WO2018010387A1 - 元件反件检测方法和*** - Google Patents

元件反件检测方法和*** Download PDF

Info

Publication number
WO2018010387A1
WO2018010387A1 PCT/CN2016/113130 CN2016113130W WO2018010387A1 WO 2018010387 A1 WO2018010387 A1 WO 2018010387A1 CN 2016113130 W CN2016113130 W CN 2016113130W WO 2018010387 A1 WO2018010387 A1 WO 2018010387A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
region
pixel
polar
area
Prior art date
Application number
PCT/CN2016/113130
Other languages
English (en)
French (fr)
Inventor
李红匣
Original Assignee
广州视源电子科技股份有限公司
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 广州视源电子科技股份有限公司 filed Critical 广州视源电子科技股份有限公司
Publication of WO2018010387A1 publication Critical patent/WO2018010387A1/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
    • 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
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30108—Industrial image inspection
    • G06T2207/30141—Printed circuit board [PCB]

Definitions

  • the present invention relates to the field of automatic optical detection technology, and in particular to a method and system for detecting component reverse parts.
  • AOI Automatic Optic Inspection
  • common defect detection includes missing parts detection, wrong part detection, reverse part detection, multi-piece detection, and the like.
  • the reverse component detection refers to the detection of polar components such as diodes, capacitors, and sockets, and judges whether there is a reverse phenomenon in the circuit board.
  • the component detection of the component is mainly based on the intelligent method, that is, the deep learning method is used to train a large number of samples to obtain a classification model.
  • Deep learning is a new field of machine learning research. Its purpose is to simulate the mechanism of the human brain to interpret data and discover distributed feature representations of data.
  • the learning models established under different learning frameworks are also different. For example, Convolutional Neural Networks (CNNs) is a deep machine learning model.
  • CNNs Convolutional Neural Networks
  • the component polarity detection classifier trained by the convolutional neural network although achieving a desirable effect in the polarity detection of the component, has its own drawbacks that cannot be solved by itself.
  • the component polarity detection model trained by the convolutional neural network has a high recognition rate for known components and can achieve a good detection effect. However, for unknown components, that is, components that do not exist in the training sample, the recognition rate of the component polarity detection model decreases, and false positives and false negatives often occur.
  • the existing component polarity detection method has a poor detection effect.
  • a method for detecting a component reverse component includes the following steps:
  • polarity area is an area where the electrode of the device to be tested is mounted on the circuit board, and the polarity symmetry area is reversed The area of the electrode on the circuit board;
  • the threshold value determines the component to be tested.
  • a component reverse component detecting system includes:
  • Obtaining a module configured to obtain an image of a polar region and a region of a polar symmetric region of the device to be tested on the circuit board; wherein the polarity region is an area of the electrode of the device to be tested on the circuit board when the polarity is correctly installed, The region of the electrode on the circuit board when the symmetrical region is the reverse member;
  • a first comparison module configured to acquire a first number of pixel points in the image of the polarity region that are within a preselected pixel value interval, and place the first number and the pixel value in the pre-stored polarity region reference image Comparing the first reference number of pixel points in the pixel interval;
  • a second comparison module configured to acquire a second number of pixel points in the polarity symmetric area image that have pixel values in the pixel value interval, and use the second quantity and the pixel value in the polarity area reference image Comparing the second reference number of pixels in the pixel interval;
  • a determining module configured to: if a difference between the first quantity and the first reference quantity is greater than a preset first difference threshold, and a difference between the second quantity and the second reference quantity is less than a preset
  • the second difference threshold is used to determine the component to be tested.
  • the above component reversal detecting method and system by placing a pixel value of a polarity region image of an element to be tested in a preselected pixel value interval, and a pixel value in a polar region reference image in the pixel interval Comparing the first reference number of pixels within the pixel, and the pixel value in the polarity symmetric region image of the component to be tested is in the preselected image Comparing the second number of pixel points in the prime value interval with the second reference number of the pixel points in the polarity symmetric region reference image in which the pixel value is within the pixel interval, if the first quantity and the first reference The difference between the quantity is greater than a preset first difference threshold, and the difference between the second quantity and the second reference quantity is less than a preset second difference threshold, and the component to be tested is determined to be reversed.
  • a large number of training samples only need to obtain the polar region and the polar symmetric region of the component, and the operation is simple, the recognition rate is high, and the detection effect
  • FIG. 1 is a flow chart of a method for detecting a component reverse member of an embodiment
  • FIG. 2 is a schematic view of a polar region and a polar symmetric region
  • FIG. 3 is a schematic diagram of a template matching method
  • FIG. 4 is a schematic structural view of an element reverse detecting system of one embodiment.
  • the component reverse component detecting method may include the following steps:
  • FIG. 1 A schematic diagram of the polar region and the polar symmetric region of the present invention is shown in FIG.
  • the image of the circuit board may be acquired first, and then the polar region and the polar symmetric region are located from the image of the circuit board, and the polar region and the polar symmetric region are respectively intercepted from the image of the circuit board.
  • the corresponding image is set as the polar area image and the polar symmetrical area image.
  • the polar region image may be acquired by a template matching method.
  • the template matching method is shown in Figure 3. Specifically, a first image region matching the polar region reference image may be selected from the image of the circuit board; and pixels of each pixel in the reference image according to the first image region and the polar region may be selected a value, a first pixel similarity of the image region to the polar region reference image is calculated; and a first image region having a first pixel similarity greater than or equal to a preset first pixel similarity threshold is set as Polar area image.
  • the polar region The test image may be pre-stored in a storage area of the system and called from the storage area when the polar area image is acquired.
  • an area of the image of the circuit board adjacent to the first image area may be set as the first image area, and repeated A step of calculating a first pixel similarity of the first image region and the polar region reference image.
  • the area adjacent to the first image area is an area obtained by moving the first image area to the x-axis and the y-axis by a plurality of pixel points in an image of the circuit board.
  • each moving pixel point may be one pixel point or multiple pixel points, and the moving distance may be set according to actual needs.
  • the polar symmetric region image can also be acquired by a template matching method.
  • a second image region matching the polar symmetric region reference image may be selected from the image of the circuit board; and each pixel in the reference image is referenced according to the second image region and the polar symmetric region a pixel value, calculating a second pixel similarity of the image region and the polar symmetric region reference image; and setting a second image region having a second pixel similarity greater than or equal to a preset second pixel similarity threshold Is the image of the polar symmetric region.
  • the polar symmetric region reference image may be pre-stored in a storage area of the system and called from the storage region when the polar region image is acquired.
  • an area adjacent to the second image area in the image of the circuit board may be set as the second image area, and repeated And calculating a second pixel similarity of the second image region and the polar region reference image.
  • the area adjacent to the second image area is an area obtained by moving the second image area to the x-axis and the y-axis by a plurality of pixel points in an image of the circuit board.
  • each moving pixel point may be one pixel point or multiple pixel points, and the moving distance may be set according to actual needs.
  • the polar area image and the polar symmetric area image may also be acquired according to other methods.
  • the first pixel similarity and the second pixel similarity may be calculated according to the following formula:
  • R(x, y) is the image of the pixel of the image region and the polar region reference image with coordinates (x, y)
  • T(x, y) is the pixel value of the pixel with the coordinate (x, y) in the reference image of the polar region
  • I(x, y) is the coordinate of the image region (x, y) The pixel value of the pixel.
  • the first pixel similarity threshold may be set according to actual needs. For example, it can be set to 0.8, or set to 0.9, or set to other values. The larger the first pixel similarity threshold, the higher the accuracy of image acquisition.
  • the pre-selected pixel value interval can be selected according to actual needs. For example, each pixel point in the polar area image may be divided into a plurality of sections according to a distribution of pixel values, and a section having the largest number of pixel points is selected from the plurality of sections, and the preselected pixel value interval is set as .
  • the plurality of sections may be two sections or two or more sections. Taking the two intervals as an example, the polar region image and the average gray value of the pixel of the polar symmetric region image may be calculated; and the pixel with the pixel value in the polar region image being greater than the average grayscale value is obtained. The first number.
  • the polarity area image may be binarized, and the pixel value of the pixel point whose pixel value is greater than the average gray value is set to P1, and the pixel value is less than or The pixel value of the pixel equal to the average gray value is set to P2.
  • the pixel value of the pixel point whose pixel value is larger than the average gray value may be set to 255, and the pixel value of the pixel point whose pixel value is less than or equal to the average gray value may be set to 0. , which is
  • f(x, y) is the pixel value of the pixel at coordinates (x, y)
  • f'(x, y) is the binarized pixel value
  • m is the average gray value
  • the average gray value can be calculated according to the following formula:
  • m 1 and m 2 are the polar region image and the polar symmetric region image, respectively, w 1 and h 1 are the width and height of the polar region image, respectively, w 2 and h 2 are respectively The width and height of the polar symmetric region image; f 1 (x, y) and f 2 (x, y) respectively indicate that the coordinates of the polar region image and the polar symmetric region image are (x, y) The pixel value of the pixel.
  • the polar area image and the polar symmetric area image may be color images, and therefore, the polar area image and the pole may also be calculated before calculating the average gray value.
  • the symmetrical region image is converted into a grayscale image. Taking the polar region image as an example, the polar region image can be converted into a grayscale image according to the following formula:
  • Gray is a gray value of a grayscale image
  • R, G, and B are color components of the polar region image in the RGB space.
  • the polar symmetric region image can be converted to a grayscale image in a similar manner.
  • the polar area image and the polar symmetric area image may also be converted into grayscale images according to other methods.
  • This step can be performed in a similar manner to step S2, and details are not described herein again.
  • the difference threshold is used to determine the component to be tested.
  • the difference between the first quantity and the first reference quantity is greater than a preset first difference threshold, and the difference between the second quantity and the second reference quantity is less than a preset
  • the second difference threshold indicates that the polar region of the device to be tested is similar to the polar symmetric region of the reference image, and the polar symmetric region of the device to be tested is similar to the polar region of the reference image, thereby determining The reverse component of the component to be tested is described.
  • the threshold value indicates that the polarity region of the device to be tested is similar to the polarity region of the reference image, and the polarity symmetry region of the device to be tested is similar to the polarity symmetry region of the reference image, so that the device under test can be determined not to be Reverse pieces.
  • the present invention further provides a component reverse component detecting system.
  • the component reverse component detecting system may include:
  • the obtaining module 10 is configured to obtain an image of a polar region and a region of a polar symmetry region of the device to be tested on the circuit board; wherein, the polar region is an area of the electrode of the device to be tested on the circuit board when the device is correctly installed.
  • the region of the electrode on the circuit board when the polar symmetric region is the reverse member;
  • FIG. 1 A schematic diagram of the polar region and the polar symmetric region of the present invention is shown in FIG.
  • the image of the circuit board may be acquired first, and then the polar region and the polar symmetric region are located from the image of the circuit board, and the polar region and the polar symmetric region are respectively intercepted from the image of the circuit board.
  • the corresponding image is set as the polar area image and the polar symmetrical area image.
  • the polar region image may be acquired by a template matching method.
  • the template matching method is shown in Figure 3. Specifically, a first image region matching the polar region reference image may be selected from the image of the circuit board; and pixels of each pixel in the reference image according to the first image region and the polar region may be selected a value, a first pixel similarity of the image region to the polar region reference image is calculated; and a first image region having a first pixel similarity greater than or equal to a preset first pixel similarity threshold is set as Polar area image.
  • the polar area reference image may be pre-stored in a storage area of the system and called from the storage area when the polar area image is acquired.
  • an area of the image of the circuit board adjacent to the first image area may be set as the first image area, and repeated A step of calculating a first pixel similarity of the first image region and the polar region reference image.
  • the area adjacent to the first image area An area obtained by moving the first image area to the x-axis and the y-axis by a plurality of pixel points in an image of the board.
  • each moving pixel point may be one pixel point or multiple pixel points, and the moving distance may be set according to actual needs.
  • the polar symmetric region image can also be acquired by a template matching method.
  • a second image region matching the polar symmetric region reference image may be selected from the image of the circuit board; and each pixel in the reference image is referenced according to the second image region and the polar symmetric region a pixel value, calculating a second pixel similarity of the image region and the polar symmetric region reference image; and setting a second image region having a second pixel similarity greater than or equal to a preset second pixel similarity threshold Is the image of the polar symmetric region.
  • the polar symmetric region reference image may be pre-stored in a storage area of the system and called from the storage region when the polar region image is acquired.
  • an area adjacent to the second image area in the image of the circuit board may be set as the second image area, and repeated And calculating a second pixel similarity of the second image region and the polar region reference image.
  • the area adjacent to the second image area is an area obtained by moving the second image area to the x-axis and the y-axis by a plurality of pixel points in an image of the circuit board.
  • each moving pixel point may be one pixel point or multiple pixel points, and the moving distance may be set according to actual needs.
  • the polar area image and the polar symmetric area image may also be acquired according to other methods.
  • the first pixel similarity and the second pixel similarity may be calculated according to the following formula:
  • R(x, y) is the pixel similarity of the pixel of the image region and the coordinate region (x, y) in the polar region reference image
  • T(x, y) is the polar region
  • the pixel value of the pixel at coordinates (x, y) in the reference image, I(x, y) is the pixel value of the pixel at coordinates (x, y) in the image region.
  • the first pixel similarity threshold may be set according to actual needs. For example, it can be set to 0.8, or set to 0.9, or set to other values. The larger the first pixel similarity threshold, the higher the accuracy of image acquisition.
  • the first comparison module 20 is configured to acquire an image in which the pixel value in the polarity region image is within a preselected pixel value interval. a first number of prime points, comparing the first number to a first reference number of pixel points in the pre-stored polar region reference image that have pixel values within the pixel interval;
  • the pre-selected pixel value interval can be selected according to actual needs. For example, each pixel point in the polar area image may be divided into a plurality of sections according to a distribution of pixel values, and a section having the largest number of pixel points is selected from the plurality of sections, and the preselected pixel value interval is set as .
  • the plurality of sections may be two sections or two or more sections. Taking the two intervals as an example, the polar region image and the average gray value of the pixel of the polar symmetric region image may be calculated; and the pixel with the pixel value in the polar region image being greater than the average grayscale value is obtained. The first number.
  • the polarity area image may be binarized, and the pixel value of the pixel point whose pixel value is greater than the average gray value is set to P1, and the pixel value is less than or The pixel value of the pixel equal to the average gray value is set to P2.
  • the pixel value of the pixel point whose pixel value is larger than the average gray value may be set to 255, and the pixel value of the pixel point whose pixel value is less than or equal to the average gray value may be set to 0. , which is
  • f(x, y) is the pixel value of the pixel at coordinates (x, y) in the polar region map
  • f'(x, y) is the coordinate in the binarized polar region map
  • the pixel value of the pixel of (x, y), m is the average gray value.
  • the average gray value can be calculated according to the following formula:
  • m 1 and m 2 are the polar region and the image region image polar symmetry
  • w 1 and h 1 are the width and height of the polar regions of the image
  • w 2 and h 2 respectively The width and height of the polar symmetric region image
  • f 1 (x, y) and f 2 (x, y) respectively indicate that the coordinates of the polar region image and the polar symmetric region image are (x, y
  • the polar area image and the polar symmetric area image may be color images, and therefore, the polar area image and the pole may also be calculated before calculating the average gray value.
  • the symmetrical region image is converted into a grayscale image. Taking the polar region image as an example, the polar region image can be converted into a grayscale image according to the following formula. image:
  • Gray is a gray value of a grayscale image
  • R, G, and B are color components of the polar region image in the RGB space.
  • the polar symmetric region image can be converted to a grayscale image in a similar manner.
  • the polar area image and the polar symmetric area image may also be converted into grayscale images according to other methods.
  • a second comparison module 30 configured to acquire a second number of pixel points in the polarity symmetric area image that have pixel values in the pixel value interval, and use the second quantity and the pixel in the polarity area reference image Comparing the second reference number of pixels at a value within the pixel interval;
  • the second comparison module 30 can be executed in a similar manner to the first comparison module 20, and details are not described herein again.
  • the determining module 40 is configured to: if the difference between the first quantity and the first reference quantity is greater than a preset first difference threshold, and the difference between the second quantity and the second reference quantity is less than a pre And setting a second difference threshold to determine the component to be tested.
  • the threshold value indicates that the polarity region of the device to be tested is similar to the polarity symmetry region of the reference image, and the polarity symmetry region of the component to be tested is similar to the polarity region of the reference image, so that the component to be tested can be determined to be opposite. Pieces.
  • the threshold value indicates that the polarity region of the device to be tested is similar to the polarity region of the reference image, and the polarity symmetry region of the device to be tested is similar to the polarity symmetry region of the reference image, so that the device under test can be determined not to be Reverse pieces.
  • the component is a reverse member, especially in the case where the polar region and the non-polar region are relatively similar in color (for example, the polar region is gray and the polar symmetric region is black). It can effectively judge whether the component is reversed.
  • the component reverse component detecting system of the present invention has a one-to-one correspondence with the component reverse component detecting method of the present invention, and the technical features and the beneficial effects thereof described in the embodiment of the component reverse component detecting method are applicable to the embodiment of the component reverse component detecting system. In this regard, hereby declare.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Quality & Reliability (AREA)
  • Image Analysis (AREA)
  • Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)

Abstract

一种元件反件检测方法和***，其中方法包括以下步骤：获取电路板上待测元件的极性区域图像和极性对称区域图像（S1）；获取所述极性区域图像中像素值处于预选的像素值区间内的像素点的第一数量，将所述第一数量与预存的极性区域参考图像中像素值处于所述像素区间内的像素点的第一参考数量进行比较（S2）；获取所述极性对称区域图像中像素值处于所述像素值区间内的像素点的第二数量，将所述第二数量与所述极性区域参考图像中像素值处于所述像素区间内的像素点的第二参考数量进行比较（S3）；若所述第一数量与所述第一参考数量的差值大于预设的第一差值阈值，且所述第二数量与所述第二参考数量的差值小于预设的第二差值阈值，判定所述待测元件反件（S4）。

Description

元件反件检测方法和*** 技术领域
本发明涉及自动光学检测技术领域，特别是涉及一种元件反件检测方法和***。
背景技术
AOI(Automatic Optic Inspection，自动光学检测)，是利用光学原理对电路板焊接生产中出现的常见缺陷进行检测的设备。对于插件的电路板来说，常见的缺陷检测包括漏件检测、错件检测、反件检测、多件检测等。其中，反件检测是指对二极管、电容、插座等有极性的元件进行检测，判断其在电路板中是否存在反向的现象。
目前，元件的反件检测主要采用智能方法，即利用深度学习的方法对大量样本进行训练，得到分类模型。深度学习是机器学习研究的一个新领域，其目的是模拟人脑的机制来解释数据、发现数据的分布式特征表示。不同的学习框架下建立的学习模型也是不同的。例如，卷积神经网络(Convolutional neural networks，简称CNNs)就是一种深度机器学习模型。
利用卷积神经网络训练的元件极性检测分类器，虽然在元件的极性检测方面达到了比较理想的效果，但是也有其自身无法解决的缺点。首先，利用卷积神经网络训练模型时，为了提高模型的准确率、增强模型的鲁棒性，需要大量的训练样本。但是在实际过程中需要耗费大量的人力、时间采集样本；当采集较多的训练样本后，也需要耗费大量的人力和时间进行数据标注。即使如此，也很难采集到足够多的负样本。另外，利用卷积神经网络训练的元件极性检测模型，对于已知的元件拥有很高的识别率，能够达到很好的检测效果。但是对于未知的元件，即训练样本中不存在的元件，元件极性检测模型的识别率下降，经常会发生误报和漏报。
综上所述，现有的元件极性检测方式检测效果较差。
发明内容
基于此，有必要针对现有的元件极性检测方式检测效果较差的问题，提供一种元件反件检测方法和***。
一种元件反件检测方法，包括以下步骤：
获取电路板上待测元件的极性区域图像和极性对称区域图像；其中，极性区域为安装正确时所述待测元件的电极在所述电路板上的区域，极性对称区域为反件时所述电极在电路板上的区域；
获取所述极性区域图像中像素值处于预选的像素值区间内的像素点的第一数量，将所述第一数量与预存的极性区域参考图像中像素值处于所述像素区间内的像素点的第一参考数量进行比较；
获取所述极性对称区域图像中像素值处于所述像素值区间内的像素点的第二数量，将所述第二数量与所述极性区域参考图像中像素值处于所述像素区间内的像素点的第二参考数量进行比较；
若所述第一数量与所述第一参考数量的差值大于预设的第一差值阈值，且所述第二数量与所述第二参考数量的差值小于预设的第二差值阈值，判定所述待测元件反件。
一种元件反件检测***，包括：
获取模块，用于获取电路板上待测元件的极性区域图像和极性对称区域图像；其中，极性区域为安装正确时所述待测元件的电极在所述电路板上的区域，极性对称区域为反件时所述电极在电路板上的区域；
第一比较模块，用于获取所述极性区域图像中像素值处于预选的像素值区间内的像素点的第一数量，将所述第一数量与预存的极性区域参考图像中像素值处于所述像素区间内的像素点的第一参考数量进行比较；
第二比较模块，用于获取所述极性对称区域图像中像素值处于所述像素值区间内的像素点的第二数量，将所述第二数量与所述极性区域参考图像中像素值处于所述像素区间内的像素点的第二参考数量进行比较；
判断模块，用于若所述第一数量与所述第一参考数量的差值大于预设的第一差值阈值，且所述第二数量与所述第二参考数量的差值小于预设的第二差值阈值，判定所述待测元件反件。
上述元件反件检测方法和***，通过将待测元件的极性区域图像中像素值处于预选的像素值区间内的像素点的第一数量与极性区域参考图像中像素值处于所述像素区间内的像素点的第一参考数量进行比较，将待测元件的极性对称区域图像中像素值处于预选的像 素值区间内的像素点的第二数量与极性对称区域参考图像中像素值处于所述像素区间内的像素点的第二参考数量进行比较，若所述第一数量与所述第一参考数量的差值大于预设的第一差值阈值，且所述第二数量与所述第二参考数量的差值小于预设的第二差值阈值，判定所述待测元件反件，无需大量的训练样本，只需要获取元件的极性区域和极性对称区域，操作简单，识别率高，检测效果较好。
附图说明
图1为一个实施例的元件反件检测方法的流程图；
图2为极性区域与极性对称区域的示意图；
图3为模板匹配方法的示意图；
图4为一个实施例的元件反件检测***的结构示意图。
具体实施方式
下面结合附图对本发明的元件反件检测方法和***的实施例进行说明。
图1为一个实施例的元件反件检测方法的流程图。如图1所示，所述元件反件检测方法可包括以下步骤：
S1，获取电路板上待测元件的极性区域图像和极性对称区域图像；其中，极性区域为安装正确时所述待测元件的电极在所述电路板上的区域，极性对称区域为反件时所述电极在电路板上的区域；
本发明所述的极性区域和极性对称区域的示意图如图2所示。
可以先获取所述电路板的图像，再从所述电路板的图像中定位极性区域和极性对称区域，并从所述电路板的图像中分别截取所述极性区域和极性对称区域对应的图像，设为极性区域图像和极性对称区域图像。
在一个实施例中，可以通过模板匹配的方法获取所述极性区域图像。模板匹配方法如图3所示。具体地，可以从所述电路板的图像中选取与所述极性区域参考图像相匹配的第一图像区域；根据所述第一图像区域与所述极性区域参考图像中各个像素点的像素值，计算所述图像区域与所述极性区域参考图像的第一像素相似度；并将第一像素相似度大于或等于预设的第一像素相似度阈值的第一图像区域设为所述极性区域图像。所述极性区域参 考图像可以预先存储在***的存储区域中，并在获取所述极性区域图像时从所述存储区域中调用。
若所述第一像素相似度小于预设的第一像素相似度阈值，可以将所述电路板的图像中与所述第一图像区域相邻的区域设为所述第一图像区域，并重复计算所述第一图像区域与所述极性区域参考图像的第一像素相似度的步骤。其中，与所述第一图像区域相邻的区域是在所述电路板的图像中将所述第一图像区域向x轴和y轴分别移动若干个像素点所得的区域。在上述步骤中，每次移动的像素点可以是一个像素点，也可以是多个像素点，移动的距离可以根据实际需要设定。
类似地，也可以通过模板匹配的方法获取所述极性对称区域图像。具体地，可以从所述电路板的图像中选取与所述极性对称区域参考图像相匹配的第二图像区域；根据所述第二图像区域与所述极性对称区域参考图像中各个像素点的像素值，计算所述图像区域与所述极性对称区域参考图像的第二像素相似度；并将第二像素相似度大于或等于预设的第二像素相似度阈值的第二图像区域设为所述极性对称区域图像。所述极性对称区域参考图像可以预先存储在***的存储区域中，并在获取所述极性区域图像时从所述存储区域中调用。
若所述第二像素相似度小于预设的第二像素相似度阈值，可以将所述电路板的图像中与所述第二图像区域相邻的区域设为所述第二图像区域，并重复计算所述第二图像区域与所述极性区域参考图像的第二像素相似度的步骤。其中，与所述第二图像区域相邻的区域是在所述电路板的图像中将所述第二图像区域向x轴和y轴分别移动若干个像素点所得的区域。在上述步骤中，每次移动的像素点可以是一个像素点，也可以是多个像素点，移动的距离可以根据实际需要设定。
还可以根据其他方式获取所述极性区域图像与所述极性对称区域图像。
在上述获取所述极性区域图像与所述极性对称区域图像的实施例中，可以根据如下公式计算所述第一像素相似度和第二像素相似度：
Figure PCTCN2016113130-appb-000001
式中，R(x,y)是所述图像区域与所述极性区域参考图像中坐标为(x,y)的像素点的像 素相似度，T(x,y)为所述极性区域参考图像中坐标为(x,y)的像素点的像素值，I(x,y)为所述图像区域中坐标为(x,y)的像素点的像素值。
所述第一像素相似度阈值可以根据实际需要来设定。例如，可以设为0.8，或者设为0.9，或设为其他数值。所述第一像素相似度阈值越大，图像获取的精确度越高。
S2，获取所述极性区域图像中像素值处于预选的像素值区间内的像素点的第一数量，将所述第一数量与预存的极性区域参考图像中像素值处于所述像素区间内的像素点的第一参考数量进行比较；
所述预选的像素值区间可以根据实际需要自行选定。例如，可以将所述极性区域图像中的各个像素点按照像素值的分布划分为若干个区间，从所述若干个区间中选择像素点最多的区间，并设为所述预选的像素值区间。所述若干个区间可以是2个区间，也可以是2个以上的区间。以两个区间为例，可以计算所述极性区域图像和所述极性对称区域图像像素的平均灰度值；获取所述极性区域图像中像素值大于所述平均灰度值的像素点的第一数量。其中，获取所述第一数量时，还可以对所述极性区域图像进行二值化处理，将像素值大于所述平均灰度值的像素点的像素值设为P1，将像素值小于或等于所述平均灰度值的像素点的像素值设为P2。以黑白二值化为例，可以将像素值大于所述平均灰度值的像素点的像素值设为255，将像素值小于或等于所述平均灰度值的像素点的像素值设为0，即
Figure PCTCN2016113130-appb-000002
式中，f(x,y)是坐标为(x,y)的像素点的像素值，f'(x,y)是二值化后的像素值，m是所述平均灰度值。
可根据如下公式计算所述平均灰度值：
m＝m1+m2；
其中，
Figure PCTCN2016113130-appb-000003
Figure PCTCN2016113130-appb-000004
式中，m1和m2分别为所述极性区域图像和所述极性对称区域图像，w1和h1分别为所述极性区域图像的宽和高，w2和h2分别为所述极性对称区域图像的宽和高；f1(x,y)和 f2(x,y)分别表示所述极性区域图像和所述极性对称区域图像中坐标为(x,y)的像素点的像素值。
在一个实施例中，所述极性区域图像和所述极性对称区域图像可能是彩色图像，因此，在计算所述平均灰度值之前，还可以将所述极性区域图像和所述极性对称区域图像转换为灰度图像。以述极性区域图像为例，可以根据如下公式将所述极性区域图像转换为灰度图像：
Gray＝(R*30+G*59+B*11)/100；
式中，Gray为灰度图像的灰度值，R、G、B为所述极性区域图像在RGB空间的颜色分量。
可根据类似的方式将所述极性对称区域图像转换为灰度图像。也可以根据其他方式将所述极性区域图像和极性对称区域图像转换为灰度图像。
S3，获取所述极性对称区域图像中像素值处于所述像素值区间内的像素点的第二数量，将所述第二数量与所述极性区域参考图像中像素值处于所述像素区间内的像素点的第二参考数量进行比较；
本步骤可以根据与步骤S2类似的方式执行，此处不再赘述。
S4，若所述第一数量与所述第一参考数量的差值大于预设的第一差值阈值，且所述第二数量与所述第二参考数量的差值小于预设的第二差值阈值，判定所述待测元件反件。
在本步骤中，若所述第一数量与所述第一参考数量的差值大于预设的第一差值阈值，且所述第二数量与所述第二参考数量的差值小于预设的第二差值阈值，则表明待测元件的极性区域与参考图像的极性对称区域较为类似，且待测元件的极性对称区域与参考图像的极性区域较为类似，从而可以判定所述待测元件反件。
若所述第一数量与所述第一参考数量的差值小于预设的第一差值阈值，且所述第二数量与所述第二参考数量的差值大于预设的第二差值阈值，则表明待测元件的极性区域与参考图像的极性区域较为类似，且待测元件的极性对称区域与参考图像的极性对称区域较为类似，从而可以判定所述待测元件未反件。
通过上述方式，可以准确地判断出元件是否反件，尤其在极性区域与非极性区域颜色较为相近(例如，极性区域为灰色，而极性对称区域为黑色)的情况下，上述方式可以有 效地判断出元件是否反件。
本发明的元件反件检测方法具有以下优点：
(1)无需大量的训练样本，也无需耗费大量的人力和时间进行数据标注，只需要获取元件的极性区域和极性对称区域，简单有效，降低了人力成本，检测效率高；
(2)可以实现元件极性的自动检测，进一步降低了人力成本，提高了检测效率。
(3)通过将待测元件的极性区域图像和极性对称区域与极性区域的参考图像进行比较，同时将待测元件的极性区域图像和极性对称区域与极性对称区域的参考图像进行比较，进一步提高了识别率，降低了误报和漏报的概率。
(4)在极性区域与非极性区域颜色较为相近的情况下判定准确性较高。
与所述元件反件检测方法相对应地，本发明还提供一种元件反件检测***，如图2所示，所述元件反件检测***可包括：
获取模块10，用于获取电路板上待测元件的极性区域图像和极性对称区域图像；其中，极性区域为安装正确时所述待测元件的电极在所述电路板上的区域，极性对称区域为反件时所述电极在电路板上的区域；
本发明所述的极性区域和极性对称区域的示意图如图2所示。
可以先获取所述电路板的图像，再从所述电路板的图像中定位极性区域和极性对称区域，并从所述电路板的图像中分别截取所述极性区域和极性对称区域对应的图像，设为极性区域图像和极性对称区域图像。
在一个实施例中，可以通过模板匹配的方法获取所述极性区域图像。模板匹配方法如图3所示。具体地，可以从所述电路板的图像中选取与所述极性区域参考图像相匹配的第一图像区域；根据所述第一图像区域与所述极性区域参考图像中各个像素点的像素值，计算所述图像区域与所述极性区域参考图像的第一像素相似度；并将第一像素相似度大于或等于预设的第一像素相似度阈值的第一图像区域设为所述极性区域图像。所述极性区域参考图像可以预先存储在***的存储区域中，并在获取所述极性区域图像时从所述存储区域中调用。
若所述第一像素相似度小于预设的第一像素相似度阈值，可以将所述电路板的图像中与所述第一图像区域相邻的区域设为所述第一图像区域，并重复计算所述第一图像区域与所述极性区域参考图像的第一像素相似度的步骤。其中，与所述第一图像区域相邻的区域 是在所述电路板的图像中将所述第一图像区域向x轴和y轴分别移动若干个像素点所得的区域。在上述步骤中，每次移动的像素点可以是一个像素点，也可以是多个像素点，移动的距离可以根据实际需要设定。
类似地，也可以通过模板匹配的方法获取所述极性对称区域图像。具体地，可以从所述电路板的图像中选取与所述极性对称区域参考图像相匹配的第二图像区域；根据所述第二图像区域与所述极性对称区域参考图像中各个像素点的像素值，计算所述图像区域与所述极性对称区域参考图像的第二像素相似度；并将第二像素相似度大于或等于预设的第二像素相似度阈值的第二图像区域设为所述极性对称区域图像。所述极性对称区域参考图像可以预先存储在***的存储区域中，并在获取所述极性区域图像时从所述存储区域中调用。
若所述第二像素相似度小于预设的第二像素相似度阈值，可以将所述电路板的图像中与所述第二图像区域相邻的区域设为所述第二图像区域，并重复计算所述第二图像区域与所述极性区域参考图像的第二像素相似度的步骤。其中，与所述第二图像区域相邻的区域是在所述电路板的图像中将所述第二图像区域向x轴和y轴分别移动若干个像素点所得的区域。在上述步骤中，每次移动的像素点可以是一个像素点，也可以是多个像素点，移动的距离可以根据实际需要设定。
还可以根据其他方式获取所述极性区域图像与所述极性对称区域图像。
在上述获取所述极性区域图像与所述极性对称区域图像的实施例中，可以根据如下公式计算所述第一像素相似度和第二像素相似度：
Figure PCTCN2016113130-appb-000005
式中，R(x,y)是所述图像区域与所述极性区域参考图像中坐标为(x,y)的像素点的像素相似度，T(x,y)为所述极性区域参考图像中坐标为(x,y)的像素点的像素值，I(x,y)为所述图像区域中坐标为(x,y)的像素点的像素值。
所述第一像素相似度阈值可以根据实际需要来设定。例如，可以设为0.8，或者设为0.9，或设为其他数值。所述第一像素相似度阈值越大，图像获取的精确度越高。
第一比较模块20，用于获取所述极性区域图像中像素值处于预选的像素值区间内的像 素点的第一数量，将所述第一数量与预存的极性区域参考图像中像素值处于所述像素区间内的像素点的第一参考数量进行比较；
所述预选的像素值区间可以根据实际需要自行选定。例如，可以将所述极性区域图像中的各个像素点按照像素值的分布划分为若干个区间，从所述若干个区间中选择像素点最多的区间，并设为所述预选的像素值区间。所述若干个区间可以是2个区间，也可以是2个以上的区间。以两个区间为例，可以计算所述极性区域图像和所述极性对称区域图像像素的平均灰度值；获取所述极性区域图像中像素值大于所述平均灰度值的像素点的第一数量。其中，获取所述第一数量时，还可以对所述极性区域图像进行二值化处理，将像素值大于所述平均灰度值的像素点的像素值设为P1，将像素值小于或等于所述平均灰度值的像素点的像素值设为P2。以黑白二值化为例，可以将像素值大于所述平均灰度值的像素点的像素值设为255，将像素值小于或等于所述平均灰度值的像素点的像素值设为0，即
Figure PCTCN2016113130-appb-000006
式中，f(x,y)是所述极性区域图中坐标为(x,y)的像素点的像素值，f'(x,y)是二值化后的极性区域图中坐标为(x,y)的像素点的像素值，m是所述平均灰度值。
可根据如下公式计算所述平均灰度值：
m＝m1+m2；
其中，
Figure PCTCN2016113130-appb-000007
Figure PCTCN2016113130-appb-000008
式中，m1和m2分别为所述极性区域图像和所述极性对称区域图像，w1和h1分别为所述极性区域图像的宽和高，w2和h2分别为所述极性对称区域图像的宽和高；f1(x,y)和f2(x,y)分别表示所述极性区域图像和所述极性对称区域图像中坐标为(x,y)的像素点的像素值。
在一个实施例中，所述极性区域图像和所述极性对称区域图像可能是彩色图像，因此，在计算所述平均灰度值之前，还可以将所述极性区域图像和所述极性对称区域图像转换为灰度图像。以述极性区域图像为例，可以根据如下公式将所述极性区域图像转换为灰度图 像：
Gray＝(R*30+G*59+B*11)/100；
式中，Gray为灰度图像的灰度值，R、G、B为所述极性区域图像在RGB空间的颜色分量。
可根据类似的方式将所述极性对称区域图像转换为灰度图像。也可以根据其他方式将所述极性区域图像和极性对称区域图像转换为灰度图像。
第二比较模块30，用于获取所述极性对称区域图像中像素值处于所述像素值区间内的像素点的第二数量，将所述第二数量与所述极性区域参考图像中像素值处于所述像素区间内的像素点的第二参考数量进行比较；
第二比较模块30可以根据与第一比较模块20类似的方式执行，此处不再赘述。
判断模块40，用于若所述第一数量与所述第一参考数量的差值大于预设的第一差值阈值，且所述第二数量与所述第二参考数量的差值小于预设的第二差值阈值，判定所述待测元件反件。
若所述第一数量与所述第一参考数量的差值大于预设的第一差值阈值，且所述第二数量与所述第二参考数量的差值小于预设的第二差值阈值，则表明待测元件的极性区域与参考图像的极性对称区域较为类似，且待测元件的极性对称区域与参考图像的极性区域较为类似，从而可以判定所述待测元件反件。
若所述第一数量与所述第一参考数量的差值小于预设的第一差值阈值，且所述第二数量与所述第二参考数量的差值大于预设的第二差值阈值，则表明待测元件的极性区域与参考图像的极性区域较为类似，且待测元件的极性对称区域与参考图像的极性对称区域较为类似，从而可以判定所述待测元件未反件。
通过上述方式，可以准确地判断出元件是否反件，尤其在极性区域与非极性区域颜色较为相近(例如，极性区域为灰色，而极性对称区域为黑色)的情况下，上述方式可以有效地判断出元件是否反件。
本发明的元件反件检测***具有以下优点：
(1)无需大量的训练样本，也无需耗费大量的人力和时间进行数据标注，只需要获取元件的极性区域和极性对称区域，简单有效，降低了人力成本，检测效率高；
(2)可以实现元件极性的自动检测，进一步降低了人力成本，提高了检测效率。
(3)通过将待测元件的极性区域图像和极性对称区域与极性区域的参考图像进行比较，同时将待测元件的极性区域图像和极性对称区域与极性对称区域的参考图像进行比较，进一步提高了识别率，降低了误报和漏报的概率。
(4)在极性区域与非极性区域颜色较为相近的情况下判定准确性较高。
本发明的元件反件检测***与本发明的元件反件检测方法一一对应，在上述元件反件检测方法的实施例阐述的技术特征及其有益效果均适用于元件反件检测***的实施例中，特此声明。
以上所述实施例的各技术特征可以进行任意的组合，为使描述简洁，未对上述实施例中的各个技术特征所有可能的组合都进行描述，然而，只要这些技术特征的组合不存在矛盾，都应当认为是本说明书记载的范围。
以上所述实施例仅表达了本发明的几种实施方式，其描述较为具体和详细，但并不能因此而理解为对发明专利范围的限制。应当指出的是，对于本领域的普通技术人员来说，在不脱离本发明构思的前提下，还可以做出若干变形和改进，这些都属于本发明的保护范围。因此，本发明专利的保护范围应以所附权利要求为准。

Claims (10)

  1. 一种元件反件检测方法，其特征在于，包括以下步骤：
    获取电路板上待测元件的极性区域图像和极性对称区域图像；其中，极性区域为安装正确时所述待测元件的电极在所述电路板上的区域，极性对称区域为反件时所述电极在电路板上的区域；
    获取所述极性区域图像中像素值处于预选的像素值区间内的像素点的第一数量，将所述第一数量与预存的极性区域参考图像中像素值处于所述像素区间内的像素点的第一参考数量进行比较；
    获取所述极性对称区域图像中像素值处于所述像素值区间内的像素点的第二数量，将所述第二数量与所述极性区域参考图像中像素值处于所述像素区间内的像素点的第二参考数量进行比较；
    若所述第一数量与所述第一参考数量的差值大于预设的第一差值阈值，且所述第二数量与所述第二参考数量的差值小于预设的第二差值阈值，判定所述待测元件反件。
  2. 根据权利要求1所述的元件反件检测方法，其特征在于，获取元件的极性区域图像的步骤包括：
    从所述电路板的图像中选取与所述极性区域参考图像相匹配的图像区域；
    根据所述图像区域与所述极性区域参考图像中各个像素点的像素值，计算所述图像区域与所述极性区域参考图像的像素相似度；
    将像素相似度大于或等于预设的像素相似度阈值的图像区域设为所述极性区域图像。
  3. 根据权利要求2所述的元件反件检测方法，其特征在于，还包括以下：
    若所述相似度小于预设的相似度阈值，将所述电路板的图像中与所述图像区域相邻的区域设为所述图像区域；
    其中，与所述图像区域相邻的区域是在所述电路板的图像中将所述图像区域向x轴和y轴分别移动若干个像素点所得的区域。
  4. 根据权利要求3所述的元件反件检测方法，其特征在于，计算所述图像区域与所述极性区域参考图像的像素相似度的步骤包括：
    根据如下公式计算所述像素相似度：
    Figure PCTCN2016113130-appb-100001
    式中，R(x,y)是所述图像区域与所述极性区域参考图像中坐标为(x,y)的像素点的像素相似度，T(x,y)为所述极性区域参考图像中坐标为(x,y)的像素点的像素值，I(x,y)为所述图像区域中坐标为(x,y)的像素点的像素值。
  5. 根据权利要求1所述的元件反件检测方法，其特征在于，获取所述极性区域图像中像素值处于预选的像素值区间内的像素点的第一数量的步骤包括：
    计算所述极性区域图像和所述极性对称区域图像像素的平均灰度值；
    获取所述极性区域图像中像素值大于所述平均灰度值的像素点的第一数量。
  6. 根据权利要求5所述的元件反件检测方法，其特征在于，计算所述极性区域图像和所述极性对称区域图像的平均灰度值的步骤包括：
    根据如下公式计算所述平均灰度值：
    m＝m1+m2；
    其中，
    Figure PCTCN2016113130-appb-100002
    Figure PCTCN2016113130-appb-100003
    式中，m1和m2分别为所述极性区域图像和所述极性对称区域图像，w1和h1分别为所述极性区域图像的宽和高，w2和h2分别为所述极性对称区域图像的宽和高；f1(x,y)和f2(x,y)分别表示所述极性区域图像和所述极性对称区域图像中坐标为(x,y)的像素点的像素值。
  7. 根据权利要求5所述的元件反件检测方法，其特征在于，在计算所述极性区域图像和所述极性对称区域图像的平均灰度值之前，还包括以下步骤：
    将所述极性区域图像和所述极性对称区域图像转换为灰度图像。
  8. 根据权利要求7所述的元件反件检测方法，其特征在于，将所述极性区域图像和所述极性对称区域图像转换为灰度图像的步骤包括：
    根据如下公式将所述极性区域图像和所述极性对称区域图像转换为灰度图像：
    Gray＝(R*30+G*59+B*11)/100；
    式中，Gray为灰度图像的灰度值，R、G、B为所述极性区域图像在RGB空间的颜色分量。
  9. 根据权利要求1所述的元件反件检测方法，其特征在于，还包括以下步骤：
    若所述第一数量与所述第一参考数量的差值小于预设的第一差值阈值，且所述第二数量与所述第二参考数量的差值大于预设的第二差值阈值，判断所述待测元件未反件。
  10. 一种元件反件检测***，其特征在于，包括：
    获取模块，用于获取电路板上待测元件的极性区域图像和极性对称区域图像；其中，极性区域为安装正确时所述待测元件的电极在所述电路板上的区域，极性对称区域为反件时所述电极在电路板上的区域；
    第一比较模块，用于获取所述极性区域图像中像素值处于预选的像素值区间内的像素点的第一数量，将所述第一数量与预存的极性区域参考图像中像素值处于所述像素区间内的像素点的第一参考数量进行比较；
    第二比较模块，用于获取所述极性对称区域图像中像素值处于所述像素值区间内的像素点的第二数量，将所述第二数量与所述极性区域参考图像中像素值处于所述像素区间内的像素点的第二参考数量进行比较；
    判断模块，用于若所述第一数量与所述第一参考数量的差值大于预设的第一差值阈值，且所述第二数量与所述第二参考数量的差值小于预设的第二差值阈值，判定所述待测元件反件。
PCT/CN2016/113130 2016-07-13 2016-12-29 元件反件检测方法和*** WO2018010387A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201610561857.XA CN106251333B (zh) 2016-07-13 2016-07-13 元件反件检测方法和***
CN201610561857.X 2016-07-13

Publications (1)

Publication Number Publication Date
WO2018010387A1 true WO2018010387A1 (zh) 2018-01-18

Family

ID=57614009

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2016/113130 WO2018010387A1 (zh) 2016-07-13 2016-12-29 元件反件检测方法和***

Country Status (2)

Country Link
CN (1) CN106251333B (zh)
WO (1) WO2018010387A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112149744A (zh) * 2020-09-25 2020-12-29 浙江数秦科技有限公司 一种侵权图片快速识别方法
CN116309518A (zh) * 2023-03-31 2023-06-23 佛山市顺德区浩硕捷电子科技有限公司 一种基于计算机视觉的pcb电路板检测方法及***

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106251333B (zh) * 2016-07-13 2019-02-26 广州视源电子科技股份有限公司 元件反件检测方法和***
CN109429473A (zh) * 2017-08-28 2019-03-05 株洲中车时代电气股份有限公司 电路板中带极性电子元器件的自动检查方法及装置
CN107610111B (zh) * 2017-09-12 2019-12-10 武汉大学 一种基于深度学习的焊点图像检测方法
CN107886131A (zh) * 2017-11-24 2018-04-06 佛山科学技术学院 一种基于卷积神经网络检测电路板元器件极性方法和装置
CN113039577A (zh) * 2020-08-14 2021-06-25 深圳欣锐科技股份有限公司 产品测试方法、装置、计算机可读存储介质及电子设备
TWI757116B (zh) * 2021-03-17 2022-03-01 英業達股份有限公司 提供電子元件極性檢測系統及其方法

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20020038510A1 (en) * 2000-10-04 2002-04-04 Orbotech, Ltd Method for detecting line width defects in electrical circuit inspection
CN102479321A (zh) * 2010-11-26 2012-05-30 鸿富锦精密工业（深圳）有限公司 差异影像自动识别***及方法
CN102831381A (zh) * 2011-06-15 2012-12-19 鸿富锦精密工业（深圳）有限公司 影像差异比较***及方法
CN104459421A (zh) * 2014-12-30 2015-03-25 广州视源电子科技股份有限公司 一种二极管极性检测方法与***
CN105139399A (zh) * 2015-08-25 2015-12-09 广州视源电子科技股份有限公司 一种二极管极性检测方法及装置
CN106251333A (zh) * 2016-07-13 2016-12-21 广州视源电子科技股份有限公司 元件反件检测方法和***

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS587164A (ja) * 1981-07-03 1983-01-14 Minolta Camera Co Ltd トナ−濃度制御方法
CN1318839C (zh) * 2002-11-28 2007-05-30 威光机械工程股份有限公司 印刷电路板上瑕疵组件的自动光学检测方法
CN101915769B (zh) * 2010-06-29 2012-03-28 华南理工大学 一种印刷电路板中带电阻元件的自动光学检测方法
CN103675588B (zh) * 2013-11-20 2016-01-20 中国矿业大学 印刷电路元件极性的机器视觉检测方法及设备
CN105184778B (zh) * 2015-08-25 2018-04-24 广州视源电子科技股份有限公司 一种检测方法及装置
CN105260740B (zh) * 2015-09-23 2019-03-29 广州视源电子科技股份有限公司 一种元件识别方法及装置

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20020038510A1 (en) * 2000-10-04 2002-04-04 Orbotech, Ltd Method for detecting line width defects in electrical circuit inspection
CN102479321A (zh) * 2010-11-26 2012-05-30 鸿富锦精密工业（深圳）有限公司 差异影像自动识别***及方法
CN102831381A (zh) * 2011-06-15 2012-12-19 鸿富锦精密工业（深圳）有限公司 影像差异比较***及方法
CN104459421A (zh) * 2014-12-30 2015-03-25 广州视源电子科技股份有限公司 一种二极管极性检测方法与***
CN105139399A (zh) * 2015-08-25 2015-12-09 广州视源电子科技股份有限公司 一种二极管极性检测方法及装置
CN106251333A (zh) * 2016-07-13 2016-12-21 广州视源电子科技股份有限公司 元件反件检测方法和***

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112149744A (zh) * 2020-09-25 2020-12-29 浙江数秦科技有限公司 一种侵权图片快速识别方法
CN112149744B (zh) * 2020-09-25 2022-09-16 浙江数秦科技有限公司 一种侵权图片快速识别方法
CN116309518A (zh) * 2023-03-31 2023-06-23 佛山市顺德区浩硕捷电子科技有限公司 一种基于计算机视觉的pcb电路板检测方法及***

Also Published As

Publication number Publication date
CN106251333B (zh) 2019-02-26
CN106251333A (zh) 2016-12-21

Similar Documents

Publication Publication Date Title
WO2018010387A1 (zh) 元件反件检测方法和***
WO2018010386A1 (zh) 元件反件检测方法和***
CN105913093B (zh) 一种用于文字识别处理的模板匹配方法
CN111612763B (zh) 手机屏幕缺陷检测方法、装置及***、计算机设备及介质
CN108520514B (zh) 基于计算机视觉的印刷电路板电子元器一致性检测方法
CN108090494B (zh) 基于Gabor滤波器及支持向量机纺织品瑕疵识别方法
WO2018010391A1 (zh) 一种板卡的检测方法及装置
CN104867144B (zh) 基于混合高斯模型的ic元件焊点缺陷检测方法
WO2017181724A1 (zh) 电子元件漏件检测方法和***
CN106599890B (zh) 变电站巡检机器人数字式仪表识别算法
CN110929720B (zh) 一种基于logo匹配和ocr的元器件检测方法
Rusinol et al. Combining focus measure operators to predict ocr accuracy in mobile-captured document images
CN110307903B (zh) 一种家禽特定部位无接触温度动态测量的方法
CN112766218B (zh) 基于非对称联合教学网络的跨域行人重识别方法和装置
WO2017071406A1 (zh) 金针类元件的引脚检测方法和***
CN110503623A (zh) 一种基于卷积神经网络的识别输电线路上鸟巢缺陷的方法
CN110866915A (zh) 基于度量学习的圆形砚台质量检测方法
CN114429445A (zh) 一种基于MAIRNet的PCB缺陷检测与识别方法
CN112750113A (zh) 基于深度学习和直线检测的玻璃瓶缺陷检测方法及装置
CN103605973A (zh) 一种图像字符检测鉴别方法
Song et al. MsfNet: a novel small object detection based on multi-scale feature fusion
CN106886609B (zh) 街区式农村居民地遥感快速标注方法
CN104112271A (zh) 移动终端外壳侧面缺陷检测方法和***
CN108898584A (zh) 一种基于图像分析的全自动贴面电容装焊极性判别方法
CN111583341B (zh) 云台像机移位检测方法

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: 16908709

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 16908709

Country of ref document: EP

Kind code of ref document: A1