CN112798613A - LCD foreign matter defect color imaging detection method, electronic equipment and storage medium - Google Patents
LCD foreign matter defect color imaging detection method, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN112798613A CN112798613A CN202110344667.3A CN202110344667A CN112798613A CN 112798613 A CN112798613 A CN 112798613A CN 202110344667 A CN202110344667 A CN 202110344667A CN 112798613 A CN112798613 A CN 112798613A
- Authority
- CN
- China
- Prior art keywords
- channel
- lcd
- foreign matter
- lcd module
- image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- 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
- G01N21/94—Investigating contamination, e.g. dust
-
- 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
-
- 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
- G01N2021/8854—Grading and classifying of flaws
-
- 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
Landscapes
- Chemical & Material Sciences (AREA)
- Biochemistry (AREA)
- Pathology (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Immunology (AREA)
- Analytical Chemistry (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The application relates to a color imaging detection method for LCD foreign matter defects. The method comprises the following steps: shooting the LCD module by a color industrial camera under a preset light source to obtain an image of the LCD module; extracting a region of interest of the LCD module image to obtain an LCD image to be detected, wherein the LCD image to be detected comprises at least one response bright spot; performing RGB channel identification on an LCD image to be detected to obtain channel gray values corresponding to at least one response bright point in RGB three channels respectively; determining a threshold segmentation channel according to the primary color of the first light wave; and performing threshold segmentation on the channel gray value corresponding to the at least one response bright point by using a gray threshold in the threshold segmentation channel to obtain a foreign matter attribute classification corresponding to the at least one response bright point in the LCD module image, wherein the foreign matter attribute classification comprises dust and foreign matter defects. The scheme that this application provided can promote the degree of accuracy that LCD module foreign matter defect detected, improves detection efficiency.
Description
Technical Field
The present disclosure relates to defect detection technologies, and particularly to a color imaging detection method for detecting defects of LCD foreign objects, an electronic device, and a storage medium.
Background
The LCD module is usually a multi-layer structure, and during the process of manufacturing the LCD module, there are various processes of film sticking and pressing, and some foreign matters such as dust and impurities are inevitably introduced during the process of manufacturing, so that the finished product of the LCD module has defects. The traditional solution is to adopt a manual detection mode, however, with the rapid development of the machine vision industry, the machine vision defect detection has replaced the old manual detection mode in various industries, and the detection efficiency is greatly improved. Machine vision defect detection usually utilizes the black and white industry camera of high resolution to carry out imaging detection to LCD module picture, shoots two product pictures respectively, and one is the formation of image picture of LCD module when the backlight is lighted, and another is the LCD module formation of image picture that the surface was polished, thereby distinguishes and discerns the foreign matter defect through the position of bright spot between detection algorithm contrast two images.
In the prior art, in patent publication No. CN110445921A (a mobile phone screen backlight foreign matter defect diagnosis method and device based on machine vision), a foreign matter defect diagnosis method is proposed, in which a dust side light device is designed for removing dust interference factors, so as to eliminate the interference of dust on the backlight foreign matter defect, and a set of detection algorithm is designed for detecting the whole backlight foreign matter defect to identify whether the mobile phone screen contains defects.
The above prior art has the following disadvantages:
when the dust side light device brightens and images dust, foreign matter defects are easily imaged, and the defects are possibly judged as surface dust by mistake and filtered out, so that the problem of missing detection of the foreign matter defects is caused. Therefore, it is required to develop a method of distinguishing surface dust and foreign matter defects from RGB values in an imaged image.
Disclosure of Invention
In order to overcome the problems in the related art, the application provides the LCD foreign matter defect color imaging detection method, and the LCD foreign matter defect color imaging detection method can improve the accuracy of the detection of the foreign matter defects of the LCD module and improve the detection efficiency.
The application provides a LCD foreign matter defect color imaging detection method in a first aspect, which comprises the following steps:
shooting the LCD module by a color industrial camera under a preset light source to obtain an LCD module image, wherein the preset light source comprises a backlight light source and a surface light source; the surface light source emits a first light wave which is any one of three primary color lights; the backlight source emits a second light wave, and the second light wave comprises at least one primary color light different from the first light wave;
extracting a region of interest of the LCD module image to obtain an LCD image to be detected, wherein the LCD image to be detected comprises at least one response bright spot;
performing RGB channel identification on an LCD image to be detected to obtain channel gray values corresponding to at least one response bright point in RGB three channels respectively;
determining a threshold segmentation channel according to the primary color of the first light wave;
and performing threshold segmentation on the channel gray value corresponding to the at least one response bright point by using a gray threshold in the threshold segmentation channel to obtain a foreign matter attribute classification corresponding to the at least one response bright point in the LCD module image, wherein the foreign matter attribute classification comprises dust and foreign matter defects.
In one embodiment, determining a threshold split channel from the primary colors of the first light wave comprises:
if the second light wave is light combined by three primary colors, determining a threshold segmentation channel as a channel with a gray value of zero in RGB values corresponding to the primary colors of the first light wave;
if the second light wave is light combined by any two primary colors, determining a threshold segmentation channel as a channel with zero gray value in RGB values corresponding to the primary colors of the first light wave and non-zero gray value in RGB values corresponding to the colors of the second light wave;
and if the second light wave is a primary light wave, determining that the threshold segmentation channel is the channel with the highest gray value in RGB values corresponding to the primary color of the second light wave.
In one embodiment, the gray threshold is determined from a range of values of channel gray values in the thresholded divided channel for at least one responsive bright spot;
performing threshold segmentation on the channel gray value corresponding to at least one response bright point by using a gray threshold in a threshold segmentation channel, wherein the threshold segmentation comprises the following steps:
and comparing the gray value of each channel with the gray threshold value respectively.
In one embodiment, obtaining at least one corresponding foreign object attribute classification for the response light in the LCD module image comprises:
if the gray value of the current channel is smaller than the gray threshold, judging that the foreign matter attribute of the response bright point corresponding to the gray value of the current channel is classified as dust;
and if the gray value of the current channel is greater than the gray threshold, judging that the foreign matter attribute of the response bright point corresponding to the gray value of the current channel is classified as a foreign matter defect.
In one embodiment, after obtaining the attribute classification of the foreign object corresponding to at least one response bright point in the LCD module image, the method includes:
and filtering out the response bright spots judged as dust in the threshold segmentation channel.
In one embodiment, the region of interest extraction of the LCD module image comprises:
and extracting the region of interest of the LCD module image through a threshold segmentation algorithm.
In one embodiment, the method for photographing the LCD module by the color industrial camera under the preset light source includes:
the LCD module is lightened through the backlight light source and the surface polishing light source;
the surface light source irradiates the LCD module with an irradiation angle alpha, the irradiation angle is an included angle formed by light waves emitted by the surface light source and a normal line of a horizontal plane, and alpha is larger than zero.
In one embodiment, the color industrial camera has a three primary color filtering function;
shoot LCD module under predetermineeing the light source through colored industry camera, include:
the screen surface front view of the LCD module is photographed by a color industrial camera.
A second aspect of the present application provides an electronic device, comprising:
a processor; and
a memory having executable code stored thereon, which when executed by the processor, causes the processor to perform the method as described above.
A third aspect of the application provides a non-transitory machine-readable storage medium having stored thereon executable code which, when executed by a processor of an electronic device, causes the processor to perform a method as described above.
The technical scheme provided by the application can comprise the following beneficial effects:
the method comprises the steps of shooting an LCD module under a preset light source through a color industrial camera, wherein the preset light source comprises a backlight light source and a surface light source, the surface light source emits first light waves which are any one of three primary color light, the backlight light source emits second light waves which comprise at least one primary color light different from the first light waves, region-of-interest extraction is carried out on an LCD module image, the extracted LCD to-be-detected image comprises at least one response bright spot, RGB channel recognition is carried out on the LCD to-be-detected image, channel gray values of the response bright spot in three channels are obtained, threshold segmentation operation is carried out on the response bright spot in a threshold segmentation channel determined according to the primary color of the first light waves, and foreign matter attribute classification of the response bright spot is obtained. Compared with the prior art, this scheme shoots the LCD module under the specific environment that the light wave that the light source sent is polished to the background light source and surface has obvious difference, polish foreign matter defect in the LCD module and LCD module surface dust and make foreign matter defect and dust all show as the response bright spot in the LCD module image after the formation of image, response bright spot after extracting carries out RGB channel identification, confirm the foreign matter type that the response bright spot corresponds after carrying out the threshold value to the grey value of response bright spot and cutting apart in the threshold value cut-apart passageway, thereby reach the effect of distinguishing surface dust and the interior foreign matter defect of module, promote the detection accuracy, it is low to detect the implementation degree of difficulty, improve detection efficiency, reduce detection cost, it is strong to the compatibility of foreign matter detection.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application.
Drawings
The foregoing and other objects, features and advantages of the application will be apparent from the following more particular descriptions of exemplary embodiments of the application, as illustrated in the accompanying drawings wherein like reference numbers generally represent like parts throughout the exemplary embodiments of the application.
FIG. 1 is a schematic flow chart of a first embodiment of a color imaging detection method for detecting a foreign object defect in an LCD according to an embodiment of the present application;
FIG. 2 is a schematic flow chart of a second embodiment of a color imaging detection method for detecting a foreign object defect in an LCD according to the present application;
FIG. 3 is a schematic flow chart of a third embodiment of a color imaging detection method for detecting a foreign object defect in an LCD according to the present application;
fig. 4 is a schematic structural diagram of an electronic device shown in an embodiment of the present application.
Detailed Description
Preferred embodiments of the present application will be described in more detail below with reference to the accompanying drawings. While the preferred embodiments of the present application are shown in the drawings, it should be understood that the present application may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in this application and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.
It should be understood that although the terms "first," "second," "third," etc. may be used herein to describe various information, these information should not be limited to these terms. These terms are only used to distinguish one type of information from another. For example, first information may also be referred to as second information, and similarly, second information may also be referred to as first information, without departing from the scope of the present application. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of the present application, "a plurality" means two or more unless specifically limited otherwise.
Example one
The LCD module is usually a multi-layer structure, and during the process of manufacturing the LCD module, there are various processes of film sticking and pressing, and some foreign matters such as dust and impurities are inevitably introduced during the process of manufacturing, so that the finished product of the LCD module has defects. The traditional solution is to adopt a manual detection mode, however, with the rapid development of the machine vision industry, the machine vision defect detection has replaced the old manual detection mode in various industries, and the detection efficiency is greatly improved. Machine vision defect detection usually utilizes the black and white industry camera of high resolution to carry out imaging detection to LCD module picture, shoots two product pictures respectively, and one is the formation of image picture of LCD module when the backlight is lighted, and another is the LCD module formation of image picture that the surface was polished, thereby distinguishes and discerns the foreign matter defect through the position of bright spot between detection algorithm contrast two images. In the prior art, a foreign matter defect diagnosis method is provided, a dust side light device is designed for removing dust interference factors, the interference of dust on the backlight foreign matter defect can be eliminated, and a set of detection algorithm is designed for detecting the whole backlight foreign matter defect to identify whether a mobile phone screen contains the defect. However, the above prior art has disadvantages that when the dust side light device brightens and images dust, foreign matter defects are easily imaged, and the defects may be mistakenly judged as surface dust and filtered out, resulting in the problem of missing detection of the foreign matter defects. Therefore, it is required to develop a method of distinguishing surface dust and foreign matter defects from RGB values in an imaged image.
In view of the above problems, the embodiment of the application provides a color imaging detection method for detecting the defects of the LCD foreign matters, which can improve the accuracy of detecting the defects of the LCD module and improve the detection efficiency.
The technical solutions of the embodiments of the present application are described in detail below with reference to the accompanying drawings.
Fig. 1 is a schematic flow chart of a first embodiment of a color imaging detection method for detecting a foreign object defect in an LCD according to an embodiment of the present application.
Referring to fig. 1, an embodiment of a method for detecting a foreign object defect in an LCD by color imaging according to the present application includes:
101. shooting the LCD module by a color industrial camera under a preset light source;
the industrial camera is a key component in a machine vision system, the most essential function of the industrial camera is to convert an optical signal into an ordered electrical signal, the industrial camera has high image stability, high transmission capability and high anti-interference capability, and most of image sensors of the industrial camera are based on a CCD chip or a CMOS chip. The resulting image from a color industrial camera is in color. In the embodiment of the application, the color industrial camera is used for shooting the LCD module and acquiring the color LCD module image.
The preset light source is a light source which comprises a backlight light source and a surface lighting light source in a shooting environment, the surface lighting light source emits a first light wave, the first light wave is any one of primary color light, the primary colors are red, green and blue, the primary color light is red light, green light and blue light, and the primary color light is any one of the red light, the green light and the blue light. The backlight light source emits a second light wave, where the second light wave includes at least one primary color light different from the first light wave, and for example, assuming that the first light wave is red light, the second light wave includes at least one primary color light different from the red light, that is, the second light wave may be blue light, or may be a composite light of the red light and the blue light, or may be white light, but may not be red light identical to the first light wave, so as to achieve an effect that the surface lighting light source and the light wave emitted by the backlight light source should be obviously different.
The LCD module is generally a multi-layer structure including at least an upper polarizer layer, a liquid crystal layer and a lower polarizer layer, wherein the liquid crystal layer is disposed between the upper polarizer layer and the lower polarizer layer. The foreign matter defect that the finished product of LCD module exists is present between last polaroid and the liquid crystal layer and between lower polaroid and the liquid crystal layer, and the characteristics of this foreign matter defect are when the LCD module is struck by backlight, and the foreign matter defect exists among the screen as a bright spot, therefore in this application embodiment, can include backlight among the preset light source, in order to distinguish dust and the foreign matter defect on LCD module surface, still can include among the preset light source and have the surface that obviously distinguishes to strike light the dust on LCD module surface with backlight among the preset light source.
102. Extracting the region of interest of the LCD module image to obtain an LCD image to be detected;
the method comprises the steps of carrying out image processing on an LCD module image obtained by shooting, wherein in the LCD module image, a backlight light source can only penetrate through the position where a foreign matter defect is located but can not penetrate through the normal part of a screen, and the surface light source has the main function of brightening the surface dust, so that the obtained LCD module image presents an image with a large part of dark tones, sporadic response bright spots exist in the image, namely at least one response bright spot, a plurality of response bright spots comprise the foreign matter defect bright spot brightened by the backlight light source and the dust bright spot brightened by the surface light source, and the response bright spots are all extracted through an image processing technology to form an LCD image to be detected.
103. Performing RGB channel identification on an LCD image to be detected to obtain channel gray values corresponding to at least one response bright point in RGB three channels respectively;
the RGB channel identification means that colors of an LCD image to be detected are decomposed into a red channel, a green channel and a blue channel, and channel gray values corresponding to response bright points in the three channels are obtained. In the embodiment of the present application, the decomplexe algorithm in HALCON machine vision software is used to perform the channel decomposition operation, and it is understood that, in practical applications, the way of performing the channel decomposition is various, the above algorithms are only exemplary, and other suitable algorithms may be selected according to practical applications, and the way of performing the channel decomposition is not limited herein. As for the method for acquiring the channel gray scale value, the embodiment of the present application acquires the channel gray scale value through the image color extraction software, and it can be understood that in practical applications, the method for acquiring the channel gray scale value is various, the method for acquiring the channel gray scale value through the software is only exemplary, and other suitable algorithms or software can be selected according to practical application situations, where the method for acquiring the channel gray scale value is not limited uniquely.
104. Determining a threshold segmentation channel according to the primary color of the first light wave;
assuming that the first light wave is red light, imaging is performed after the first light wave illuminates surface dust, and the color displayed by the dust can be regarded as the same as the color of the first light wave within a reasonable error range, so that after the RGB channel identification, the response bright spot corresponding to the dust only has a higher gray value in a red channel, and also because the second light wave is obviously different from the first light wave, that is, at least one of a green channel or a blue channel of the response bright spot corresponding to the foreign matter defect illuminated by the second light wave has a higher gray value, in the present case, the green channel or the blue channel can be selected as a threshold segmentation channel, and the response bright spot corresponding to the dust and the response bright spot corresponding to the foreign matter defect can be clearly distinguished.
It is understood that the above determination method for the threshold value division channel is only exemplary, and in practical applications, the first light wave may be green light or blue light, and is not limited herein.
105. Performing threshold segmentation on the channel gray value corresponding to at least one response bright point by using a gray threshold in a threshold segmentation channel to obtain a foreign matter attribute classification corresponding to at least one response bright point in the LCD module image;
in the determined one or two threshold segmentation channels, the gray threshold is used to divide the channel gray values corresponding to all the response bright points into two sets, wherein the foreign matter attribute corresponding to the response bright point corresponding to the channel gray value in one set is classified as dust, and the foreign matter attribute corresponding to the response bright point corresponding to the channel gray value in the other set is classified as a foreign matter defect in the LCD module.
The following beneficial effects can be seen from the first embodiment:
the method comprises the steps of shooting an LCD module under a preset light source through a color industrial camera, wherein the preset light source comprises a backlight light source and a surface light source, the surface light source emits first light waves which are any one of three primary color light, the backlight light source emits second light waves which comprise at least one primary color light different from the first light waves, region-of-interest extraction is carried out on an LCD module image, the extracted LCD to-be-detected image comprises at least one response bright spot, RGB channel recognition is carried out on the LCD to-be-detected image, channel gray values of the response bright spot in three channels are obtained, threshold segmentation operation is carried out on the response bright spot in a threshold segmentation channel determined according to the primary color of the first light waves, and foreign matter attribute classification of the response bright spot is obtained. Compared with the prior art, this scheme shoots the LCD module under the specific environment that the light wave that the light source sent is polished to the background light source and surface has obvious difference, polish foreign matter defect in the LCD module and LCD module surface dust and make foreign matter defect and dust all show as the response bright spot in the LCD module image after the formation of image, response bright spot after extracting carries out RGB channel identification, confirm the foreign matter type that the response bright spot corresponds after carrying out the threshold value to the grey value of response bright spot and cutting apart in the threshold value cut-apart passageway, thereby reach the effect of distinguishing surface dust and the interior foreign matter defect of module, promote the detection accuracy, it is low to detect the implementation degree of difficulty, improve detection efficiency, reduce detection cost, it is strong to the compatibility of foreign matter detection.
Example two
In practical application, when determining the threshold segmentation channel, how many primary colors are included in the second light wave is also considered to accurately determine the threshold segmentation channel, so as to improve the detection efficiency, avoid the situation of repeated detection or invalid detection, and filter the response bright point corresponding to the dust after completing the classification of the foreign matter attribute corresponding to the response bright point, so as to detect the position of the foreign matter defect.
Fig. 2 is a schematic flow chart of a second embodiment of a color imaging detection method for detecting a foreign object defect in an LCD according to the present application.
Referring to fig. 2, an embodiment of a method for detecting a defect in an LCD by color imaging according to the present application includes:
201. extracting the region of interest of the LCD module image to obtain an LCD image to be detected;
and extracting the region of interest of the LCD module image through a threshold segmentation algorithm, and filtering out other non-target detection objects except the LCD module.
The threshold segmentation algorithm is an image segmentation technology based on regions, and the principle is to divide image pixel points into a plurality of classes, which are necessary image processing processes before image analysis, feature extraction and pattern recognition.
202. Performing RGB channel identification on an LCD image to be detected to obtain channel gray values corresponding to at least one response bright point in RGB three channels respectively;
in the embodiment of the present application, the specific content of step 202 is similar to that of step 103 in the first embodiment, and is not described herein again.
203. Determining a threshold segmentation channel according to the colors of the first light wave and the second light wave;
and if the second light wave is light combined by three primary colors, determining that the threshold segmentation channel is a channel with a gray value of zero in RGB values corresponding to the primary colors of the first light wave. Assuming that the first light wave is red light, gray values of the first light wave on a green channel and the second light wave on a blue channel in an RGB value of the first light wave are zero, and the second light wave is composite light in which three primary colors participate, it can be determined that gray values of the first light wave and the second light wave on the green channel or the blue channel are greatly different, and gray values of response bright points imaged by dust irradiated by the first light wave and a foreign object defect irradiated by the second light wave on the green channel or the blue channel are greatly different, so in the present case, the green channel or the blue channel with a gray value of zero in the first light wave can be selected to determine the threshold segmentation channel.
If the second light wave is light combined by any two primary colors, the threshold segmentation channel is determined to be a channel of which the gray value in the RGB values corresponding to the primary colors of the first light wave is zero and the gray value in the RGB values corresponding to the colors of the second light wave is not zero. Assuming that the first light wave is red light, whose RGB values have a zero gray value in the green channel and in the blue channel, and the second light wave is light combined from two primary colors, i.e. in the present case the second light wave may be light combined from red light and blue light or green light, then in the case of a combination of red light and blue light the gray values of the first light wave and the second light wave in the red channel and the green channel are both relatively close, whereas the gray value difference in the blue channel is relatively large, it may be determined that the blue channel is a threshold-divided channel. The second light wave may also be a combination of blue light and green light, and when the gray values of the first light wave and the second light wave in the blue channel and the green channel are greatly different, it may be determined that the blue channel or the green channel may be the threshold segmentation channel.
And if the second light wave is a primary light wave, determining that the threshold segmentation channel is the channel with the highest gray value in RGB values corresponding to the primary color of the second light wave. Assuming that the first light wave is red light, the gray scale values of the first light wave in the RGB values on the green channel and the blue channel are zero, the second light wave is green light, the gray scale values of the first light wave and the second light wave in the RGB values on the red channel and the blue channel are zero, the gray scale values of the first light wave and the second light wave in the red channel and the green channel are greatly different, but the second light wave is used for lightening the foreign object defect, so that the determination that the green channel is the threshold dividing channel can specifically detect the foreign object defect.
It is understood that the above hypothetical description is only used for better understanding of the scheme, and the first optical wave and the second optical wave can be set differently in practical application according to the practical application, and are not limited herein.
It can be understood that, due to the constraint or limitation of the precision of the existing industrial detection device, if the actual gray scale value of any one channel in the RGB values corresponding to the light colors of the first light wave and the second light wave is close to zero, the detection value output by the detection device defaults to zero, which does not exclude the improvement of the technical level in the future, and can detect the case where the actual gray scale value of any one channel in the RGB values corresponding to the light colors is zero.
204. Performing threshold segmentation on the channel gray value corresponding to at least one response bright point by using a gray threshold in a threshold segmentation channel to obtain a foreign matter attribute classification corresponding to at least one response bright point in the LCD module image;
the gray threshold is determined according to the numerical range of the channel gray values of the at least one response bright point in the threshold segmentation channel, and the average of all the channel gray values in the threshold segmentation channel can be selected as the gray threshold.
Dividing the channel gray value, namely comparing each channel gray value with a gray threshold value respectively, and if the current channel gray value is smaller than the gray threshold value, indicating that the main light source of the current response bright point is a first light wave, judging that the foreign matter attribute of the response bright point corresponding to the current channel gray value is classified as dust; and if the gray value of the current channel is greater than the gray threshold, the main light source of the current response bright point is the second light wave, and the foreign matter attribute of the response bright point corresponding to the gray value of the current channel is judged to be classified as the foreign matter defect.
205. Detecting the position of the LCD foreign matter defect;
and filtering the response bright spots judged as dust in the threshold segmentation channel, wherein the remaining response bright spots in the image of the threshold segmentation channel are response bright spots of the foreign matter defect, and the position of the foreign matter defect can be judged to be the position of the remaining response bright spots.
The following beneficial effects can be seen from the second embodiment:
the method comprises the steps of extracting an interested region of an LCD module image by adopting a threshold segmentation algorithm, filtering other non-target detection objects except the LCD module, determining a threshold segmentation channel according to the colors of a first light wave and a second light wave, comparing a channel gray value with a gray threshold in the threshold segmentation channel, distinguishing a response bright point corresponding to dust and a response bright point corresponding to a foreign matter defect, filtering the response bright point corresponding to the dust, and detecting the position of the response bright point corresponding to the foreign matter defect. Compared with the prior art, the scheme filters other non-target detection objects except the response bright spots, reduces interference to detection, considers various light color combination modes for lighting the LCD module, determines the optimal threshold segmentation channel to execute the distinguishing of the response bright spots corresponding to the dust and the response bright spots corresponding to the foreign matter defects, is strong in compatibility, improves detection accuracy, is low in detection implementation difficulty, and improves detection efficiency.
EXAMPLE III
In order to facilitate understanding, an embodiment of a color imaging detection method for detecting a defect of an LCD foreign object is provided below for description, and in practical applications, certain requirements are required for a preset light source and shooting imaging so as to ensure the quality of an image of an LCD module and improve the detection accuracy.
Fig. 3 is a schematic flow chart of a third embodiment of a color imaging detection method for detecting a foreign object defect in an LCD according to the present application.
Referring to fig. 3, a third embodiment of the method for detecting a color image of a foreign object defect in an LCD according to the present application includes:
301. the LCD module is lightened through the backlight light source and the surface polishing light source;
the LCD module is positioned between the backlight source and the surface light source, the brightness of the backlight source and the surface light source is required to be more than x, wherein the gray value of the response bright point corresponding to the dust and the foreign matter defect in the imaged LCD module image on any channel is more than x, and the value of x can be 150.
The surface light source irradiates the LCD module with an irradiation angle α, which is an included angle formed by a light wave emitted by the surface light source and a normal of a horizontal plane, where α is greater than zero.
302. Shooting an LCD module through a color industrial camera;
the color industrial camera has a three-primary-color filtering function, wherein the three-primary-color filtering function is that after light reflected by a shot object enters a camera photosensitive chip, the light reflected by the shot object is decomposed into components of three primary colors, namely red, green and blue, by the three-primary-color filtering function, and color signals are converted into electric signals, so that the camera photosensitive chip can identify the color of the light reflected by the shot object.
The front view of the screen surface of the LCD module is shot by the color industrial camera, and the color industrial camera can be arranged right above the LCD module to shoot.
The following beneficial effects can be seen from the third embodiment:
after the LCD module is brightened with certain luminance and angle through backlight source and surface light source of polishing, the front view of shooing the LCD module obtains the LCD module image, for prior art, this technical scheme can effectively improve the quality of LCD module image, promotes the detection accuracy.
Example four
Corresponding to the embodiment of the application function realization method, the application also provides an electronic device for executing the LCD foreign matter defect color imaging detection method and a corresponding embodiment.
Fig. 4 is a schematic structural diagram of an electronic device shown in an embodiment of the present application.
Referring to fig. 4, the electronic device 1000 includes a memory 1010 and a processor 1020.
The Processor 1020 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory 1010 may include various types of storage units, such as system memory, Read Only Memory (ROM), and permanent storage. Wherein the ROM may store static data or instructions that are needed by the processor 1020 or other modules of the computer. The persistent storage device may be a read-write storage device. The persistent storage may be a non-volatile storage device that does not lose stored instructions and data even after the computer is powered off. In some embodiments, the persistent storage device employs a mass storage device (e.g., magnetic or optical disk, flash memory) as the persistent storage device. In other embodiments, the permanent storage may be a removable storage device (e.g., floppy disk, optical drive). The system memory may be a read-write memory device or a volatile read-write memory device, such as a dynamic random access memory. The system memory may store instructions and data that some or all of the processors require at runtime. Further, the memory 1010 may include any combination of computer-readable storage media, including various types of semiconductor memory chips (DRAM, SRAM, SDRAM, flash memory, programmable read-only memory), magnetic and/or optical disks, among others. In some embodiments, memory 1010 may include a removable storage device that is readable and/or writable, such as a Compact Disc (CD), a read-only digital versatile disc (e.g., DVD-ROM, dual layer DVD-ROM), a read-only Blu-ray disc, an ultra-density optical disc, a flash memory card (e.g., SD card, min SD card, Micro-SD card, etc.), a magnetic floppy disc, or the like. Computer-readable storage media do not contain carrier waves or transitory electronic signals transmitted by wireless or wired means.
The memory 1010 has stored thereon executable code that, when processed by the processor 1020, may cause the processor 1020 to perform some or all of the methods described above.
The aspects of the present application have been described in detail hereinabove with reference to the accompanying drawings. In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments. Those skilled in the art should also appreciate that the acts and modules referred to in the specification are not necessarily required in the present application. In addition, it can be understood that the steps in the method of the embodiment of the present application may be sequentially adjusted, combined, and deleted according to actual needs, and the modules in the device of the embodiment of the present application may be combined, divided, and deleted according to actual needs.
Furthermore, the method according to the present application may also be implemented as a computer program or computer program product comprising computer program code instructions for performing some or all of the steps of the above-described method of the present application.
Alternatively, the present application may also be embodied as a non-transitory machine-readable storage medium (or computer-readable storage medium, or machine-readable storage medium) having stored thereon executable code (or a computer program, or computer instruction code) which, when executed by a processor of an electronic device (or electronic device, server, etc.), causes the processor to perform part or all of the various steps of the above-described method according to the present application.
Those of skill would further appreciate that the various illustrative logical blocks, modules, circuits, and algorithm steps described in connection with the applications disclosed herein may be implemented as electronic hardware, computer software, or combinations of both.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems and methods according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
Having described embodiments of the present application, the foregoing description is intended to be exemplary, not exhaustive, and not limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen in order to best explain the principles of the embodiments, the practical application, or improvements made to the technology in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.
Claims (10)
1. A LCD foreign body defect color imaging detection method is characterized by comprising the following steps:
shooting an LCD module by a color industrial camera under a preset light source to obtain an LCD module image, wherein the preset light source comprises a backlight light source and a surface light source; the surface light source emits a first light wave, and the first light wave is any one of three primary color lights; the backlight light source emits a second light wave, and the second light wave comprises at least one primary color light different from the first light wave;
extracting the region of interest of the LCD module image to obtain an LCD image to be detected, wherein the LCD image to be detected comprises at least one response bright spot;
performing RGB channel identification on the LCD image to be detected to obtain channel gray values corresponding to at least one response bright point in RGB three channels respectively;
determining a threshold segmentation channel according to the primary color of the first light wave;
and performing threshold segmentation on the channel gray value corresponding to at least one response bright point by using a gray threshold in the threshold segmentation channel to obtain a foreign matter attribute classification corresponding to at least one response bright point in the LCD module image, wherein the foreign matter attribute classification comprises dust and foreign matter defects.
2. The LCD foreign body defect color imaging detection method of claim 1,
the determining a threshold segmentation channel according to the primary color of the first light wave includes:
if the second light wave is light combined by three primary colors, determining the threshold segmentation channel as a channel with a gray value of zero in RGB values corresponding to the primary colors of the first light wave;
if the second light wave is light combined by any two primary colors, determining that the threshold segmentation channel is a channel with zero gray value in RGB values corresponding to the primary colors of the first light wave and non-zero gray value in RGB values corresponding to the colors of the second light wave;
and if the second light wave is a primary light wave, determining that the threshold segmentation channel is a channel with the highest gray value in RGB values corresponding to the primary color of the second light wave.
3. The LCD foreign body defect color imaging detection method of claim 1,
the gray threshold is determined according to the numerical range of the channel gray values of at least one response bright point in the threshold segmentation channel;
the threshold segmentation of the channel gray value corresponding to at least one response bright point by using a gray threshold in the threshold segmentation channel comprises:
and comparing the gray value of each channel with the gray threshold value respectively.
4. The LCD foreign body defect color imaging detection method of claim 3,
the obtaining of the foreign matter attribute classification corresponding to at least one response bright spot in the LCD module image includes:
if the gray value of the current channel is smaller than the gray threshold, determining that the foreign matter attribute of the response bright point corresponding to the gray value of the current channel is classified as the dust;
and if the gray value of the current channel is greater than the gray threshold, judging that the foreign matter attribute of the response bright point corresponding to the gray value of the current channel is classified as the foreign matter defect.
5. The LCD foreign body defect color imaging detection method of claim 4,
after obtaining the foreign matter attribute classification corresponding to at least one response bright spot in the LCD module group image, the method comprises the following steps:
and filtering out the response bright spots judged as the dust in the threshold segmentation channel.
6. The LCD foreign body defect color imaging detection method of claim 1,
the region of interest extraction of the LCD module image comprises the following steps:
and extracting the region of interest of the LCD module image through a threshold segmentation algorithm.
7. The LCD foreign body defect color imaging detection method of claim 1,
shoot the LCD module under predetermineeing the light source through colored industry camera, include:
the LCD module is lightened through the backlight light source and the surface polishing light source;
the surface light source irradiates the LCD module with an irradiation angle alpha, the irradiation angle is an included angle formed by light waves emitted by the surface light source and a normal line of a horizontal plane, and the alpha is larger than zero.
8. The LCD foreign body defect color imaging detection method of claim 1,
the color industrial camera has a three-primary-color filtering function;
shoot the LCD module under predetermineeing the light source through colored industry camera, include:
and shooting the front view of the screen surface of the LCD module through the color industrial camera.
9. An electronic device, comprising:
a processor; and
a memory having executable code stored thereon, which when executed by the processor, causes the processor to perform the method of any one of claims 1-8.
10. A non-transitory machine-readable storage medium having stored thereon executable code, which when executed by a processor of an electronic device, causes the processor to perform the method of any one of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110344667.3A CN112798613B (en) | 2021-03-31 | 2021-03-31 | LCD foreign matter defect color imaging detection method, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110344667.3A CN112798613B (en) | 2021-03-31 | 2021-03-31 | LCD foreign matter defect color imaging detection method, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112798613A true CN112798613A (en) | 2021-05-14 |
| CN112798613B CN112798613B (en) | 2021-08-06 |
Family
ID=75816038
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110344667.3A Active CN112798613B (en) | 2021-03-31 | 2021-03-31 | LCD foreign matter defect color imaging detection method, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112798613B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114494122A (en) * | 2021-12-20 | 2022-05-13 | 苏州镁伽科技有限公司 | Target object detection method and device, storage medium and electronic equipment |
| CN116137031A (en) * | 2023-03-06 | 2023-05-19 | 信利光电股份有限公司 | LCD display screen slight bright point defect detection method |
| CN117636077A (en) * | 2024-01-25 | 2024-03-01 | 高视科技(苏州)股份有限公司 | Defect detection parameter adjustment method, electronic device and storage medium |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005043174A (en) * | 2003-07-28 | 2005-02-17 | Nidec Tosok Corp | Color irregularity inspection apparatus |
| JP2005148670A (en) * | 2003-11-20 | 2005-06-09 | Seiko Epson Corp | Method and device for generating inspection image for liquid crystal panel, and method and device for inspecting outward shape |
| CN101021490A (en) * | 2007-03-12 | 2007-08-22 | 3i系统公司 | Automatic detecting system and method for planar substrate |
| CN104749184A (en) * | 2013-12-31 | 2015-07-01 | 研祥智能科技股份有限公司 | Automatic optical detection method and automatic optical detection system |
| US9493025B2 (en) * | 2015-01-19 | 2016-11-15 | International Business Machines Corporation | Graphene layers for identification of products |
| CN108318503A (en) * | 2018-02-06 | 2018-07-24 | 凌云光技术集团有限责任公司 | LCD screen dust detection method and device |
| CN207992608U (en) * | 2018-01-25 | 2018-10-19 | 惠州高视科技有限公司 | The imaging mechanism that liquid-crystalline glasses screen surfaces dust is distinguished with internal foreign matter |
| CN111474177A (en) * | 2020-05-06 | 2020-07-31 | 深圳市斑马视觉科技有限公司 | Liquid crystal screen backlight foreign matter defect detection method based on computer vision |
| CN111781203A (en) * | 2020-06-15 | 2020-10-16 | 杭州百子尖科技股份有限公司 | Configurable intelligent visual inspection system and method based on standard industrial camera |
-
2021
- 2021-03-31 CN CN202110344667.3A patent/CN112798613B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005043174A (en) * | 2003-07-28 | 2005-02-17 | Nidec Tosok Corp | Color irregularity inspection apparatus |
| JP2005148670A (en) * | 2003-11-20 | 2005-06-09 | Seiko Epson Corp | Method and device for generating inspection image for liquid crystal panel, and method and device for inspecting outward shape |
| CN101021490A (en) * | 2007-03-12 | 2007-08-22 | 3i系统公司 | Automatic detecting system and method for planar substrate |
| CN104749184A (en) * | 2013-12-31 | 2015-07-01 | 研祥智能科技股份有限公司 | Automatic optical detection method and automatic optical detection system |
| US9493025B2 (en) * | 2015-01-19 | 2016-11-15 | International Business Machines Corporation | Graphene layers for identification of products |
| CN207992608U (en) * | 2018-01-25 | 2018-10-19 | 惠州高视科技有限公司 | The imaging mechanism that liquid-crystalline glasses screen surfaces dust is distinguished with internal foreign matter |
| CN108318503A (en) * | 2018-02-06 | 2018-07-24 | 凌云光技术集团有限责任公司 | LCD screen dust detection method and device |
| CN111474177A (en) * | 2020-05-06 | 2020-07-31 | 深圳市斑马视觉科技有限公司 | Liquid crystal screen backlight foreign matter defect detection method based on computer vision |
| CN111781203A (en) * | 2020-06-15 | 2020-10-16 | 杭州百子尖科技股份有限公司 | Configurable intelligent visual inspection system and method based on standard industrial camera |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114494122A (en) * | 2021-12-20 | 2022-05-13 | 苏州镁伽科技有限公司 | Target object detection method and device, storage medium and electronic equipment |
| CN116137031A (en) * | 2023-03-06 | 2023-05-19 | 信利光电股份有限公司 | LCD display screen slight bright point defect detection method |
| CN116137031B (en) * | 2023-03-06 | 2023-10-03 | 信利光电股份有限公司 | LCD display screen slight bright point defect detection method |
| CN117636077A (en) * | 2024-01-25 | 2024-03-01 | 高视科技(苏州)股份有限公司 | Defect detection parameter adjustment method, electronic device and storage medium |
| CN117636077B (en) * | 2024-01-25 | 2024-04-02 | 高视科技(苏州)股份有限公司 | Defect detection parameter adjustment method, electronic device and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112798613B (en) | 2021-08-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112798613B (en) | LCD foreign matter defect color imaging detection method, electronic equipment and storage medium | |
| TWI626440B (en) | Defect detection apparatus, defect detection method and program product | |
| TWI484161B (en) | Defect inspection system and filming device for defect inspection, image processing device for defect inspection, image processing program for defect inspection, recording media, and image processing method for defect inspection used therein | |
| KR100819412B1 (en) | Defect detecting method and defect detecting device | |
| CN111627009A (en) | Screen detection method and device and head-mounted display equipment | |
| JP6348289B2 (en) | Inspection apparatus and inspection method | |
| CN112858318B (en) | Method for distinguishing screen foreign matter defect from dust, electronic equipment and storage medium | |
| JP2003500780A (en) | Pixel Classification Based on Accuracy in Object Inspection | |
| US8837809B2 (en) | Method for detecting a bridge connecting failure | |
| CN110412055B (en) | Lens white fog defect detection method based on multi-light-source dark field illumination | |
| KR20190045857A (en) | Method and image capturing device for detecting for in a scene | |
| CN111583258A (en) | Defect detection method, device, system and storage medium | |
| CN115018797A (en) | Screen defect detection method, screen defect detection device and computer-readable storage medium | |
| CN113785181A (en) | OLED screen point defect judgment method and device, storage medium and electronic equipment | |
| CN113781396A (en) | Screen defect detection method, device, equipment and storage medium | |
| JP2019168388A (en) | Image inspection method and image inspection device | |
| KR101022187B1 (en) | Substrate inspection device | |
| JP2007033339A (en) | Method and device for determining detection of fisheye | |
| CN117309892A (en) | Defect detection method, device and system for blue film of battery and light source controller | |
| CN113295710A (en) | Method for detecting LCD module, electronic equipment and storage medium | |
| CN113628212B (en) | Defective polarizer identification method, electronic device, and storage medium | |
| CN112987356B (en) | Liquid crystal display panel bottom foreign matter filtering device | |
| CN114219758A (en) | Defect detection method, system, electronic device and computer readable storage medium | |
| JP3314253B2 (en) | Inspection device for color filters for viewfinder | |
| JP4967132B2 (en) | Defect inspection method for object surface |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 215163 rooms 101, 102, 901 and 902, floor 1, building 11, 198 Jialingjiang Road, high tech Zone, Suzhou City, Jiangsu Province Applicant after: Gaoshi Technology (Suzhou) Co.,Ltd. Address before: 516000 west side of the fourth floor, building CD, science and technology entrepreneurship center, No.2, South Huatai Road, Huinan hi tech Industrial Park, huiao Avenue, Huicheng District, Huizhou City, Guangdong Province Applicant before: HUIZHOU GOVION TECHNOLOGY Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| EE01 | Entry into force of recordation of patent licensing contract | ||
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20210514 Assignee: Suzhou Gaoshi Semiconductor Technology Co.,Ltd. Assignor: Gaoshi Technology (Suzhou) Co.,Ltd. Contract record no.: X2021990000430 Denomination of invention: LCD foreign object defect color imaging detection method, electronic equipment and storage medium License type: Common License Record date: 20210722 |
|
| CP03 | Change of name, title or address | ||
| CP03 | Change of name, title or address |
Address after: 215129 Rooms 101, 102, 901, 902, Floor 9, Building 11, No. 198, Jialing River Road, High tech Zone, Suzhou City, Jiangsu Province Patentee after: Gaoshi Technology (Suzhou) Co.,Ltd. Address before: 215163 rooms 101, 102, 901 and 902, floor 1, building 11, 198 Jialingjiang Road, high tech Zone, Suzhou City, Jiangsu Province Patentee before: Gaoshi Technology (Suzhou) Co.,Ltd. |