of the pin.
  • the expected position of the pin can be the location area of the flat pin (the area formed by the length and width of the flat pin), and the expected position of the pin can also be the center point coordinates of the flat pin.
  • Step 103 perform defect detection on the connecting device according to the pin information, the pin position, and the expected position of the pin.
  • the defect detection of the connection device includes quantity detection and position detection, that is, whether the connection device lacks pins and whether the pin positions are correct.
  • a connection device detection method proposed in this application processes the image of the connection device according to the preset plug-in information, and can automatically calculate and obtain the position of the pin and the position of the pin group for various types of pins, and then according to the pre-acquired connection
  • the expected position of each pin is determined by the device angle, pin information and pin group position, taking into account the problem of the image shooting angle of the connected device, by obtaining the image rotation angle, this method can make the scope of application wider, and finally according to the pin information , the position of the pin and the expected position of the pin can complete the defect detection of the connected device.
  • the whole method has low environmental requirements, wide application range and high detection efficiency.
  • connection device detection method as shown in Figure 3, including:
  • Step 301 Detect the image of the connecting device to be tested based on a preset target detection algorithm, and obtain an initial pin group position and an initial pin position.
  • the preset target detection algorithm may include one of the following or any combination thereof: sliding window detector, R-CNN, Fast R-CNN, R-FCN, RetianNet, Cascade RCNN.
  • sliding window detector R-CNN
  • Fast R-CNN R-FCN
  • RetianNet RetianNet
  • Cascade RCNN RCNN
  • Step 302 based on a preset image segmentation algorithm, the image of the area where the pins are located in the image of the connected device to be tested is processed to extract a pin image mask.
  • the image of the area where the pin is located is further analyzed and processed according to a preset image segmentation algorithm, and the pin image mask is extracted.
  • the preset image segmentation algorithm can be either a deep learning-based semantic segmentation algorithm or an instance-based image segmentation algorithm. Specifically, such as: fully convolutional pixel labeling networks, encoder-decoder architectures, multi-scale and pyramid-based methods, recurrent networks, visual attention models, and generative confrontation models.
  • this application adopts various image processing algorithms to detect and identify the insertion pins, so that the detection method of this application has strong adaptability to changes in illumination, and is adaptable to changes in the shooting effect of materials caused by stains on parts and small foreign objects powerful.
  • Step 303 correcting the initial pin position according to the pin information of the connected device and the pin image mask to determine the pin position.
  • the image of the pin position at the pixel level is further accurately determined through the pin image mask, so that the initial pin position can be corrected through the pixel coordinates of the pin mask image, and an accurate pin position can be obtained. Location. After the precise position of all pins is determined, the precise position of the entire pin group can be quickly determined based on this.
  • Step 304 correct the initial pin group position according to the pin position, and determine the pin group position.
  • Step 305 determine the expected position of the pin according to the pre-acquired image rotation angle, pin information and pin group position.
  • step 305 before step 305, it also includes: determining the apex position of the pin group from the position of the pin group, and determining the image rotation angle through the apex position; or, based on preset image detection
  • the algorithm determines a plurality of calibration points of the connected device image, and calculates the image rotation angle according to the plurality of calibration points.
  • the image rotation angle can be calculated according to the vertex position of the pin group, or the image rotation angle can be calculated according to the calibration point, and the two methods can also be combined, that is, the rotation angle of the connected device calculated by the two methods is averaged Get more accurate values to improve the accuracy of subsequent defect detection.
  • the image detection algorithm may include a target detection algorithm, an edge detection algorithm, an image filtering algorithm, an image segmentation algorithm, an image detection algorithm based on Hough transform, etc., and these algorithms are used in combination to obtain calibration points.
  • a rough calibration point position can be obtained first, and further corrections can be made to obtain an accurate calibration point position.
  • determining the vertex position of the pin group from the position of the pin group, and determining the image rotation angle through the vertex position includes: when the size of the pin group is greater than or equal to a preset threshold, according to the pin group The position determines the multiple vertex positions of the pin group; the coordinate difference of each vertex is calculated through the vertex position, and the horizontal edge rotation angle and the vertical edge rotation angle of the pin group are determined according to the coordinate difference; the horizontal edge rotation angle and the vertical edge rotation angle are used as an initial rotation angle, and average the acquired initial rotation angles of multiple pin groups to determine the image rotation angle.
  • the positions of the vertices of the four vertices of the pin group can be determined, two vertices in the longitudinal direction of the pin group are selected, and the coordinates of the two vertices are compared, and the difference can be calculated according to the difference Vertical rotation angle.
  • two vertices in the horizontal direction of the pin group are selected, the coordinates of the two vertices are made a difference, and the lateral rotation angle can be calculated according to the difference.
  • the lateral rotation angle and the vertical rotation angle are used as the initial rotation angles of the connected device in the image to be tested.
  • the smaller pin group is excluded in advance, and only the larger pin group is calculated to improve the calculation. Accuracy.
  • each pin group can calculate a rotation angle, and the average value of multiple rotation angles is calculated as the final connecting device rotation angle.
  • Step 306 perform defect detection on the connecting device according to the pin information, the pin position, and the expected position of the pin.
  • a connection device detection method proposed in this application processes the image of the connection device according to the preset plug-in information, and can automatically calculate and obtain the position of the pin and the position of the pin group for various types of pins, and then according to the pre-acquired connection
  • the expected position of each pin is determined by the angle of the device, the information of the pins and the position of the pin group. Taking into account the problem of the image shooting angle of the connected device, the method can be applied to a wider range by obtaining the rotation angle of the connected device.
  • pin Information pin position and expected position of the pins are enough to complete the defect detection of connected devices. The whole method has low environmental requirements, wide application range and high detection efficiency.
  • accurate positioning can be achieved, and the situation of false detection can be reduced.
  • connection device detection method as shown in Figure 4, including:
  • Step 401 Detect the image of the connection device to be tested according to the preset pin information of the connection device, and obtain the position of the pin and the position of the group of pins.
  • Step 402 determine the expected position of the pin according to the pre-acquired image rotation angle, pin information and pin group position.
  • step 401 and step 402 are basically the same as the specific implementation details of step 301-step 305, and will not be repeated here.
  • Step 403 when the type of the pin is single, determine whether there is a missing pin and/or a crooked pin in the connecting device according to the position of the pin and the expected position of the pin.
  • Step 404 when the pin type is a compound type, decompose the image of the connected device to be tested, obtain the component position of the component in the pin, and determine the expected position of the component according to the pin information, the image rotation angle and the position of the pin group , to perform defect detection on connection devices by pin position, expected position of pin, component position and expected position of component.
  • the defect detection is performed on the connecting device through the position of the pin, the expected position of the pin, the position of the component, and the expected position of the component, including: determining whether there is a missing pin in the connecting device according to the position of the pin and the expected position of the pin situation and/or crooked pin situation; determine whether there is a missing frame and/or skewed frame of the connecting device according to the position of the frame and the expected position of the frame; determine whether there is a middle pin in the connecting device according to the position of the middle pin and the expected position of the middle pin Missing case and/or center needle skew case.
  • the pin information also includes: component information, the components in the pin include the frame and the middle pin, the position of the component includes the position of the frame and the position of the middle pin, and the expected position of the component includes: the expected position of the frame and the middle pin Needle expected position. If it is determined that the pin is of a single type according to the preset pin information, then it can be determined whether there is a missing pin and/or a crooked pin in the connecting device according to the pin position and the expected position of the pin. It should be noted that the expected position of the pin may include the coordinates of the center point of the pin and the location area of the pin. It is determined whether there is a pin in the connecting device at this position through the location area of the pin, and it is determined by the coordinates of the center point of the pin. Whether the pin is skewed.
  • the compound pin when it is determined that the pin type is a compound type, the compound pin also includes other components, such as a frame, a middle pin, and the like. It is necessary to further analyze the components in the pins, that is, to segment the image of the area where the pins are located in the image, to obtain the component positions of the components in the pins, such as: frame position and middle pin position, and then according to the pins containing component information
  • the pin information, image rotation angle, and pin group position determine the expected position of the part, namely the frame expected position and the middle pin expected position.
  • the pin information includes frame size, middle pin shape, and middle pin size.
  • segmenting the image of the area where the pins are located in the image of the connected device to be tested specifically includes: segmenting the image of the area where the pins are located according to the component information and a preset image segmentation algorithm, and obtaining The component area of each component; the component area of each component is detected based on the preset target detection algorithm, and the position of the component is determined. For example: once it is determined that the pin type is a compound type, the component information in the pin information is obtained, and the component information includes component shape, component size, and component orientation.
  • the shape of the part may include the frame style and the shape of the middle pin
  • the size of the part may include the size of the frame and the size of the middle pin
  • the orientation of the part may include: the frame is below the pin area, and the middle pin is located in the middle of the pin area.
  • the method for obtaining the expected position of the component is similar to the method for obtaining the expected position of the pin, which will not be repeated here.
  • multiple image processing algorithms can be used in combination, such as: target detection algorithm, edge detection algorithm, image filtering algorithm, etc. In order to improve the image processing precision.
  • a connection device detection method proposed in this application processes the image of the connection device according to the preset plug-in information, and can automatically calculate and obtain the position of the pin and the position of the pin group for various types of pins, and then according to the pre-acquired connection
  • the expected position of each pin is determined by the angle of the device, the information of the pins and the position of the pin group. Taking into account the problem of the image shooting angle of the connected device, the method can be applied to a wider range by obtaining the rotation angle of the connected device.
  • pin Information pin position and expected position of the pins are enough to complete the defect detection of connected devices. The whole method has low environmental requirements, wide application range and high detection efficiency.
  • the application automatically further decomposes the pins according to the type of the pins, and determines the position of the components and the expected position of the components, which can be adapted to different batches of products and has good practicability.
  • connection device detection device including:
  • the information acquisition module is used to detect the image of the connected device to be tested according to the preset pin information of the connected device, obtain the position of the pin and the position of the pin group, and obtain the position according to the pre-acquired image rotation angle, the pin information and the Determine the expected position of the pins based on the position of the pin group described above;
  • a defect detection module configured to perform defect detection on the connecting device according to the pin information, the position of the pin, and the expected position of the pin.
  • modules involved in this embodiment are logical modules, and a logical unit may be a physical unit, or a part of a physical unit, or may be realized by a combination of multiple physical units.
  • a logical unit may be a physical unit, or a part of a physical unit, or may be realized by a combination of multiple physical units.
  • units that are not closely related to solving the technical problem proposed by the present invention are not introduced in this embodiment, but this does not mean that there are no other units in this embodiment.
  • this embodiment is an apparatus embodiment corresponding to the embodiment of the method for detecting a connecting device, and this embodiment can be implemented in cooperation with the above-mentioned embodiments.
  • the relevant technical details mentioned in the foregoing embodiments are still valid in this embodiment, and will not be repeated here in order to reduce repetition.
  • the relevant technical details mentioned in this embodiment can also be applied to the above method embodiments.
  • An embodiment of the present invention relates to an electronic device, as shown in FIG. 5 , including: at least one processor 501; and a memory 502 communicatively connected to the at least one processor 501; Instructions executed by the at least one processor 501, the instructions are executed by the at least one processor 501, so that the at least one processor 501 can execute the connection device detection method of the above-mentioned embodiment.
  • the memory and the processor are connected by a bus
  • the bus may include any number of interconnected buses and bridges, and the bus connects one or more processors and various circuits of the memory together.
  • the bus may also connect together various other circuits such as peripherals, voltage regulators, and power management circuits, all of which are well known in the art and therefore will not be further described herein.
  • the bus interface provides an interface between the bus and the transceivers.
  • a transceiver may be a single element or multiple elements, such as multiple receivers and transmitters, providing means for communicating with various other devices over a transmission medium.
  • the data processed by the processor is transmitted on the wireless medium through the antenna, further, the antenna also receives the data and transmits the data to the processor.
  • the processor is responsible for managing the bus and general processing, and can also provide various functions, including timing, peripheral interface, voltage regulation, power management, and other control functions. Instead, memory can be used to store data that the processor uses when performing operations.
  • Embodiments of the present invention relate to a computer-readable storage medium storing a computer program.
  • the computer program is executed by the processor, the above connection device detection method is realized.
  • a storage medium includes several instructions to make a device ( It may be a single-chip microcomputer, a chip, etc.) or a processor (processor) to execute all or part of the steps of the methods described in the various embodiments of the present application.
  • the aforementioned storage media include: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disk or optical disc, etc., which can store program codes. .

Abstract

本申请提出一种连接器件检测方法、电子设备和存储介质。本申请的连接器件包含多个插针组，所述插针组包含多个插针，所述方法包括：根据预设的连接器件的插针信息对待测的连接器件图像进行检测，获取插针位置和插针组位置；根据预先获取的图像旋转角度、所述插针信息和所述插针组位置确定插针的预期位置；根据所述插针信息、所述插针位置、所述插针的预期位置对所述连接器件进行缺陷检测。

Description

连接器件检测方法、电子设备及存储介质
相关申请
本申请要求于2021年12月14日申请的、申请号为202111531962.6的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请实施例涉及通信领域，特别涉及一种连接器件检测方法、电子设备及存储介质。
背景技术
电子行业需要各种连接器件，各个电子器件之间需要用连接器件组成一个整体。但是连接器件在生产过程或组装过程中可能出现缺陷，导致电子产品无法正常工作。有些缺陷则可能造成产品的组装过程中连接器件损坏，导致无法修复。有缺陷的连接器件也可能在生产、运行过程中对其它器件造成影响，导致产品损毁，造成损失。因此需要在生产过程的多个环节对连接器件进行检查，将有缺陷的连接器件挑选出来，进行维修或者丢弃。
目前主要通过人工方式对连接器件进行检查。但是连接器件上包含多个插针组，多个插针组包含多个插针，这些插针排列比较密集，人工检查容易漏检，且人工检查速度较低，检查标准不统一，不适用于大量的电子产品生产过程。
发明内容
本申请实施例的主要目的在于提出一种连接器件检测方法、电子设备及存储介质，能自动、高效率地对连接器件的缺陷进行检测。
为实现上述目的，本申请实施例提供了一种连接器件检测方法，所述连接器件包含多个插针组，所述插针组包含多个插针，所述方法包括：根据预设的连接器件的插针信息对待测的连接器件图像进行检测，获取插针位置和插针组位置；根据预先获取的图像旋转角度、所述插针信息和所述插针组位置确定插针的预期位置；根据所述插针信息、所述插针位置、所述插针的预期位置对所述连接器件进行缺陷检测。
为实现上述目的，本申请实施例还提出了一种电子设备，包括：至少一个处理器；以及，与所述至少一个处理器通信连接的存储器；其中，所述存储器存储有可被所述至少一个处理器执行的指令，所述指令被所述至少一个处理器执行，以使所述至少一个处理器能够执行以上实施例所述的连接器件检测方法。
为实现上述目的，本申请实施例还提出了一种计算机可读存储介质，存储有计算机程序，所述计算机程序被处理器执行时实现以上实施例所述的连接器件检测方法。
本申请提出的一种连接器件检测方法、电子设备及存储介质，根据预设的插件信息对连接器件图像进行处理，可针对多种类型的插针自动计算获取插针位置和插针组位置，然后根据预先获取的连接器件角度、插针信息和插针组位置确定每个插针的预期位置，考虑到了连接器件图像拍摄角度的问题，通过获取连接器件旋转角度，可使得本方法适用范围更广，最后根据插针信息、插针位置和插针的预期位置即可完成连接器件的缺陷检测。整个方法对环 境要求低，适用范围广，检测效率高。
附图说明
一个或多个实施例通过与之对应的附图中的图片进行示例性说明，这些示例性说明并不构成对实施例的限定。
图1是本申请的实施例提供的连接器件检测方法的流程图一；
图2a是本申请的实施例提供的连接器件的单一型插针结构示意图；
图2b是本申请的实施例提供的连接器件的复合型插针结构示意图；
图3是本申请的实施例提供的连接器件检测方法的流程图二；
图4是本申请的实施例提供的连接器件检测方法的流程图三；
图5是本申请的实施方式提供的电子设备的结构示意图。
具体实施方式
为使本申请实施例的目的、技术方案和优点更加清楚，下面将结合附图对本申请的各实施例进行详细的阐述。然而，本领域的普通技术人员可以理解，在本申请各实施例中，为了使读者更好地理解本申请而提出了许多技术细节。但是，即使没有这些技术细节和基于以下各实施例的种种变化和修改，也可以实现本申请所要求保护的技术方案。以下各个实施例的划分是为了描述方便，不应对本申请的具体实现方式构成任何限定，各个实施例在不矛盾的前提下可以相互结合相互引用。
本申请的实施例涉及一种连接器件检测方法，如图1所示，包括：
步骤101，根据预设的连接器件的插针信息对待测的连接器件图像进行检测，获取插针位置和插针组位置。
在本实施例中，预设的连接器件的插针信息可以从待测的连接器件图像中获取，也可以从连接器件生产厂家提供的信息中获取。
在一实施例中，预设的连接器件的插针信息包含插针尺寸、插针类型、插针组类型、插针形态、插针组尺寸等。插针类型包含单一型、复合型等，插针组类型指的是插针的排列方式，插针形态包含圆针、扁针等。
如图2所示，图2a为单一型插针，图2b为复合型插针，以图2a为例，插针类型为单一型，插针组类型为横6竖9，插针形态为扁针，插针尺寸为每个扁针的长和宽，插针组尺寸为54个插针构成的插针组的长和宽。以图2b为例，插针类型为复合型，插针组类型为横6竖4，需要注意的是，当插针类型为复合型时，插针包含边框(图2b中凹字型部分)和中间针(边框中两个圆点)这两个部件，插针形态指的是中间针的形态，此时中间针的形态为圆针，插针尺寸包含由边框和中间针构成的整个插针的尺寸、边框的尺寸和中间针的尺寸，插针组尺寸为24个插针构成的插针组的长和宽。当然，此处仅为具体的举例说明，插针信息不仅限于上述信息，每个信息的具体内容可以根据具体的插针类型和构成进行调整。
步骤102，根据预先获取的图像旋转角度、插针信息和插针组位置确定插针的预期位置。
在本实施例中，本领域技术人员可以理解的是，获取的待测的连接器件图像在拍摄过程中，连接器件并不一定与拍摄设备完全对齐，可能存在一定的旋转角度，导致获取的连接器件图像中连接器件的位置存在歪斜，影响后续缺陷检测结果的准确性。因此需要预先确定图 像旋转角度。根据图像旋转角度、插针信息和插针位置就可以确定插针的预期位置，该预期位置可以理解为按照生产设计标准插针应该存在的正确位置，比如：确定某一连接器件的插针类型为单一型，插针组类型为横6竖4，插针为圆针，插针尺寸为圆针的直径2，插针组的尺寸为长10宽6，按照该连接器件的生产设计标准，在长10宽6的插针组内需要设计24个圆形插针，每个插针之间均匀排列，那么即可计算出每个插针的预期位置。
需要说明的是，插针的预期位置可以是插针的中心点坐标，也可以是插针的位置区域，还可以同时包含插针中心点坐标和插针位置区域两个信息。比如：当插针为扁针时，插针的预期位置可以是扁针的位置区域(由扁针长和宽所构成的区域)，插针的预期位置也可以是扁针的中心点坐标。
步骤103，根据插针信息、插针位置、插针的预期位置对连接器件进行缺陷检测。
本实施例中，对连接器件进行缺陷检测包含数量的检测和位置的检测，即连接器件是否缺少插针，插针位置是否正确。
本申请提出的一种连接器件检测方法，根据预设的插件信息对连接器件图像进行处理，可针对多种类型的插针自动计算获取插针位置和插针组位置，然后根据预先获取的连接器件角度、插针信息和插针组位置确定每个插针的预期位置，考虑到了连接器件图像拍摄角度的问题，通过获取图像旋转角度，可使得本方法适用范围更广，最后根据插针信息、插针位置和插针的预期位置即可完成连接器件的缺陷检测。整个方法对环境要求低，适用范围广，检测效率高。
本申请的实施例涉及一种连接器件检测方法，如图3所示，包括：
步骤301，基于预设的目标检测算法对所述待测的连接器件图像进行检测，获取初始插针组位置和初始插针位置。
本实施例中，预设的目标检测算法可以包含以下之一或其任意组合：滑动窗口检测器、R-CNN、Fast R-CNN、R-FCN、RetianNet、Cascade RCNN。当然，本领域技术人员可以理解的是，在对待测的连接器件图像进行检测前，可以对图像进行滤波处理或其他处理，以提高检测准确度。
步骤302，基于预设的图像分割算法对待测的连接器件图像中插针所在区域的图像进行处理，提取插针图像掩码。
本实施例中，在获取到初始插针位置后，根据预设的图像分割算法对插针所在区域的图像进一步分析处理，提取出插针图像掩码。预设的图像分割算法可以是基于深度学习的语义分割算法，也可以是基于实例的图像分割算法。具体地，比如：完全卷积像素标记网络、编码器-解码器架构、多尺度和基于金字塔的方法、递归网络，视觉attention模型，以及生成对抗模型等。
需要说明的是，本申请采用各种图像处理算法对插针进行检测识别，使得本申请的检测方法对光照变化的适应性强，对部件上污渍、小型异物引起的物料拍摄效果的变化适应性强。
步骤303，根据连接器件的插针信息和插针图像掩码对所述初始插针位置进行修正，确定插针位置。
本实施例中，通过插针图像掩码进一步精确确定出像素级别的插针位置的图像，由此可以通过插针掩码图像的像素坐标可对初始插针位置进行修正，得到精确的插针位置。在确定出所有插针的精确位置后，即可基于此快速确定出整个插针组的精确位置。
步骤304，根据插针位置对初始插针组位置进行修正，确定插针组位置。
步骤305，根据预先获取的图像旋转角度、插针信息和插针组位置确定插针的预期位置。
在一实施例中，在步骤305之前还包括：从所述插针组位置中确定插针组的顶点位置，并通过所述顶点位置确定所述图像旋转角度；或者，基于预设的图像检测算法确定所述连接器件图像的多个校准点，根据所述多个校准点计算所述图像旋转角度。
需要说明的是，可以根据插针组的顶点位置计算图像旋转角度，也可以根据校准点计算图像旋转角度，还可以将两个方法结合起来，即将两个方法计算得到的连接器件旋转角度进行平均得到更为精确的数值，以提高后续缺陷检测的准确性。
另外，本实施例中，图像检测算法可以包括目标检测算法、边缘检测算法，图像滤波算法、图像分割算法、基于Hough变换的图像检测算法等，将这些算法结合使用获取校准点。在这个过程中，可以先获取粗略的校准点位置，在进一步进行修正，获取精确的校准点位置。
在一实施例中，从插针组位置中确定插针组的顶点位置，并通过顶点位置确定图像旋转角度，包括：当插针组尺寸大于或等于于预设的阈值时，根据插针组位置确定插针组的多个顶点位置；通过顶点位置计算各顶点的坐标差，根据坐标差确定插针组的横向边缘旋转角度和纵向边缘旋转角度；将横向边缘旋转角度和纵向边缘旋转角度作为初始旋转角度，并对获取到的多个插针组的初始旋转角度进行平均，确定图像旋转角度。
具体地说，确定插针组的位置后即可确定出插针组四个顶点的顶点位置，选取插针组纵向的两个顶点，将两个顶点坐标作差，根据差值就可计算出纵向旋转角度。类似地，选取插针组横向的两个顶点，将两个顶点坐标作差，根据差值就可计算出横向旋转角度。将横向旋转角度和纵向旋转角度作为待测图像中连接器件的初始旋转角度。此外，当插针组尺寸较小时，计算图像旋转角度时，很容易出现较大误差，因此，事先排除掉尺寸较小的插针组，只针对尺寸较大的插针组进行计算，提高计算准确度。
需要说明的是，由于连接器件中包含多个插针组，因此，每个插针组都可以计算出一个旋转角度，计算多个旋转角度的平均值作为最终的连接器件旋转角度。当然，也可以对多个旋转角度值进行分析，确定其方差、中位数、标准差等值，根据分析结果从中选出一个合适的旋转角度作为最终的结果。
步骤306，根据插针信息、插针位置、插针的预期位置对连接器件进行缺陷检测。
本申请提出的一种连接器件检测方法，根据预设的插件信息对连接器件图像进行处理，可针对多种类型的插针自动计算获取插针位置和插针组位置，然后根据预先获取的连接器件角度、插针信息和插针组位置确定每个插针的预期位置，考虑到了连接器件图像拍摄角度的问题，通过获取连接器件旋转角度，可使得本方法适用范围更广，最后根据插针信息、插针位置和插针的预期位置即可完成连接器件的缺陷检测。整个方法对环境要求低，适用范围广，检测效率高。另外，本申请通过对插针位置和插针组位置的两阶段定位，可精确定位，减少误检的情况。
本申请的实施例涉及一种连接器件检测方法，如图4所示，包括：
步骤401，根据预设的连接器件的插针信息对待测的连接器件图像进行检测，获取插针位置和插针组位置。
步骤402，根据预先获取的图像旋转角度、插针信息和插针组位置确定插针的预期位置。
本实施例中，步骤401、步骤402的具体实施细节与步骤301-步骤305的具体实施细节 基本相同，在此不作赘述。
步骤403，当插针类型为单一型时，根据插针位置和插针的预期位置确定所述连接器件是否存在缺针情况和/或歪针情况。
步骤404，当插针类型为复合型时，对待测的连接器件图像进行分解，获取插针中的部件的部件位置，并根据插针信息、图像旋转角度和插针组位置确定部件的预期位置，通过插针位置、插针的预期位置、部件位置和部件的预期位置对连接器件进行缺陷检测。
在一实施例中，通过插针位置、插针的预期位置、部件位置和部件的预期位置对连接器件进行缺陷检测，包括：根据插针位置和插针的预期位置确定连接器件是否存在缺针情况和/或歪针情况；根据边框位置和边框的预期位置确定连接器件是否存在边框缺少情况和/或边框歪斜情况；根据中间针位置和所述中间针的预期位置确定连接器件是否存在中间针缺少情况和/或中间针歪斜情况。
本实施例中，插针信息还包括：部件信息，插针中的部件包含边框和中间针，所述部件位置包含边框位置和中间针位置，所述部件的预期位置包括：边框预期位置和中间针预期位置。根据预设的插针信息确定插针为单一型，则根据插针位置和插针预期位置即可确定该连接器件是否存在缺针情况和/歪针情况。需要说明的是，插针的预期位置可以包含插针的中心点坐标和插针的位置区域，通过插针的位置区域判断连接器件在该位置是否存在插针，通过插针的中心点坐标确定插针是否歪斜。
本实施例中，当确定插针类型为复合型时，由于复合型插针还包含其他部件，比如：边框、中间针等。需要进一步对插针中的部件进行分析，即对图像中插针所在区域的图像进行分割，获取插针中的部件的部件位置，比如：边框位置和中间针位置，然后根据包含部件信息的插针信息、图像旋转角度和插针组位置确定部件的预期位置，即边框预期位置和中间针预期位置。当然，插针信息包含边框尺寸，中间针形态、中间针尺寸。
在一实施例中，对待测的连接器件图像中插针所在区域的图像进行分割，具体包括：根据所述部件信息和预设的图像分割算法对所述插针所在区域的图像进行分割，获取各部件的部件区域；基于预设的目标检测算法对各部件的部件区域进行检测，确定部件位置。比如：一旦确定插针类型为复合型时，则获取插针信息中的部件信息，部件信息包括部件形态、部件尺寸、部件方位。具体地，部件形态可以包括边框样式、中间针的形态，部件尺寸可以包括边框尺寸、中间针尺寸，部件方位可以包括：边框在插针区域的下方，中间针位于插针区域的中部。根据部件信息可以对插针区域的图像进一步分割，确定各部件的部件区域，对各部件区域根据目标检测算法获取各部件的精确位置。
另外，部件预期位置的获取方法与插针预期位置的获取方法类似，在此不做赘述。
需要说明的是，对连接器件图像中插针所在区域的图像进行分割获取部件位置的过程中，可以将多个图像处理算法结合使用，比如：目标检测算法、边缘检测算法、图像滤波算法等，以提高图像处理精度。
本申请提出的一种连接器件检测方法，根据预设的插件信息对连接器件图像进行处理，可针对多种类型的插针自动计算获取插针位置和插针组位置，然后根据预先获取的连接器件角度、插针信息和插针组位置确定每个插针的预期位置，考虑到了连接器件图像拍摄角度的问题，通过获取连接器件旋转角度，可使得本方法适用范围更广，最后根据插针信息、插针位置和插针的预期位置即可完成连接器件的缺陷检测。整个方法对环境要求低，适用范围广， 检测效率高。另外，本申请按照插针类型自动对插针进一步分解，确定其中的部件位置和部件的预期位置，可适应不同批次的产品，具有很好的实用性。
此外，应当理解的是，上面各种方法的步骤划分，只是为了描述清楚，实现时可以合并为一个步骤或者对某些步骤进行拆分，分解为多个步骤，只要包括相同的逻辑关系，都在本专利的保护范围内；对流程中添加无关紧要的修改或者引入无关紧要的设计，但不改变其流程的核心设计都在该专利的保护范围内。
本申请的实施例涉及一种连接器件检测装置，包括：
信息获取模块，用于根据预设的连接器件的插针信息对待测的连接器件图像进行检测，获取插针位置和插针组位置，根据预先获取的图像旋转角度、所述插针信息和所述插针组位置确定插针的预期位置；
缺陷检测模块，用于根据所述插针信息、所述插针位置、所述插针的预期位置对所述连接器件进行缺陷检测。
值得一提的是，本实施例中所涉及到的各模块均为逻辑模块，一个逻辑单元可以是一个物理单元，也可以是一个物理单元的一部分，还可以以多个物理单元的组合实现。此外，为了突出本发明的创新部分，本实施例中并没有将与解决本发明所提出的技术问题关系不太密切的单元引入，但这并不表明本实施例中不存在其它的单元。
不难发现，本实施例为与连接器件检测方法实施例相对应的装置实施例，本实施例可与上述实施例互相配合实施。上述实施例中提到的相关技术细节在本实施例中依然有效，为了减少重复，这里不再赘述。相应地，本实施例中提到的相关技术细节也可应用在上述方法实施例中。
本发明的实施方式涉及一种电子设备，如图5所示，包括：至少一个处理器501；以及，与所述至少一个处理器501通信连接的存储器502；其中，所述存储器502存储有可被所述至少一个处理器501执行的指令，所述指令被所述至少一个处理器501执行，以使所述至少一个处理器501能够执行上述实施方式的连接器件检测方法。
其中，存储器和处理器采用总线方式连接，总线可以包括任意数量的互联的总线和桥，总线将一个或多个处理器和存储器的各种电路连接在一起。总线还可以将诸如外围设备、稳压器和功率管理电路等之类的各种其他电路连接在一起，这些都是本领域所公知的，因此，本文不再对其进行进一步描述。总线接口在总线和收发机之间提供接口。收发机可以是一个元件，也可以是多个元件，比如多个接收器和发送器，提供用于在传输介质上与各种其他装置通信的单元。经处理器处理的数据通过天线在无线介质上进行传输，进一步，天线还接收数据并将数据传送给处理器。
处理器负责管理总线和通常的处理，还可以提供各种功能，包括定时，外围接口，电压调节、电源管理以及其他控制功能。而存储器可以被用于存储处理器在执行操作时所使用的数据。
本发明的实施方式涉及一种计算机可读存储介质，存储有计算机程序。计算机程序被处理器执行时实现上述连接器件检测方法。
即，本领域技术人员可以理解，实现上述实施方式方法中的全部或部分步骤是可以通过程序来指令相关的硬件来完成，该程序存储在一个存储介质中，包括若干指令用以使得一个设备(可以是单片机，芯片等)或处理器(processor)执行本申请各个实施方式所述方法的 全部或部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器(ROM，Read-Only Memory)、随机存取存储器(RAM，Random Access Memory)、磁碟或者光盘等各种可以存储程序代码的介质。
本领域的普通技术人员可以理解，上述各实施例是实现本申请的具体实施例，而在实际应用中，可以在形式上和细节上对其作各种改变，而不偏离本申请的精神和范围。

Claims (10)

  1. 一种连接器件检测方法，其中，所述连接器件包含插针组，所述插针组包含多个插针，所述方法包括：
    根据预设的连接器件的插针信息对待测的连接器件图像进行检测，获取插针位置和插针组位置；
    根据预先获取的图像旋转角度、所述插针信息和所述插针组位置确定插针的预期位置；
    根据所述插针信息、所述插针位置、所述插针的预期位置对所述连接器件进行缺陷检测。
  2. 根据权利要求1所述的连接器件检测方法，其中，所述根据预设的连接器件的插针信息对待测的连接器件图像进行检测，获取插针位置和插针组位置，包括：
    基于预设的目标检测算法对所述待测的连接器件图像进行检测，获取初始插针组位置和初始插针位置；
    基于预设的图像分割算法对所述待测的连接器件图像中插针所在区域的图像进行处理，提取插针图像掩码；
    根据所述连接器件的插针信息和所述插针图像掩码对所述初始插针位置进行修正，确定插针位置；
    根据所述插针位置对所述初始插针组位置进行修正，确定插针组位置。
  3. 根据权利要求1所述的连接器件检测方法，其中，所述插针信息包括：插针尺寸、插针类型、插针组类型、插针形态、插针组尺寸。
  4. 根据权利要求3中所述的连接器件检测方法，其中，所述根据预先获取的图像旋转角度、所述插针信息和所述插针组位置确定各个插针的预期位置之前，还包括：
    从所述插针组位置中确定插针组的顶点位置，并通过所述顶点位置确定所述图像旋转角度；或者，
    基于预设的图像检测算法确定所述连接器件图像的多个校准点，根据所述多个校准点计算所述图像旋转角度。
  5. 根据权利要求4所述的连接器件检测方法，其中，所述从所述插针组位置中确定插针组的顶点位置，并通过所述顶点位置确定所述图像旋转角度，包括：
    当所述插针组尺寸大于或等于于预设的阈值时，根据所述插针组位置确定所述插针组的多个顶点位置；
    通过所述顶点位置计算各顶点的坐标差，根据所述坐标差确定所述插针组的横向边缘旋转角度和纵向边缘旋转角度；
    将所述横向边缘旋转角度和所述纵向边缘旋转角度作为初始旋转角度，并对获取到的多个插针组的初始旋转角度进行平均，确定所述图像旋转角度。
  6. 根据权利要求3所述的连接器件检测方法，其中，当所述插针类型为复合型时，所述插针信息还包括：部件信息；
    所述根据所述插针信息、所述插针位置、所述插针的预期位置对所述连接器件进行缺陷检测，包括：
    当所述插针类型为单一型时，根据所述插针位置和所述插针的预期位置确定所述连接器 件是否存在缺针情况和/或歪针情况；
    当所述插针类型为复合型时，对所述待测的连接器件图像中插针所在区域的图像进行分割，获取所述插针中的部件的部件位置，并根据所述插针信息、所述图像旋转角度和所述插针组位置确定部件的预期位置，通过所述插针位置、所述插针的预期位置、所述部件位置和所述部件的预期位置对所述连接器件进行缺陷检测。
  7. 根据权利要求6所述的连接器件检测方法，其中，所述对所述待测的连接器件图像中插针所在区域的图像进行分割，包括：
    根据所述部件信息和预设的图像分割算法对所述插针所在区域的图像进行分割，获取各部件的部件区域；
    基于预设的目标检测算法对各部件的部件区域进行检测，确定部件位置。
  8. 根据权利要求6或7所述的连接器件检测方法，其中，所述插针中的部件包含边框和中间针，所述部件位置包含边框位置和中间针位置，所述部件的预期位置包括：边框预期位置和中间针预期位置；
    所述通过所述插针位置、所述插针的预期位置、所述部件位置和所述部件的预期位置对所述连接器件进行缺陷检测，包括：
    根据所述插针位置和所述插针的预期位置确定所述连接器件是否存在缺针情况和/或歪针情况；
    根据所述边框位置和所述边框的预期位置确定所述连接器件是否存在边框缺少情况和/或边框歪斜情况；
    根据所述中间针位置和所述中间针的预期位置确定所述连接器件是否存在中间针缺少情况和/或中间针歪斜情况。
  9. 一种电子设备，包括：
    至少一个处理器；以及，
    与所述至少一个处理器通信连接的存储器；其中，
    所述存储器存储有可被所述至少一个处理器执行的指令，所述指令被所述至少一个处理器执行，以使所述至少一个处理器能够执行如权利要求1至8中任一项所述的连接器件检测方法。
  10. 一种计算机可读存储介质，存储有计算机程序，其中，所述计算机程序被处理器执行时实现权利要求1至8中任一项所述的连接器件检测方法。
PCT/CN2022/136705 2021-12-14 2022-12-05 连接器件检测方法、电子设备及存储介质 WO2023109557A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202111531962.6 2021-12-14
CN202111531962.6A CN116342456A (zh) 2021-12-14 2021-12-14 连接器件检测方法、电子设备及存储介质

Publications (1)

Publication Number Publication Date
WO2023109557A1 true WO2023109557A1 (zh) 2023-06-22

Family

ID=86774853

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/136705 WO2023109557A1 (zh) 2021-12-14 2022-12-05 连接器件检测方法、电子设备及存储介质

Country Status (2)

Country Link
CN (1) CN116342456A (zh)
WO (1) WO2023109557A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117571724A (zh) * 2024-01-16 2024-02-20 季华实验室 留置针缺陷检测方法、系统、电子设备和存储介质

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116863175B (zh) * 2023-08-31 2023-12-26 中江立江电子有限公司 一种直角连接器缺陷识别方法、装置、设备及介质

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102096795A (zh) * 2010-11-25 2011-06-15 西北工业大学 磨损二维条码图像识别方法
US20140078498A1 (en) * 2012-09-14 2014-03-20 Keyence Corporation Appearance Inspection Device, Appearance Inspection Method, And Program
CN104933720A (zh) * 2015-06-25 2015-09-23 哈尔滨工业大学 一种基于视觉的sop元件定位和缺陷检测方法
CN106500593A (zh) * 2016-10-31 2017-03-15 哈尔滨工业大学 航空电连接器插针位置偏差检测方法

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102096795A (zh) * 2010-11-25 2011-06-15 西北工业大学 磨损二维条码图像识别方法
US20140078498A1 (en) * 2012-09-14 2014-03-20 Keyence Corporation Appearance Inspection Device, Appearance Inspection Method, And Program
CN104933720A (zh) * 2015-06-25 2015-09-23 哈尔滨工业大学 一种基于视觉的sop元件定位和缺陷检测方法
CN106500593A (zh) * 2016-10-31 2017-03-15 哈尔滨工业大学 航空电连接器插针位置偏差检测方法

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117571724A (zh) * 2024-01-16 2024-02-20 季华实验室 留置针缺陷检测方法、系统、电子设备和存储介质

Also Published As

Publication number Publication date
CN116342456A (zh) 2023-06-27

Similar Documents

Publication Publication Date Title
WO2023109557A1 (zh) 连接器件检测方法、电子设备及存储介质
WO2018068415A1 (zh) 元件错件检测方法和系统
CN107356213B (zh) 滤光片同心度测量方法及终端设备
CN115082394A (zh) 一种插件缺陷视觉检测识别方法、可读存储介质及设备
CN113030121B (zh) 用于电路板元器件的自动光学检测方法、系统、及设备
CN111915549A (zh) 瑕疵检测方法、电子装置及计算机可读存储介质
US11120545B2 (en) Method for measuring hole provided in workpiece
US11315229B2 (en) Method for training defect detector
CN115049736B (zh) 用于电缆表面缺陷精准定位的方法
EP4296952A1 (en) Ccd camera calibration system, method and apparatus, computing device, and storage medium
CN113393447B (zh) 基于深度学习的针尖正位度检测方法及系统
CN117058411B (zh) 电池棱边外形瑕疵识别方法、装置、介质和设备
US11176419B1 (en) Method for labeling image
CN112419225B (zh) 一种基于引脚分割的sop型芯片检测方法及系统
CN117152145A (zh) 一种基于图像的板卡工艺检测方法及装置
CN117589770A (zh) Pcb贴片板检测方法、装置、设备及介质
CN116993725A (zh) 一种柔性电路板智能贴片信息处理系统
CN115147386A (zh) U型管的缺陷检测方法、装置及电子设备
JP2002008029A (ja) 画像検査装置
CN110874837A (zh) 一种基于局部特征分布的缺陷自动检测方法
CN117876376B (zh) 高速率多功能连接器质量视觉检测方法
KR102648104B1 (ko) 차량 단차 측정 방법, 장치 및 컴퓨터 프로그램
CN112730427B (zh) 一种基于机器视觉的产品表面缺陷检测方法及系统
CN116245900A (zh) 一种基于投影的电子元器件边缘瑕疵检测方法
TWI571829B (zh) 光學檢測方法

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22906307

Country of ref document: EP

Kind code of ref document: A1