WO2017181722A1 - 元件漏检方法和系统 - Google Patents

元件漏检方法和系统 Download PDF

Info

Publication number
WO2017181722A1
WO2017181722A1 PCT/CN2016/112886 CN2016112886W WO2017181722A1 WO 2017181722 A1 WO2017181722 A1 WO 2017181722A1 CN 2016112886 W CN2016112886 W CN 2016112886W WO 2017181722 A1 WO2017181722 A1 WO 2017181722A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
value
tested
color
hsv
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/CN2016/112886
Other languages
English (en)
French (fr)
Inventor
林建民
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guangzhou Shiyuan Electronics Thecnology Co Ltd
Original Assignee
Guangzhou Shiyuan Electronics Thecnology Co Ltd
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 Guangzhou Shiyuan Electronics Thecnology Co Ltd filed Critical Guangzhou Shiyuan Electronics Thecnology Co Ltd
Publication of WO2017181722A1 publication Critical patent/WO2017181722A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0004—Industrial image inspection
    • G06T7/0008—Industrial image inspection checking presence/absence
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84—Systems specially adapted for particular applications
    • G01N21/88—Investigating the presence of flaws or contamination
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84—Systems specially adapted for particular applications
    • G01N21/88—Investigating the presence of flaws or contamination
    • G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84—Systems specially adapted for particular applications
    • G01N21/88—Investigating the presence of flaws or contamination
    • G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
    • G01N21/956—Inspecting patterns on the surface of objects
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84—Systems specially adapted for particular applications
    • G01N21/88—Investigating the presence of flaws or contamination
    • G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
    • G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
    • G01N2021/8893—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques providing a video image and a processed signal for helping visual decision
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84—Systems specially adapted for particular applications
    • G01N21/88—Investigating the presence of flaws or contamination
    • G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
    • G01N21/956—Inspecting patterns on the surface of objects
    • G01N2021/95638—Inspecting patterns on the surface of objects for PCB's
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30108—Industrial image inspection
    • G06T2207/30141—Printed circuit board [PCB]

Definitions

  • the present invention relates to the field of automated optical inspection, and more particularly to methods and systems for component miss detection.
  • the PCB circuit board (printed circuit board) is tested, and the AOI (Automatic Optic Inspection) system is used more.
  • the automatic optical inspection is an essential part of the industrial production process, and the surface of the finished product is obtained optically. Status, image processing to detect foreign objects or surface defects.
  • the fault, leakage and reverse detection of electronic components is a common application in the field of circuit board defect detection.
  • the machine automatically scans the circuit board to acquire images, extracts partial images of each electronic component, and judges electronic components through image processing technology. Whether there are errors, leaks, and anti-defects, and finally display or mark the components with suspected defects for easy viewing and overhaul.
  • a component missing detection method includes the following steps:
  • a component missing detection system comprising the following units:
  • a first acquiring unit configured to acquire a plate-making image of an area where the component to be tested is located, and an image to be tested of an area where the component to be tested is located;
  • a second acquiring unit configured to acquire an HSV image of the plate-making image, and acquire an HSV image of the image to be tested;
  • a first statistical unit configured to count, according to the hue value and the saturation value of the body color of the component to be tested, and the preset tolerance value, the number of the first pixel points in the HSV image of the plate-making image that match the color of the body, wherein The color of the main body is the color having the largest proportion among the colors of the component to be tested;
  • a second statistic unit configured to count, according to a hue value and a saturation value of the main body color and a preset tolerance value, a number of second pixel points in the HSV image of the image to be tested that match the color of the main body;
  • a comparison unit configured to obtain a ratio of the number of the first pixel points and the number of the second pixel points, compare the ratio with the first preset value, and if the ratio is smaller than the first preset value, determine that the device to be tested is Missing parts in the image to be tested.
  • the plate-making image of the area where the component to be tested is located and the image to be tested of the area where the component to be tested is located are respectively obtained, and then the HSV image of the plate-making image and the HSV image of the image to be tested are respectively obtained, according to the test
  • the image is converted to the HSV color space, and the hue value and the saturation value and the tolerance value in the HSV image are used to calculate the number of pixels matching the main color, and the brightness value is discarded, thereby reducing the illumination change to match the color.
  • the effect of the pixel improves the accuracy of the component miss detection method.
  • FIG. 1 is a schematic flow chart of a component missing detection method in one embodiment
  • Figure 2 is a graph showing the relationship between the number of matched color pixels and the tolerance in one of the embodiments
  • FIG. 3 is a schematic structural view of a component missing inspection system in one embodiment
  • FIG. 4 is a schematic structural view of a component missing inspection system in one embodiment
  • Figure 5 is a schematic structural view of a component missing inspection system in one embodiment
  • Fig. 6 is a schematic view showing the structure of the component missing detecting system in one embodiment.
  • the component missing detection method in this embodiment includes the following steps:
  • Step S101 acquiring a plate-making image of an area where the component to be tested is located and an image to be tested of an area where the component to be tested is located;
  • the component to be tested may be an electronic component on the PCB, such as a resistor, an inductor, a capacitor, etc.; the plate-making image may be a part of the PCB image of the area of the PCB component corresponding to the component to be tested that is not missing; the image to be tested may be The part of the PCB board image corresponding to the area where the component to be tested is obtained by actually taking the PCB board, but it is not determined whether the component to be tested is missing;
  • Step S102 Acquire an HSV image of the plate-making image, and acquire an HSV image of the image to be tested;
  • the HSV image of the plate-making image is the image of the three channels of the plate image in H (hue), S (saturation), and V (lightness), and each pixel in the HSV image of the plate-making image corresponds to each pixel of the plate-making image.
  • the HSV image of the image to be tested is an image of the three channels of the image to be tested in H (hue), S (saturation), and V (lightness), and each pixel in the HSV image of the image to be tested is the image to be tested. Corresponding to each pixel;
  • Step S103 According to the hue value and the saturation value of the main body color of the device to be tested and the preset tolerance value, the number of the first pixel points in the HSV image of the plate-making image that matches the color of the main body is counted, wherein the main body color is The color that accounts for the largest proportion of each color of the component to be tested;
  • Step S104 Calculate the number of second pixel points in the HSV image of the image to be tested that match the color of the subject according to the hue value and the saturation value of the subject color and the preset tolerance value;
  • Step S105 Obtain a ratio of the number of the first pixel points to the number of the second pixel points, compare the ratio with the first preset value, and if the ratio is smaller than the first preset value, determine that the device to be tested is in the test Missing pieces in the image.
  • the plate-making image of the area where the component to be tested is located and the image to be tested of the area where the component to be tested is located are respectively obtained, and then the HSV image of the plate-making image and the HSV image of the image to be tested are respectively obtained, according to the component to be tested.
  • the ratio of the number of two pixels and the size of the first preset value determine whether the component to be tested is missing in the image to be tested.
  • the image is converted to the HSV color space, and the hue value and the saturation value and the tolerance value in the HSV image are used to calculate the number of pixels matching the main color, and the brightness value is discarded, thereby reducing the illumination change to match the color.
  • the effect of the pixel improves the accuracy of the component miss detection method.
  • first a first pixel
  • second a second pixel
  • first pixel a first pixel without departing from the scope of the present invention.
  • the color pixel value of the subject color under the different tolerance values, the number of the third pixel points matching the color of the main body in the plate-making image is obtained, and the relationship curve of the number of the third pixel points-tolerance is obtained, and the relationship curve is obtained.
  • the tolerance corresponding to the slowest point of the third pixel point is used as the preset tolerance value.
  • the preset tolerance value is determined according to the relationship between the number of third pixel points and the tolerance.
  • the tolerance value of the color is very important for the detection of the missing parts. If the tolerance setting is too small, the missing first part of the pixel will be misjudged when the missing part is detected. If the tolerance is set too large, the missing part is missing. When detecting, it will be easy to misjudge because the first pixel is too large. Therefore, it is necessary to set the appropriate tolerance value.
  • the tolerance value corresponding to the minimum slope in the relationship curve of the third pixel number-tolerance is selected. That is, the tolerance value corresponding to the change in the number of color pixels that matches the color of the subject is the slowest.
  • the color pixel values herein are mainly for the RGB pixel values of each pixel in the image.
  • the step of counting the number of first pixel points matching the color of the subject in the HSV image of the statistical plate image further comprises the following steps:
  • the preset tolerance value is decreased by a preset step size, and returned to the statistical plate making The step of the number of first pixels in the HSV image of the image.
  • the preset tolerance value is too large, and the first pixel point The image area covered is too large, which will affect the accuracy of component miss detection. Therefore, it is necessary to appropriately reduce the preset tolerance value and re-statistically count the number of first pixel points and the number of second pixel points.
  • the second preset value and the preset step size can be freely adjusted according to actual conditions.
  • the step of counting the number of first pixel points in the HSV image of the plate-making image that matches the color of the subject includes the following steps:
  • the step of counting the number of first pixel points in the HSV image of the image to be tested that matches the color of the subject includes the following steps:
  • a pixel region whose saturation is less than a preset threshold is excluded from the HSV image of the image to be tested.
  • the pixel region whose saturation is less than the preset threshold value is removed, because the color with lower saturation is relatively unstable, which is not conducive to the miss detection judgment, and therefore the pixel region smaller than the preset threshold value is used.
  • the preset threshold can be adjusted freely according to the actual situation.
  • the step of counting the number of first pixel points in the HSV image of the plate-making image that matches the color of the subject according to the hue value and the saturation value of the body color of the element to be tested and the preset tolerance value includes the following steps:
  • H x, y represents the hue value at the (x, y) coordinate of the HSV image of the plate-making image
  • S x, y represents the saturation value at the (x, y) coordinate of the HSV image of the plate-making image
  • C represents The preset tolerance value, H target and S target respectively represent the tonal value and the saturation value of the subject color
  • the step of counting the second pixel point in the HSV image of the image to be tested that matches the color of the subject includes the following steps:
  • H i,j represents the hue value at the (i,j) coordinate of the HSV image of the image to be tested
  • S i,j represents the saturation value at the (i,j) coordinate of the HSV image of the image to be tested.
  • the first pixel in the HSV image of the plate-making image and the second in the HSV image of the image to be tested are counted according to the formula determined by the hue value and the saturation value of the subject color and the preset tolerance value. Pixels, according to the formula in the HSV image, it is very convenient to select the pixels of the matching matching color and count the corresponding number.
  • the hue value is the value of the HSV image in the H channel
  • the saturation value is the HSV image in the S. The value of the channel.
  • the component missing detection method can be divided into two parts, one is a plate making process, and the other is a missed detection process, the plate making process is mainly for the plate making image, and the missing detecting process is mainly for the image to be tested;
  • the tolerance corresponding to the slowest point is used as the preset tolerance value.
  • the abscissa is the tolerance value
  • the ordinate is the number of matching color pixels
  • the tolerance range can be 0 to 50.
  • the tolerance value is 20
  • the tolerance value can be selected to be 20.
  • the tolerance range can be adjusted as needed;
  • the conversion formula is as follows:
  • the V (lightness) channel under different illumination conditions has a large difference. Therefore, in order to reduce the influence of the illumination, the information of the V channel is discarded, and only the H (hue) channel, S is taken. (Saturation) The image information of the channel is compared with the color information. At the same time, because the color with lower saturation is relatively unstable, the pixel area with saturation less than 30 in the image is removed, and the color information is not compared.
  • the number of the first pixel points in the HSV image of the plate-making image that matches the color of the body is counted;
  • H x, y represents the hue value at the (x, y) coordinate of the H channel of the HSV image of the plate image
  • S x, y represents the (x, y) coordinate in the S channel of the HSV image of the plate image Saturation value
  • C represents a preset tolerance value (20)
  • H target and S target respectively represent a hue value and a saturation value of the subject color
  • the preset tolerance value After counting the number of the first pixel points, if the ratio of the image area size covered by the first pixel point to the image size of the component to be tested in the HSV image of the plate-making image exceeds the second preset value, it represents the preset tolerance value. (20) If the value is too large, the preset tolerance value needs to be reduced by a preset difference, such as the preset difference value being 1, and returning to the step of counting the number of the first pixel points, and re-stating the first pixel points. number.
  • the steps of the plate making process need only be performed once during the missed inspection of a single component, and the steps of the plate making process need to be re-executed when missing components of different types and types of components.
  • the first preset value may be 50%, and the first preset value may be appropriately adjusted according to the strictness of the leak detection.
  • the invention provides a component missing detection method, which converts an image into an HSV color space, calculates a pixel number of a matching color by using a tone value and a saturation value and a tolerance value in the HSV image, and uses the missing point as a basis. It is judged that the brightness value is discarded when calculating the number of pixels of the matching color, which reduces the influence of the illumination change on the pixels of the matched color, and improves the accuracy of the component missing detection method.
  • the present invention also provides a component missing detecting system, and an embodiment of the component missing detecting system of the present invention will be described in detail below.
  • the component missing detection system in this embodiment includes the following units:
  • the first obtaining unit 201 is configured to acquire a plate-making image of an area where the component to be tested is located and an image to be tested of an area where the component to be tested is located;
  • a second acquiring unit 202 configured to acquire an HSV image of the plate-making image, and acquire an HSV image of the image to be tested;
  • a first statistic unit 203 configured to count, according to the hue value and the saturation value of the body color of the component to be tested, and the preset tolerance value, the number of the first pixel points in the HSV image of the plate-making image that match the color of the body,
  • the main body color is a color having the largest proportion among the colors of the component to be tested;
  • a second statistic unit 204 configured to count, according to a hue value and a saturation value of the main body color and a preset tolerance value, a number of second pixel points in the HSV image of the image to be tested that match the color of the main body;
  • the comparing unit 205 is configured to obtain a ratio of the number of the first pixel points and the number of the second pixel points, compare the ratio with the first preset value, and determine the component to be tested if the ratio is smaller than the first preset value. Missing pieces in the image to be tested.
  • the component miss detection system further includes a tolerance value acquisition unit 206, and the tolerance value acquisition unit 206 is configured to use different color tolerance values according to color pixel values of the subject color. And counting the number of the third pixel points in the plate-making image that match the color of the body, acquiring a relationship curve of the number of the third pixel points-tolerance, and the third pixel point in the relationship curve The tolerance corresponding to the point where the number changes the slowest is taken as the preset tolerance value.
  • the component missing detection system further includes a tolerance value adjustment unit 207, and the tolerance value adjustment unit 207 is configured to use the image area size covered by the first pixel point and the When the ratio of the image size of the component to be tested in the HSV image of the plate image exceeds the preset second ratio, the preset tolerance value is decreased by a preset step size;
  • the first statistic unit 203 is further configured to count the number of the first pixel points according to the tone value and the saturation value of the body color and the adjusted preset tolerance value;
  • the second statistic unit 204 is further configured to count the number of the second pixel points according to the hue value and the saturation value of the subject color and the adjusted preset tolerance value.
  • the component miss detection system further includes a pre-processing unit 208 for using the HSV of the plate-making image before counting the number of the first pixel points.
  • a pre-processing unit 208 for using the HSV of the plate-making image before counting the number of the first pixel points. A pixel area in which the saturation is less than a preset threshold is excluded from the image;
  • the pre-processing unit 208 is further configured to: before counting the number of the second pixel points, cull the pixel region whose saturation is less than the preset threshold in the HSV image of the image to be tested.
  • the first statistic unit 203 passes Counting the number of first pixels
  • H x, y represents the hue value at the (x, y) coordinate of the HSV image of the plate-making image
  • S x, y represents the saturation value at the (x, y) coordinate of the HSV image of the plate-making image
  • C represents The preset tolerance value, H target and S target respectively represent the tonal value and the saturation value of the subject color
  • the second statistic unit 204 passes Counting the number of second pixels
  • H i,j represents the hue value at the (i,j) coordinate of the HSV image of the image to be tested
  • S i,j represents the saturation value at the (i,j) coordinate of the HSV image of the image to be tested.
  • the component missing detecting system of the present invention has a one-to-one correspondence with the component missing detecting method of the present invention, and the technical features and advantageous effects thereof in the embodiment of the above component missing detecting method are all applicable to the embodiment of the component missing detecting system.

Landscapes

  • General Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Immunology (AREA)
  • Health & Medical Sciences (AREA)
  • Biochemistry (AREA)
  • General Health & Medical Sciences (AREA)
  • Chemical & Material Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Pathology (AREA)
  • Analytical Chemistry (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Theoretical Computer Science (AREA)
  • Signal Processing (AREA)
  • Quality & Reliability (AREA)
  • Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
  • Spectrometry And Color Measurement (AREA)
  • Image Processing (AREA)
  • Image Analysis (AREA)

Abstract

一种元件漏检方法和系统，获取待测元件所在区域的制版图像和待测元件所在区域的待测图像（S101），再获取制版图像的HSV图像和待测图像的HSV图像（S102），根据待测元件的主体颜色的色调值和饱和度值以及预设容差值，统计制版图像的HSV图像中与主体颜色相匹配的第一像素点的个数以及待测图像的HSV图像中与主体颜色相匹配的第二像素点的个数，并根据第一像素点的个数和第二像素点的个数的比值与第一预设值的大小来确定待测元件是否漏件。该方法和系统将图像转换到HSV颜色空间，利用HSV图像中的色调值和饱和度值以及容差值来计算相匹配颜色的像素点数，舍弃了明度值，减少了光照变化对相匹配颜色的像素的影响，提高了元件漏检方法的准确度。

Description

元件漏检方法和系统 技术领域
本发明涉及自动光学检测领域，特别是涉及元件漏检方法和系统。
背景技术
当前，对PCB电路板(印制电路板)进行检测，使用较多的是AOI(Automatic Optic Inspection，自动光学检测)系统，自动光学检测是工业制作过程的必要环节，利用光学方式取得成品的表面状态，以影像处理来检测异物或表面瑕疵。电子元件的错、漏、反检测是电路板缺陷检测领域中的一种常见应用，机器通过摄像头自动扫描电路板获取图像，提取每个电子元件的局部图像，并通过图像处理技术，判断电子元件是否存在错、漏、反缺陷，最后将疑似缺陷的元件显示或标记出来，方便查看与检修。
在传统的AOI系统中，电子元件的漏件检测主要是通过对比对应位置的像素颜色值的差别来实现的，但是这种基于颜色对比的方法，比较容易受到光照变化的影响，从而产生误判。
发明内容
基于此，有必要针对现有的元件漏检检测方法容易发生误判的问题，提供一种元件漏检方法和系统。
一种元件漏检方法，包括以下步骤：
获取待测元件所在区域的制版图像和待测元件所在区域的待测图像；
获取制版图像的HSV图像，获取待测图像的HSV图像；
根据待测元件的主体颜色的色调值和饱和度值以及预设容差值，统计制版图像的HSV图像中与主体颜色相匹配的第一像素点的个数，其中，主体颜色为待测元件的各颜色中占比最大的一种颜色；
根据主体颜色的色调值和饱和度值以及预设容差值，统计待测图像的HSV图像中与主体颜色相匹配的第二像素点的个数；
获取第一像素点的个数和第二像素点的个数的比值，将比值与第一预设值相比较，若 比值小于第一预设值，则判定待测元件在待测图像中漏件。
一种元件漏检系统，包括以下单元：
第一获取单元，用于获取待测元件所在区域的制版图像和待测元件所在区域的待测图像；
第二获取单元，用于获取制版图像的HSV图像，获取待测图像的HSV图像；
第一统计单元，用于根据待测元件的主体颜色的色调值和饱和度值以及预设容差值，统计制版图像的HSV图像中与主体颜色相匹配的第一像素点的个数，其中，主体颜色为待测元件的各颜色中占比最大的一种颜色；
第二统计单元，用于根据主体颜色的色调值和饱和度值以及预设容差值，统计待测图像的HSV图像中与主体颜色相匹配的第二像素点的个数；
比较单元，用于获取第一像素点的个数和第二像素点的个数的比值，将比值与第一预设值相比较，若比值小于第一预设值，则判定待测元件在待测图像中漏件。
根据上述本发明的方案，其是先分别获取待测元件所在区域的制版图像和待测元件所在区域的待测图像，再分别获取制版图像的HSV图像和待测图像的HSV图像，根据待测元件的主体颜色的色调值和饱和度值以及预设容差值，统计制版图像的HSV图像中的第一像素点的个数以及待测图像的HSV图像中的第二像素点的个数，并根据第一像素点的个数和第二像素点的个数的比值与第一预设值的大小来确定待测元件是否在待测图像中漏件。此方案中将图像转换到HSV颜色空间，利用HSV图像中的色调值和饱和度值以及容差值来计算与主体颜色相匹配的像素点数，舍弃了明度值，减少了光照变化对相匹配颜色的像素的影响，提高了元件漏检方法的准确度。
附图说明
图1是其中一个实施例中元件漏检方法的流程示意图；
图2是其中一个实施例中相匹配颜色像素个数-容差的关系曲线图；
图3是其中一个实施例中元件漏检系统的结构示意图；
图4是其中一个实施例中元件漏检系统的结构示意图；
图5是其中一个实施例中元件漏检系统的结构示意图；
图6是其中一个实施例中元件漏检系统的结构示意图。
具体实施方式
为使本发明的目的、技术方案及优点更加清楚明白，以下结合附图及实施例，对本发明进行进一步的详细说明。应当理解，此处所描述的具体实施方式仅仅用以解释本发明，并不限定本发明的保护范围。
参见图1所示，为本发明的元件漏检方法的实施例。该实施例中的元件漏检方法包括如下步骤：
步骤S101：获取待测元件所在区域的制版图像和待测元件所在区域的待测图像；
待测元件可以为PCB板上的电子元器件，如电阻、电感、电容等；制版图像可以是PCB板图像中对应未漏件的待测元件所在区域的部分PCB板图像；待测图像可以是对应待测元件所在区域的部分PCB板图像，是对PCB板进行实际拍摄得到的，但未确定待测元件是否漏件；
步骤S102：获取制版图像的HSV图像，获取待测图像的HSV图像；
制版图像的HSV图像是制版图像在H(色调)、S(饱和度)、V(明度)三个通道的图像，制版图像的HSV图像中的各像素点是与制版图像的各像素点相对应的；待测图像的HSV图像是待测图像在H(色调)、S(饱和度)、V(明度)三个通道的图像，待测图像的HSV图像中的各像素点是与待测图像的各像素点相对应的；
步骤S103：根据待测元件的主体颜色的色调值和饱和度值以及预设容差值，统计制版图像的HSV图像中与主体颜色相匹配的第一像素点的个数，其中，主体颜色为待测元件的各颜色中占比最大的一种颜色；
步骤S104：根据主体颜色的色调值和饱和度值以及预设容差值，统计待测图像的HSV图像中与主体颜色相匹配的第二像素点的个数；
步骤S105：获取第一像素点的个数和第二像素点的个数的比值，将比值与第一预设值相比较，若比值小于第一预设值，则判定待测元件在待测图像中漏件。
在本实施例中，其是先分别获取待测元件所在区域的制版图像和待测元件所在区域的待测图像，再分别获取制版图像的HSV图像和待测图像的HSV图像，根据待测元件的主体颜色的色调值和饱和度值以及预设容差值，统计制版图像的HSV图像中的第一像素点的个数以及待测图像的HSV图像中的第二像素点的个数，并根据第一像素点的个数和第 二像素点的个数的比值与第一预设值的大小来确定待测元件是否在待测图像中漏件。此方案中将图像转换到HSV颜色空间，利用HSV图像中的色调值和饱和度值以及容差值来计算与主体颜色相匹配的像素点数，舍弃了明度值，减少了光照变化对相匹配颜色的像素的影响，提高了元件漏检方法的准确度。
另外，在将比值与第一预设值相比较后，若比值大于或等于第一预设值，则判定待测元件在待测图像中未漏件。
应当理解，其中所使用的术语“第一”、“第二”等在本文中仅用于区分对象，但这些对象不受这些术语限制。例如，在不脱离本发明的范围的情况下，可以将第一像素点称为第二像素点，将第二像素点称为第一像素点。
在其中一个实施例中，获取待测元件的制版图像之后还包括以下步骤：
根据主体颜色的颜色像素值，在不同容差值下，统计制版图像中与主体颜色相匹配的第三像素点的个数，获取第三像素点个数-容差的关系曲线，将关系曲线中第三像素点的个数变化最缓慢的点对应的容差作为预设的容差值。
在本实施例中，预设容差值是根据第三像素点个数-容差的关系曲线来确定的。颜色的容差值对漏件检测非常重要，如果容差设置过小，在漏件检测时会因为获取的第一像素点过少而容易发生误判，如果容差设置过大，在漏件检测时会因为获取的第一像素点过多而容易发生误判，因此需要设置合适的容差值，一般选取第三像素点个数-容差的关系曲线中斜率最小时对应的容差值，即与主体颜色相匹配的颜色像素个数变化最缓慢时对应的容差值。此外，此处的颜色像素值主要针对的是图像中各像素点的RGB像素值。
在其中一个实施例中，在统计制版图像的HSV图像中与主体颜色相匹配的第一像素点的个数的步骤之后还包括以下步骤：
若第一像素点所覆盖的图像大小与制版图像的HSV图像中待测元件图像大小的比值超过第二预设值，则将预设容差值减小预设步长，并返回至统计制版图像的HSV图像中的第一像素点的个数的步骤。
在本实施例中，若第一像素点所覆盖的图像大小与制版图像的HSV图像中待测元件图像大小的比值超过第二预设值，代表预设容差值过大，第一像素点所覆盖的图像区域也过大，会影响元件漏检的准确性，因此此时需要适当减小预设容差值，并重新统计第一像素点的个数以及第二像素点的个数，第二预设值和预设步长可以根据实际情况自由调整。
在其中一个实施例中，统计制版图像的HSV图像中与主体颜色相匹配的第一像素点的个数的步骤之前包括以下步骤：
在制版图像的HSV图像中剔除饱和度小于预设临界值的像素区域；
统计待测图像的HSV图像中与主体颜色相匹配的第一像素点的个数的步骤之前包括以下步骤：
在待测图像的HSV图像中剔除饱和度小于预设临界值的像素区域。
在本实施例中，剔除了饱和度小于预设临界值的像素区域，这是因为饱和度较低的颜色本身就比较不稳定，不利于漏检判断，因此将小于预设临界值的像素区域剔除，预设临界值可以根据实际情况自由调整。
在其中一个实施例中，根据待测元件的主体颜色的色调值和饱和度值以及预设容差值，统计制版图像的HSV图像中与主体颜色相匹配的第一像素点的个数的步骤包括以下步骤：
通过
Figure PCTCN2016112886-appb-000001
统计第一像素点的个数；
式中，Hx,y表示制版图像的HSV图像的(x,y)坐标处的色调值，Sx,y表示制版图像的HSV图像的(x,y)坐标处的饱和度值，C表示预设容差值，Htarget和Starget分别表示主体颜色的色调值和饱和度值；
根据色调值和饱和度值以及预设容差值，统计待测图像的HSV图像中与主体颜色相匹配的第二像素点的步骤包括以下步骤：
通过
Figure PCTCN2016112886-appb-000002
统计第二像素点的个数；
式中，Hi,j表示待测图像的HSV图像的(i,j)坐标处的色调值，Si,j表示待测图像的HSV图像的(i,j)坐标处的饱和度值。
在本实施例中，根据由主体颜色的色调值和饱和度值以及预设容差值确定的公式来统计制版图像的HSV图像中的第一像素点和待测图像的HSV图像中的第二像素点，依据公式在HSV图像中可以非常方便的选出符合条件的相匹配颜色的像素点并统计相应的个数，色调值即HSV图像在H通道的数值，饱和度值即HSV图像在S通道的数值。
在一个具体的实施例中，元件漏检方法可以分为两个部分，一个是制版过程，另一个是漏检过程，制版过程主要是针对制版图像，而漏检过程主要是针对待测图像；
在制版过程，获取待测元件的制版图像；
计算制版图像中在不同容差值下与待测元件的主体颜色相匹配的颜色的像素个数，获取相匹配颜色像素个数-容差的关系曲线，将关系曲线中相匹配颜色像素个数变化最缓慢的点对应的容差作为预设容差值，如图2所示，横坐标为容差值，纵坐标为相匹配颜色像素个数，容差范围可以是0至50，容差值为20时相匹配颜色像素个数的增长最小，因此可以选择容差值为20，另外，在获取曲线时，容差范围可以根据需要进行调整；
接着获取制版图像的HSV图像，将制版图像从RGB颜色空间转换到HSV颜色空间，其转换公式如下：
Figure PCTCN2016112886-appb-000003
Figure PCTCN2016112886-appb-000004
Figure PCTCN2016112886-appb-000005
V＝Cmax
由于元件的像素值容易受到光照的影响，不同光照条件下面的V(明度)通道的差别较大，因此，为了降低光照的影响，舍弃掉V通道的信息，只取H(色调)通道、S(饱和度)通道的图像信息进行颜色信息的对比。同时因为饱和度较低的颜色本身就比较不稳定，再将图像中饱和度小于30的像素区域剔除，不参与颜色信息的比较；
然后根据待测元件的主体颜色的色调值和饱和度值以及预设容差值，统计制版图像的HSV图像中与主体颜色相匹配的第一像素点的个数；
统计第一像素点的个数时使用的公式为：
Figure PCTCN2016112886-appb-000006
式中，Hx,y表示制版图像的HSV图像的H通道中(x,y)坐标处的色调值，Sx,y表示制版图像的HSV图像的S通道中(x,y)坐标处的饱和度值，C表示预设容差值(20)，Htarget和Starget分别表示主体颜色的色调值和饱和度值；
在统计第一像素点的个数之后，如果第一像素点所覆盖的图像区域大小与制版图像的HSV图像中待测元件图像大小的比值超过第二预设值，则代表预设容差值(20)过大，需要将预设容差值减小预设差值，如预设差值为1，并返回至统计第一像素点的个数的步骤，重新统计第一像素点的个数。
制版过程的步骤在对单种元件进行漏检的过程中只需进行一次，在对不同种类、不同类型的元件进行漏件时才需要重新进行制版过程的步骤。
在漏检过程，获取待测元件所在区域的待测图像，获取待测图像的HSV图像；
根据在制版过程已经确定的待测元件的主体颜色的色调值和饱和度值以及预设容差值，统计待测图像的HSV图像中与主体颜色相匹配的第二像素点的个数；
漏检过程的上述步骤的具体过程与制版过程中对制版图像的处理过程相类似，在此不再赘述；
在统计完第一像素点和第二像素点的个数后，获取第一像素点的个数和第二像素点的个数的比值，将比值与第一预设值相比较，若比值大于或等于第一预设值，则判定待测元件在待测图像中未漏件；若比值小于第一预设值，则判定待测元件在待测图像中漏件；
第一预设值可以为50％，还可以根据漏件检测的严格程度适当调整该第一预设值。
本发明提供了一种元件漏检方法，将图像转换到HSV颜色空间，利用HSV图像中的色调值和饱和度值以及容差值来计算相匹配颜色的像素点数，以此为依据进行漏件判断，在计算相匹配颜色的像素点数时舍弃了明度值，减少了光照变化对相匹配颜色的像素的影响，提高了元件漏检方法的准确度。
根据上述元件漏检方法，本发明还提供一种元件漏检系统，以下就本发明的元件漏检系统的实施例进行详细说明。
参见图3所示，为本发明的元件漏检系统的实施例。该实施例中的元件漏检系统包括以下单元：
第一获取单元201，用于获取待测元件所在区域的制版图像和待测元件所在区域的待测图像；
第二获取单元202，用于获取所述制版图像的HSV图像，获取所述待测图像的HSV图像；
第一统计单元203，用于根据待测元件的主体颜色的色调值和饱和度值以及预设容差值，统计制版图像的HSV图像中与主体颜色相匹配的第一像素点的个数，其中，主体颜色为待测元件的各颜色中占比最大的一种颜色；
第二统计单元204，用于根据主体颜色的色调值和饱和度值以及预设容差值，统计待测图像的HSV图像中与主体颜色相匹配的第二像素点的个数；
比较单元205，用于获取第一像素点的个数和第二像素点的个数的比值，将比值与第一预设值相比较，若比值小于第一预设值，则判定待测元件在待测图像中漏件。
在其中一个实施例中，如图4所示，元件漏检系统还包括容差值获取单元206，容差值获取单元206用于根据所述主体颜色的颜色像素值，在不同容差值下，统计所述制版图像中与所述主体颜色相匹配的第三像素点的个数，获取第三像素点个数-容差的关系曲线，将所述关系曲线中所述第三像素点的个数变化最缓慢的点对应的容差作为所述预设的容差值。
在其中一个实施例中，如图5所示，元件漏检系统还包括容差值调整单元207，容差值调整单元207用于在所述第一像素点所覆盖的图像区域大小与所述制版图像的HSV图像中待测元件图像大小的比值超过预设第二比值时，将所述预设容差值减小预设步长；
第一统计单元203还用于根据所述主体颜色的色调值和饱和度值以及调整后的预设容差值统计所述第一像素点的个数；
第二统计单元204还用于根据所述主体颜色的色调值和饱和度值以及调整后的预设容差值统计所述第二像素点的个数。
在其中一个实施例中，如图6所示，元件漏检系统还包括预处理单元208，预处理单元208用于在统计所述第一像素点的个数之前，在所述制版图像的HSV图像中剔除饱和度小于预设临界值的像素区域；
预处理单元208还用于在统计所述第二像素点的个数之前，在所述待测图像的HSV图像中剔除饱和度小于所述预设临界值的像素区域。
在其中一个实施例中，第一统计单元203通过
Figure PCTCN2016112886-appb-000007
统计第一像素点的个数；
式中，Hx,y表示制版图像的HSV图像的(x,y)坐标处的色调值，Sx,y表示制版图像的HSV图像的(x,y)坐标处的饱和度值，C表示预设容差值，Htarget和Starget分别表示主体颜色的色调值和饱和度值；
第二统计单元204通过
Figure PCTCN2016112886-appb-000008
统计第二像素点的个数；
式中，Hi,j表示待测图像的HSV图像的(i,j)坐标处的色调值，Si,j表示待测图像的HSV图像的(i,j)坐标处的饱和度值。
本发明的元件漏检系统与本发明的元件漏检方法一一对应，在上述元件漏检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漏检系统的实施例中。
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. 一种元件漏检方法，其特征在于，包括以下步骤：
    获取待测元件所在区域的制版图像和所述待测元件所在区域的待测图像；
    获取所述制版图像的HSV图像，获取所述待测图像的HSV图像；
    根据所述待测元件的主体颜色的色调值和饱和度值以及预设容差值，统计所述制版图像的HSV图像中与所述主体颜色相匹配的第一像素点的个数，其中，所述主体颜色为所述待测元件的各颜色中占比最大的一种颜色；
    根据所述主体颜色的色调值和饱和度值以及预设容差值，统计所述待测图像的HSV图像中与所述主体颜色相匹配的第二像素点的个数；
    获取所述第一像素点的个数和所述第二像素点的个数的比值，将所述比值与第一预设值相比较，若所述比值小于所述第一预设值，则判定所述待测元件在所述待测图像中漏件。
  2. 根据权利要求1所述的元件漏检方法，其特征在于，所述获取待测元件的制版图像之后还包括以下步骤：
    根据所述主体颜色的颜色像素值，在不同容差值下，统计所述制版图像中与所述主体颜色相匹配的第三像素点的个数，获取第三像素点个数-容差的关系曲线，将所述关系曲线中所述第三像素点的个数变化最缓慢的点对应的容差作为所述预设的容差值。
  3. 根据权利要求1所述的元件漏检方法，其特征在于，在统计所述制版图像的HSV图像中与所述主体颜色相匹配的第一像素点的个数的步骤之后还包括以下步骤：
    若所述第一像素点所覆盖的图像大小与所述制版图像的HSV图像中待测元件图像大小的比值超过第二预设值，则将所述预设容差值减小预设步长，并返回至统计所述制版图像的HSV图像中的第一像素点的个数的步骤。
  4. 根据权利要求1所述的元件漏检方法，其特征在于：
    所述统计所述制版图像的HSV图像中与所述主体颜色相匹配的第一像素点的个数的步骤之前还包括以下步骤：
    在所述制版图像的HSV图像中剔除饱和度小于预设临界值的像素区域；
    所述统计所述待测图像的HSV图像中与所述主体颜色相匹配的第二像素点的个数的步骤之前还包括以下步骤：
    在所述待测图像的HSV图像中剔除饱和度小于所述预设临界值的像素区域。
  5. 根据权利要求1至4中任意一项所述的元件漏检方法，其特征在于：
    所述根据所述待测元件的主体颜色的色调值和饱和度值以及预设容差值，统计所述制版图像的HSV图像中与所述主体颜色相匹配的第一像素点的个数的步骤包括以下步骤：
    通过
    Figure PCTCN2016112886-appb-100001
    统计所述第一像素点的个数；
    式中，Hx,y表示所述制版图像的HSV图像的(x,y)坐标处的色调值，Sx,y表示所述制版图像的HSV图像的(x,y)坐标处的饱和度值，C表示预设容差值，Htarget和Starget分别表示所述主体颜色的色调值和饱和度值；
    所述根据所述主体颜色的色调值和饱和度值以及预设容差值，统计所述待测图像的HSV图像中与所述主体颜色相匹配的第二像素点的个数的步骤包括以下步骤：
    通过
    Figure PCTCN2016112886-appb-100002
    统计所述第二像素点的个数；
    式中，Hi,j表示所述待测图像的HSV图像的(i,j)坐标处的色调值，Si,j表示所述待测图像的HSV图像的(i,j)坐标处的饱和度值。
  6. 一种元件漏检系统，其特征在于，包括以下单元：
    第一获取单元，用于获取待测元件所在区域的制版图像和所述待测元件所在区域的待测图像；
    第二获取单元，用于获取所述制版图像的HSV图像，获取所述待测图像的HSV图像；
    第一统计单元，用于根据所述待测元件的主体颜色的色调值和饱和度值以及预设容差值，统计所述制版图像的HSV图像中与所述主体颜色相匹配的第一像素点的个数，其中，所述主体颜色为所述待测元件的各颜色中占比最大的一种颜色；
    第二统计单元，用于根据所述主体颜色的色调值和饱和度值以及预设容差值，统计所述待测图像的HSV图像中与所述主体颜色相匹配的第二像素点的个数；
    比较单元，用于获取所述第一像素点的个数和所述第二像素点的个数的比值，将所述比值与第一预设值相比较，若所述比值小于所述第一预设值，则判定所述待测元件在所述待测图像中漏件。
  7. 根据权利要求6所述的元件漏检系统，其特征在于，还包括容差值获取单元，所述容差值获取单元用于根据所述主体颜色的颜色像素值，在不同容差值下，统计所述制版图像中与所述主体颜色相匹配的第三像素点的个数，获取第三像素点个数-容差的关系曲线， 将所述关系曲线中所述第三像素点的个数变化最缓慢的点对应的容差作为所述预设的容差值。
  8. 根据权利要求6所述的元件漏检系统，其特征在于，还包括容差值调整单元，所述容差值调整单元用于在所述第一像素点所覆盖的图像区域大小与所述制版图像的HSV图像中待测元件图像大小的比值超过预设第二比值时，将所述预设容差值减小预设步长；
    所述第一统计单元还用于根据所述主体颜色的色调值和饱和度值以及调整后的预设容差值统计所述第一像素点的个数；
    所述第二统计单元还用于根据所述主体颜色的色调值和饱和度值以及调整后的预设容差值统计所述第二像素点的个数。
  9. 根据权利要求6所述的元件漏检系统，其特征在于，还包括预处理单元；
    所述预处理单元用于在统计所述第一像素点的个数之前，在所述制版图像的HSV图像中剔除饱和度小于预设临界值的像素区域；
    所述预处理单元还用于在统计所述第二像素点的个数之前，在所述待测图像的HSV图像中剔除饱和度小于所述预设临界值的像素区域。
  10. 根据权利要求6至9中任意一项所述的元件漏检系统，其特征在于:
    所述第一统计单元通过
    Figure PCTCN2016112886-appb-100003
    统计所述第一像素点的个数；
    式中，Hx,y表示所述制版图像的HSV图像的(x,y)坐标处的色调值，Sx,y表示所述制版图像的HSV图像的(x,y)坐标处的饱和度值，C表示预设容差值，Htarget和Starget分别表示所述主体颜色的色调值和饱和度值；
    所述第二统计单元通过
    Figure PCTCN2016112886-appb-100004
    统计所述第二像素点的个数；
    式中，Hi,j表示所述待测图像的HSV图像的(i,j)坐标处的色调值，Si,j表示所述待测图像的HSV图像的(i,j)坐标处的饱和度值。
PCT/CN2016/112886 2016-04-21 2016-12-29 元件漏检方法和系统 Ceased WO2017181722A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201610257944.6 2016-04-21
CN201610257944.6A CN105957065A (zh) 2016-04-21 2016-04-21 元件漏检方法和系统

Publications (1)

Publication Number Publication Date
WO2017181722A1 true WO2017181722A1 (zh) 2017-10-26

Family

ID=56915512

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2016/112886 Ceased WO2017181722A1 (zh) 2016-04-21 2016-12-29 元件漏检方法和系统

Country Status (2)

Country Link
CN (1) CN105957065A (zh)
WO (1) WO2017181722A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110310341A (zh) * 2019-07-02 2019-10-08 广州视源电子科技股份有限公司 颜色算法中默认参数的生成方法、装置、设备和存储介质

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105957065A (zh) * 2016-04-21 2016-09-21 广州视源电子科技股份有限公司 元件漏检方法和系统
CN106529572B (zh) * 2016-10-14 2019-07-09 广州视源电子科技股份有限公司 色环电阻的检测方法、装置和自动光学检测系统
CN107330879A (zh) * 2017-06-21 2017-11-07 广州视源电子科技股份有限公司 一种器件的检查方法、装置、设备及存储介质
CN114627053B (zh) * 2022-02-11 2025-12-02 纯米科技(上海)股份有限公司 检漏方法、生产线工作方法、装置、系统和存储介质

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20090296082A1 (en) * 2008-05-28 2009-12-03 Asustek Computer Inc. Circuit board detecting device and method thereof
CN102301225A (zh) * 2009-01-31 2011-12-28 玛机统丽公司 通孔检查装置
CN104504703A (zh) * 2014-12-20 2015-04-08 河南机电高等专科学校 一种基于片式元器件smt焊点彩色图像分割方法
CN104504375A (zh) * 2014-12-18 2015-04-08 广州视源电子科技股份有限公司 一种pcb元件的识别方法及装置
CN104899871A (zh) * 2015-05-15 2015-09-09 广东工业大学 一种ic元件焊点空焊检测方法
CN105957065A (zh) * 2016-04-21 2016-09-21 广州视源电子科技股份有限公司 元件漏检方法和系统

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2007074770A1 (ja) * 2005-12-26 2007-07-05 Nikon Corporation 画像解析によって欠陥検査を行う欠陥検査装置
CN103024434B (zh) * 2012-12-20 2014-12-24 广州视源电子科技股份有限公司 一种基于图像匹配的自动测试系统
CN103808731B (zh) * 2014-01-20 2016-06-29 北京大恒图像视觉有限公司 一种在印刷品检测系统中使用的缺陷检测方法
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

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20090296082A1 (en) * 2008-05-28 2009-12-03 Asustek Computer Inc. Circuit board detecting device and method thereof
CN102301225A (zh) * 2009-01-31 2011-12-28 玛机统丽公司 通孔检查装置
CN104504375A (zh) * 2014-12-18 2015-04-08 广州视源电子科技股份有限公司 一种pcb元件的识别方法及装置
CN104504703A (zh) * 2014-12-20 2015-04-08 河南机电高等专科学校 一种基于片式元器件smt焊点彩色图像分割方法
CN104899871A (zh) * 2015-05-15 2015-09-09 广东工业大学 一种ic元件焊点空焊检测方法
CN105957065A (zh) * 2016-04-21 2016-09-21 广州视源电子科技股份有限公司 元件漏检方法和系统

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110310341A (zh) * 2019-07-02 2019-10-08 广州视源电子科技股份有限公司 颜色算法中默认参数的生成方法、装置、设备和存储介质

Also Published As

Publication number Publication date
CN105957065A (zh) 2016-09-21

Similar Documents

Publication Publication Date Title
CN107945184B (zh) 一种基于彩色图像分割和梯度投影定位的贴装元件检测方法
CN106651857B (zh) 一种印刷电路板贴片缺陷检测方法
WO2017181722A1 (zh) 元件漏检方法和系统
WO2018068417A1 (zh) 元件缺陷检测方法和系统
CN107093174B (zh) 一种pcb设计缺陷检测方法
CN106370671A (zh) 基于机器视觉的pcb上元器件检测系统及方法
WO2017181724A1 (zh) 电子元件漏件检测方法和系统
WO2018010391A1 (zh) 一种板卡的检测方法及装置
WO2017177717A1 (zh) 基于颜色和梯度的元件定位方法和系统
CN108827979A (zh) 一种模组镜头外观检测方法
CN107271445B (zh) 一种缺陷检测方法及装置
WO2017071406A1 (zh) 金针类元件的引脚检测方法和系统
WO2020130786A1 (en) A method of analyzing visual inspection image of a substrate for corrosion determination
CN112014407A (zh) 一种集成电路晶圆表面缺陷检测的方法
CN103500457B (zh) 一种视频图像偏色检测的方法
TWI496111B (zh) 針腳彎曲檢測方法
CN110853031A (zh) 汽车组合仪表指示灯点亮的排他检测方法
CN101666621B (zh) 一种与光照无关的标记点提取方法
WO2018068414A1 (zh) 色环电阻的检测方法、装置和自动光学检测系统
KR101383827B1 (ko) 인쇄회로기판의 솔더링 영역 자동검출 시스템 및 방법
Zhang et al. Defect detection of mobile phone screen based on improved difference image method
WO2017080295A1 (zh) 元件的定位方法和系统
CN116843659B (zh) 一种基于红外图像的电路板故障自动检测方法
CN103137218B (zh) 指针的调校方法和装置
TWI634308B (zh) 二維檢測錫膏印刷的定位方法

Legal Events

Date Code Title Description
NENP Non-entry into the national phase

Ref country code: DE

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

Ref document number: 16899301

Country of ref document: EP

Kind code of ref document: A1

122 Ep: pct application non-entry in european phase

Ref document number: 16899301

Country of ref document: EP

Kind code of ref document: A1