CN112666733B - LCD gray scale picture offline defect detection method, electronic equipment and storage medium - Google Patents
LCD gray scale picture offline defect detection method, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN112666733B CN112666733B CN202110275858.9A CN202110275858A CN112666733B CN 112666733 B CN112666733 B CN 112666733B CN 202110275858 A CN202110275858 A CN 202110275858A CN 112666733 B CN112666733 B CN 112666733B
- Authority
- CN
- China
- Prior art keywords
- response
- lcd
- linear
- image
- filtering
- 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.)
- Active
Links
Images
Abstract
The application relates to a method for detecting LCD gray scale picture down line type defects. The method comprises the following steps: obtaining a target detection image according to the LCD image to be detected under the gray scale picture; respectively carrying out linear interference filtering processing on the target detection image according to N detection angles to obtain N spatial filtering result graphs, wherein N is an integer greater than 1; respectively carrying out linear defect highlighting processing on the N spatial filtering result graphs to obtain N first filtering response graphs; and determining the positions of the linear defects according to the N first filter response graphs. The scheme that this application provided can improve LCD line type defect responsibility, and is high to the suitability of line type defect, promotes the accuracy of line type defect testing result, promotes LCD production quality and production efficiency.
Description
Technical Field
The present disclosure relates to the field of screen inspection technologies, and in particular, to a method for inspecting a defect of an LCD grayscale image offline type, an electronic device and a storage medium.
Background
Along with the development of the times, the participation degree of the liquid crystal display screen in the life of people is higher and higher, the liquid crystal display screen is used as a key part of human-computer interaction, the display quality of the liquid crystal display screen directly influences the experience feeling of users, and the defect detection of the liquid crystal display screen is generated at the right moment in order to improve the quality of the liquid crystal display screen. The traditional human eye detection method is used for detecting the defects of the screen based on the human eye visual characteristics, is greatly influenced by the subjective feeling of a human body and the detection environment, and is difficult to objectively judge whether the defects exist, so that the research and development of an automatic detection system of the liquid crystal display screen, which has an objective judgment standard and accords with the practical application, are needed to meet the requirements of product quality and production efficiency.
In the prior art, in a patent with publication number CN103792699A (TFT-LCD Mura defect machine vision detection method based on B-spline surface fitting), an LCD screen detection method is proposed, in which a lighted LCD grayscale image to be detected is collected by a CCD camera, an area of interest is extracted after filtering an original image, an image background is fitted by a bicubic B-spline surface fitting method, an image with the uneven brightness background removed is obtained by subtracting the background image from the original image, and a Mura defect is detected by using a Canny operator.
The above prior art solution has the following disadvantages:
the method for obtaining the response image by subtracting the fitting background image from the original image has high requirement on the quality of the original image and low linear defect responsiveness. Therefore, it is necessary to develop an efficient detection method for LCD without fitting image background and with high responsiveness to linear defects.
Disclosure of Invention
In order to solve the problems in the related art, the method for detecting the line defect under the LCD gray scale picture can improve the responsivity of the line defect of the LCD, has high applicability to the line defect, improves the accuracy of a line defect detection result, and improves the production quality and the production efficiency of the LCD.
The first aspect of the present application provides a method for detecting LCD gray scale image offline defects, comprising:
obtaining a target detection image according to the LCD image to be detected under the gray scale picture;
respectively carrying out linear interference filtering processing on the target detection image according to N detection angles to obtain N spatial filtering result graphs, wherein N is an integer greater than 1;
respectively carrying out linear defect highlighting processing on the N spatial filtering result graphs to obtain N first filtering response graphs;
the linear defect highlighting treatment comprises the following steps: controlling the first linear filtering kernel and the second linear filtering kernel to respectively perform linear spatial filtering on the spatial filtering result graph to obtain a second filtering response graph and a third filtering response graph, and subtracting the second filtering response graph from the third filtering response graph;
the first linear filter kernel and the second linear filter kernel are square filter kernels, the arrangement directions of filter parameters are the same and are perpendicular to the detection angle direction of the spatial filter result graph, the size of the first linear filter kernel is smaller than that of the second linear filter kernel, and the first filter parameter of the first linear filter kernel is larger than the second filter parameter of the second linear filter kernel;
and determining the positions of the linear defects according to the N first filter response graphs.
In one embodiment, the line-type interference filtering processing according to N detection angles is performed on the target detection image, and includes:
when the ith detection angle is detected for the target detection image, controlling the linear filter kernel with the same direction as the rest N-1 detection angles to perform linear spatial filtering on the target detection image, wherein i is an integer larger than 0.
In one embodiment, determining linear defect locations from the N first filter response maps comprises:
respectively carrying out linear interference filtering processing according to the N detection angles on the N first filtering response graphs to obtain N target response graphs;
and respectively carrying out dust filtration on the N target response graphs.
In one embodiment, the dust filtering is performed on the N target response maps, respectively, and includes:
acquiring an LCD entity graph to be detected, and extracting dust information of the LCD entity graph to be detected through threshold segmentation to obtain a dust response graph;
comparing the dust response graph with the N target response graphs respectively, and determining the dust position of each target response graph;
and respectively eliminating the dust positions of the target response images to obtain N response images to be segmented, wherein the response images to be segmented are binary images.
In one embodiment, obtaining N response maps to be segmented includes:
acquiring a minimum rotation circumscribed rectangle of the contours of the response areas in the N response graphs to be segmented;
calculating the width and height values of the response region of the minimum rotation circumscribed rectangle and the area of the response region of the minimum rotation circumscribed rectangle;
comparing the width and height values of the response regions and the areas of the response regions with a linear defect standard mapping table, wherein the linear defect standard mapping table is a set of corresponding width and height thresholds and area thresholds of the response regions, which are used for judging that the contours of the response regions are linear defects, under the size of each target detection image;
and determining the position of the linear defect according to the comparison result.
In one embodiment, obtaining a target detection image according to an LCD image to be detected in a grayscale frame includes:
if the LCD image to be detected is an LCD main view, performing threshold segmentation on the LCD image to be detected to obtain an LCD area;
if the LCD image to be detected is an LCD oblique view, after the LCD image to be detected is affine transformed into an LCD main view, threshold segmentation is carried out on the LCD image to be detected, and an LCD area is obtained.
In one embodiment, after obtaining the LCD area, the method includes:
performing Gaussian pyramid downsampling on the LCD area to obtain an M-layer downsampling result graph, wherein M is an integer larger than 1;
respectively calculating Hessian matrixes for the M layers of down-sampling result graphs to obtain M down-sampling response graphs;
respectively calculating the areas of the maximum response ranges in the M downsampling response graphs to obtain M areas of the maximum response ranges;
and respectively calculating the ratio of the area of each maximum response range to the area of the LCD area, and selecting the down-sampling result image corresponding to the down-sampling response image with the maximum ratio as the target detection image.
In one embodiment, after selecting the down-sampling result graph corresponding to the down-sampling response graph with the largest ratio as the target detection image, the method includes:
and after connecting the non-target detection objects in the target detection image through a closing operation, rejecting the non-target detection objects through threshold segmentation.
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 aim of removing other linear interference under the current detection angle is achieved by obtaining a target detection image according to an LCD image to be detected under a gray scale picture and respectively carrying out linear spatial filtering on the target detection image according to a plurality of detection angles, a first filtering response image with the same quantity as that of a spatial filtering result image is obtained after linear defect highlighting processing according to the obtained spatial filtering result image with the same quantity as that of the detection angles, the linear defect highlighting processing refers to the difference after the spatial filtering result image is further subjected to spatial filtering by controlling two linear filtering check images with the same filtering parameter arrangement direction with the larger size and the smaller size and vertical to the detection angle direction of the spatial filtering result image, please refer to FIG. 11, in the filtering response image obtained after the linear defect highlighting processing, the pixel value of the position of a linear defect is obviously higher than that of the peripheral region, the position of the linear defect is highlighted, so that the position of the linear defect can be determined according to the acquired first filter response diagram. Compared with the prior art, the line type interference of other angle directions is got rid of through spatial filtering when detecting the line type filtering under the current angle direction to this application technical scheme, avoids the detection of the line type defect under the current detection angle to receive the interference, and the response degree that improves the line type defect is handled through the line type defect highlight, makes line type defect position obtain more obvious demonstration in the response diagram, improves the detection accuracy degree of line type defect, promotes the detection efficiency of line type defect, promotes LCD production quality and production efficiency.
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 method for detecting LCD gray scale frame pull-down defects according to the present application;
FIG. 2 is a schematic flow chart of a second embodiment of a method for detecting LCD gray-scale frame pull-down defects according to the present application;
FIG. 3 is a schematic flowchart illustrating a third embodiment of a method for detecting a defect in an LCD gray scale frame;
FIG. 4 is a flowchart illustrating a fourth exemplary embodiment of a method for detecting a defect in an LCD gray scale frame;
FIG. 5 is a diagram illustrating pixel value results of line-type defect locations in a spatial filtering result graph obtained by a method for detecting line-type defects under an LCD gray scale screen according to an embodiment of the present application;
FIG. 6 is a global exemplary diagram of a spatial filtering result graph obtained by the LCD gray scale frame offline defect detection method according to the embodiment of the present application;
FIG. 7 is a diagram illustrating an example of a first linear filtering kernel constructed in the LCD gray scale frame offline defect detection method according to an embodiment of the present disclosure;
FIG. 8 is a diagram illustrating an example of a second linear filtering kernel constructed in the method for detecting defects under LCD gray scale images according to an embodiment of the present application;
FIG. 9 is a diagram illustrating an exemplary second filter response in a method for detecting defects in an LCD gray scale frame layout according to an embodiment of the present disclosure;
FIG. 10 is a diagram illustrating an exemplary third filter response in a method for detecting LCD gray scale line defect in an LCD panel according to an embodiment of the present invention;
FIG. 11 is a diagram illustrating an exemplary first filter response in a method for detecting LCD gray scale line defect in an LCD panel according to an embodiment of the present disclosure;
fig. 12 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
Along with the development of the times, the participation degree of the liquid crystal display screen in the life of people is higher and higher, the liquid crystal display screen is used as a key part of human-computer interaction, the display quality of the liquid crystal display screen directly influences the experience feeling of users, and the defect detection of the liquid crystal display screen is generated at the right moment in order to improve the quality of the liquid crystal display screen. The traditional human eye detection method is used for detecting the defects of the screen based on the human eye visual characteristics, is greatly influenced by the subjective feeling of a human body and the detection environment, and is difficult to objectively judge whether the defects exist, so that the research and development of an automatic detection system of the liquid crystal display screen, which has an objective judgment standard and accords with the practical application, are needed to meet the requirements of product quality and production efficiency. In the prior art, an LCD screen detection method is provided, a lighted LCD gray image to be detected is collected through a CCD camera, an interested region is extracted after an original image is filtered, an image background is fitted by adopting a bicubic B-spline surface fitting method, an image with the background image removed is obtained after the original image is subtracted, and a Canny operator is used for detecting the Mura defect. However, the prior art scheme has the defects that the method for obtaining the response image by subtracting the fitting background image from the original image has high requirements on the quality of the original image and low linear defect responsiveness. Therefore, it is necessary to develop an efficient detection method for LCD without fitting image background and with high responsiveness to linear defects.
In view of the above problems, the embodiments of the present application provide a method for detecting linear defects in an LCD grayscale image, which can improve responsiveness of linear defects of an LCD, has high applicability to linear defects, improves accuracy of linear defect detection results, and improves production quality and production efficiency of an LCD.
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 flowchart illustrating a first method for detecting a defect in an LCD grayscale frame according to an embodiment of the present disclosure.
Referring to fig. 1, an embodiment of a method for detecting a defect in an LCD grayscale frame includes:
101. obtaining a target detection image according to the LCD image to be detected under the gray scale picture;
the gray scale is to divide the brightness variation between the brightest and darkest into several parts so as to control the brightness of the screen corresponding to the signal input. The digital image is composed of several pixels, and a pixel can present many different colors because the pixel is composed of three sub-pixels of red, green and blue, the light source behind the sub-pixels can display different brightness levels, and the gray scale represents the gradation level of different brightness from the darkest to the brightest.
A gray scale picture refers to a gray image having a single channel pixel value in the range of 0-255, and is typically displayed as a gray scale change from darkest black to brightest white.
In the embodiment of the application, the LCD image to be measured is photographed by an industrial camera, and it can be understood that, in practical application, the obtaining manner of the LCD image to be measured is various, and photographing and obtaining by the industrial camera is only exemplary and is not used as the only limitation of the obtaining manner of the LCD image to be measured.
The target detection image is an image for detecting linear defects, which is extracted according to the acquired LCD image to be detected.
102. Respectively carrying out linear interference filtering processing according to N detection angles on the target detection image;
the detection angle refers to a detection angle of the line type defect, and for example, if the detection angle is 45 degrees, the line type defect with the angle direction of 45 degrees is detected.
For example, the number of the detection angles may be 4, which is 45 degrees, 90 degrees, 135 degrees and 180 degrees, and the value of N is 4 at this time, it can be understood that the value of the detection angle is various, and the value needs to be taken according to the actual application condition in the actual application, and the value of the detection angle is only exemplary and is not limited uniquely, and the value of N is determined according to the number of the detection angles, and the value range is an integer greater than 1.
The linear interference filtering processing refers to performing linear spatial filtering on a target detection image, the linear spatial filtering refers to performing filtering operation on image pixels surrounded by a linear neighborhood, namely a linear filtering kernel, wherein the response of the filtering operation is the sum of products of a filtering coefficient of the linear neighborhood and the image pixels surrounded by the linear neighborhood, a new pixel is generated after the filtering operation, the coordinate of the new pixel is equal to the coordinate of the center of the linear neighborhood, and the value of the pixel is the response result.
After the linear interference filtering processing, N spatial filtering result graphs are obtained.
Referring to fig. 5 and 6, after the line interference filtering process, a white suspected line defect can be seen from the bottom right corner of fig. 6, and although other line interferences are filtered out, the suspected line defect is not obvious at this time. As can be seen from fig. 5, the pixel value of the corresponding portion of the pseudo-line type defect is about 140, which is higher than the pixel values of the remaining background positions (about 135), but the difference is not large, so that all the pseudo-line type defects need to be highlighted.
103. Respectively carrying out linear defect highlighting treatment on the N spatial filtering result graphs;
and respectively carrying out linear defect highlighting treatment on the N spatial filtering result graphs to obtain N first filtering response graphs.
Before the linear defect highlighting processing, two linear filter kernels, one large linear filter kernel and one small linear filter kernel, are required to be constructed, the first linear filter kernel and the second linear filter kernel are both square filter kernels, the arrangement directions of the filter parameters are the same and are perpendicular to the detection angle direction of the spatial filter result graph, the size of the first linear filter kernel is smaller than that of the second linear filter kernel, and the first filter parameter of the first linear filter kernel is larger than the second filter parameter of the second linear filter kernel.
For example, referring to fig. 6, fig. 7 and fig. 8, it can be seen from fig. 6 that the angular direction of the suspected linear defect is about 135 degrees clockwise based on the horizontal plane, and therefore, the arrangement direction angle of the filter parameters of the first linear filter kernel and the second linear filter kernel is perpendicular to the angular direction of the suspected linear defect, i.e. the arrangement direction angle is 45 degrees clockwise based on the horizontal line. The size of the filter parameter is generally a real number greater than 0 and smaller than 1, and may be determined based on size data of a linear filter kernel, such as a 7 × 7 linear filter kernel shown in fig. 7, whose filter parameter is set to be the reciprocal of the number of edge length pixels, that is, 1/7, or a 21 × 21 linear filter kernel shown in fig. 8, whose filter parameter is set to be 1/21.
The linear defect highlighting processing is to control the first linear filtering kernel and the second linear filtering kernel to respectively perform linear spatial filtering on the spatial filtering result graph to obtain a second filtering response graph and a third filtering response graph, and subtract the second filtering response graph from the third filtering response graph.
For example, referring to fig. 9, 10 and 11, in fig. 9 and 10, the background pixel values of the second filter response map except the suspected line-type defect position are very close to the background pixel values of the third filter response map except the suspected line-type defect position, the absolute difference between the background pixel values of the two response maps is mostly within 1, and the difference between the pixel values in the suspected line-type defect position is basically more than 1, so that the background pixel value can be changed to a value close to 0 by subtracting the second filter response map from the third filter response map, and in the image display, the pixel value is 0 or less than 0, which is regarded as black, so in the first filter response map of fig. 11, since the pixel values in the positions of only the suspected line-type defect are not close to 0 and mostly more than 1, only the position of the suspected line-type defect is displayed.
In summary, the line defect highlighting process can eliminate the background interference, enhance the response of the suspected line defect position, and clearly display the suspected line defect position.
104. Determining the position of the linear defect according to the N first filter response graphs;
although the positions of the suspected line-type defects can be clearly displayed in the first filter response map, there may be a line-type response which is not enough to be regarded as a line-type defect, or since there is dust on the LCD surface when acquiring the LCD image to be measured, and the dust may be mistaken for a line-type defect to be detected, so that it is necessary to screen out the N first filter response maps to determine the true line-type defect.
The following beneficial effects can be seen from the first embodiment:
the aim of removing other linear interference under the current detection angle is achieved by obtaining a target detection image according to an LCD image to be detected under a gray scale picture and respectively carrying out linear spatial filtering on the target detection image according to a plurality of detection angles, a first filtering response image with the same quantity as that of a spatial filtering result image is obtained after linear defect highlighting processing according to the obtained spatial filtering result image with the same quantity as that of the detection angles, the linear defect highlighting processing refers to the difference after the spatial filtering result image is further subjected to spatial filtering by controlling two linear filtering check images with the same filtering parameter arrangement direction with the larger size and the smaller size and vertical to the detection angle direction of the spatial filtering result image, please refer to FIG. 11, in the filtering response image obtained after the linear defect highlighting processing, the pixel value of the position of a linear defect is obviously higher than that of the peripheral region, the position of the linear defect is highlighted, so that the position of the linear defect can be determined according to the acquired first filter response diagram. Compared with the prior art, the line type interference of other angle directions is got rid of through spatial filtering when detecting the line type filtering under the current angle direction to this application technical scheme, avoids the detection of the line type defect under the current detection angle to receive the interference, and the response degree that improves the line type defect is handled through the line type defect highlight, makes line type defect position obtain more obvious demonstration in the response diagram, improves the detection accuracy degree of line type defect, promotes the detection efficiency of line type defect, promotes LCD production quality and production efficiency.
Example two
In practical applications, the line type interference filtering process will avoid the line type defect at the current detection angle from being filtered, so that it is necessary to use the detection angles other than the current detection angle to construct line type filter kernels, and use these filter kernels to eliminate the line type interference at other angles, thereby avoiding the situation that the detection accuracy is reduced due to the interference of the line type interference at other angles on the detection result of the line type defect at the current detection angle.
Fig. 2 is a schematic flowchart illustrating a second embodiment of a method for detecting a defect in an LCD grayscale frame according to the present application.
Referring to fig. 2, an embodiment of a method for detecting a defect in an LCD grayscale frame includes:
201. determining a current detection angle, and constructing a linear filtering kernel according to the rest N-1 detection angles;
assuming that the detection angles are 45 degrees, 90 degrees, 135 degrees and 180 degrees, if the current ith detection angle is 135 degrees, respectively constructing three linear filter kernels according to the other three angles, namely 45 degrees, 90 degrees and 180 degrees, so that the arrangement direction of the filter parameters of the constructed linear filter kernels is equal to the three angles based on the horizontal plane clockwise direction. It is to be understood that the specific angular values described above are exemplary and not limiting.
The linear filtering kernel for removing the linear interference may be a linear filtering kernel with a small size, and the shape of the linear filtering kernel is a square, so as to achieve a better interference removal effect.
202. Controlling the constructed linear filtering kernel to carry out linear spatial filtering;
since the response of the linear spatial filtering is the sum of the products of the filter coefficients of the linear neighborhood and the image pixels surrounded by the linear neighborhood, when the angle direction of the linear interference is the same as the arrangement direction of the filter parameters of the linear filter kernel, and the size of the current linear filter kernel is smaller, the pixel values at the linear interference are multiplied by the filter coefficients and then added, the obtained pixel value of the response is smaller than the original target pixel value, and when the linear filter kernel passes through the linear interference position, the area covering the linear interference is more, so that when the angle direction of the linear interference is the same as the filter parameter arrangement direction of the linear filter kernel, the influence degree of the pixel value of the linear interference position is larger than that of the pixel value of the linear defect position under the current detection angle, so that the linear interference can be filtered by using the linear filter kernel with the same angle as the linear interference.
The following beneficial effects can be seen from the second embodiment:
and linear spatial filtering is carried out on the target detection image by controlling the linear filtering cores in the other N-1 detection angle directions, so that the effect of removing linear interference at other angles is achieved. Compared with the prior art, the linear type interference at other angles is eliminated, the detection accuracy of the linear type defects at the current detection angle can be improved, the linear type interference is checked by utilizing linear type filtering, the pertinence is achieved, and the filtering effect is improved.
EXAMPLE III
In practical application, all detected line type defects in the N first filter response graphs are further screened, so that the condition that dust on the LCD to be detected is mistaken for the line type defects and the line type response which does not meet the line type defect standard is eliminated, and the effect of improving the detection precision of the line type defects is achieved.
Fig. 3 is a schematic flowchart illustrating a third embodiment of a method for detecting a defect in an LCD grayscale frame according to the present application.
Referring to fig. 3, a third embodiment of the method for detecting the offline defect of the LCD grayscale image in the embodiment of the present application includes:
301. respectively carrying out linear interference filtering processing according to the N detection angles on the N first filtering response graphs;
and executing the operations from step 201 to step 202 on the obtained first filter response map, and further filtering out linear interference in the response map to obtain N target response maps.
302. Respectively carrying out dust filtration on the N target response graphs;
and acquiring the LCD entity image to be detected in the same manner as the LCD image to be detected, shooting by using a practical industrial camera, and selecting a proper acquisition manner according to the actual application condition, wherein the acquisition manner is not limited here.
And extracting dust information of the LCD entity image to be detected through threshold segmentation, wherein the threshold segmentation refers to selecting one or more thresholds according to gray levels to divide a pixel set into a plurality of classes, and the pixels of the image are divided into a plurality of classes. And extracting dust information according to a threshold value of the pixel point of the dust to obtain a dust response graph.
And comparing the dust response graph with the N target response graphs respectively, and determining the dust position of each target response graph according to the comparison result.
And respectively removing dust positions of each target response image to obtain N response images to be segmented, wherein the response images to be segmented are binary images, each pixel on the response images to be segmented only has two possible values or gray scale states, one value is a background part of the image, and the other value is a linear response which meets the linear defect standard and does not meet the linear defect standard.
303. Determining the position of the linear defect;
and acquiring the minimum rotating circumscribed rectangle of the contours of the response regions in the N response images to be segmented, and calculating the width and height values of the response regions of the minimum rotating circumscribed rectangle and the area of the response regions of the minimum rotating circumscribed rectangle.
Comparing the width and height values of the response region and the area of the response region with a linear defect standard mapping table, where the defect standard mapping table is a set of corresponding width and height thresholds and area thresholds of the response region for determining that the contour of the response region is a linear defect under the size of each target detection image, and the linear defect standard mapping table is exemplarily shown in the following table:
it is understood that the size and the threshold in the linear defect standard mapping table are exemplary, in practical applications, the size data and the number of size categories may be set according to practical applications, and the same response region width and height threshold and response region area threshold corresponding to the size of the target detection image may also be set according to practical applications, and are not limited herein.
And judging whether each suspected linear defect reaches the standard capable of being judged as a linear defect according to the comparison result, eliminating the suspected linear defects which do not reach the standard, and determining the suspected linear defects as linear defects.
The following beneficial effects can be seen from the third embodiment:
and finally determining the linear defect by respectively carrying out linear interference filtering processing, dust filtering processing and linear defect standard judging processing on the N first filter response graphs. Compared with the prior art, the N first filter response graphs are respectively subjected to linear interference filtering processing to further filter linear interference in the same direction as the linear defect, which is generated when the first filter response graphs are obtained, the dust filtering processing removes the dust interference objectively existing on the LCD screen to be detected, the linear response which is not enough to be judged as the linear defect is removed by linear defect standard judging processing, the linear defect detection precision is improved by the combination of the three processing modes, the linear defect detection error rate is reduced, the situation that repeated inspection is needed is avoided, and the linear defect detection efficiency is improved.
Example four
In practical application, a target detection image obtained according to an LCD image to be detected needs to be subjected to threshold segmentation, gaussian pyramid down-sampling and other processing under a gray scale image to ensure the quality of the target detection image.
Fig. 4 is a flowchart illustrating a fourth embodiment of a method for detecting a defect in an LCD grayscale frame according to the present application.
Referring to fig. 4, a fourth embodiment of the method for detecting the offline defect of the LCD grayscale image in the embodiment of the present application includes:
401. acquiring an LCD area;
acquiring an LCD image to be detected, reading a gray image with a single-channel pixel value range of 0-255 by default, and if the LCD image to be detected is an LCD main view, performing threshold segmentation on the LCD image to be detected to obtain an LCD area; if the LCD image to be detected is an LCD oblique view, after the LCD image to be detected is affine transformed into an LCD main view, threshold segmentation is carried out on the LCD image to be detected, and an LCD area is obtained. The affine transformation is that in geometry, one vector space is transformed into another vector space after linear transformation and translation are performed once.
402. Performing Gaussian pyramid downsampling on the LCD area;
gaussian pyramid down-sampling is a technique for multi-rate digital signal processing or a process for reducing the signal sampling rate, and is commonly used to reduce the data transmission rate or data size.
And performing Gaussian pyramid downsampling on the LCD area to obtain an M-layer downsampling result graph, wherein M is an integer larger than 1.
403. Acquiring a down-sampling response map;
and respectively calculating Hessian matrixes for the M layers of down-sampling result graphs to obtain M down-sampling response graphs.
The Hessian matrix is a square matrix formed by second-order partial derivatives of a multivariate function, describes the local curvature of the function, is commonly used for solving the optimization problem by a Newton method, and can be used for judging the extreme value of the multivariate function by utilizing the Hessian matrix. In the optimization design of the engineering practical problem, the listed objective functions are often complex, in order to simplify the problem, the objective functions are often expanded into taylor polynomials in the neighborhood of a certain point to approximate to the original functions, and at the moment, the functions relate to hessian matrixes in the matrix form of the taylor expansion at the certain point.
404. Determining a target detection image;
and respectively calculating the areas of the maximum response ranges in the M downsampling response graphs to obtain the areas of the M maximum response ranges, respectively calculating the ratio of the area of each maximum response range to the area of the LCD area, and selecting the downsampling result graph corresponding to the downsampling response graph with the maximum ratio as the target detection image.
405. Rejecting non-target detection objects in the target detection image;
and after connecting the non-target detection objects in the target detection image through a closing operation, rejecting the non-target detection objects through threshold segmentation.
The following beneficial effects can be seen from the fourth embodiment:
and extracting a target detection image for subsequent linear defect detection by performing preprocessing operations such as threshold segmentation and Gaussian pyramid downsampling on the LCD image to be detected under the gray scale picture. Compared with the prior art, the method and the device have the advantages that the proper target detection image is selected by adopting the Gaussian pyramid downsampling method, the selection requirement on the target detection image is higher, the quality of the target detection image is guaranteed, and a foundation is laid for improving the linear defect detection accuracy.
EXAMPLE five
Corresponding to the embodiment of the application function realization method, the application also provides electronic equipment for executing the LCD gray scale picture lower line type defect detection method and a corresponding embodiment.
Fig. 12 is a schematic structural diagram of an electronic device shown in an embodiment of the present application.
Referring to fig. 12, 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 (8)
1. A LCD gray scale picture downward line type defect detection method is characterized by comprising the following steps:
obtaining a target detection image according to the LCD image to be detected under the gray scale picture;
respectively carrying out linear interference filtering processing on the target detection image according to N detection angles to obtain N spatial filtering result graphs, wherein N is an integer greater than 1;
respectively carrying out linear defect highlighting processing on the N spatial filtering result graphs to obtain N first filtering response graphs;
the linear defect highlighting treatment comprises the following steps: controlling a first linear filtering kernel and a second linear filtering kernel to respectively perform linear spatial filtering on the spatial filtering result graph to obtain a second filtering response graph and a third filtering response graph, and subtracting the second filtering response graph from the third filtering response graph;
the first linear filter kernel and the second linear filter kernel are square filter kernels, the arrangement directions of filter parameters are the same and are perpendicular to the detection angle direction of the spatial filter result graph, the size of the first linear filter kernel is smaller than that of the second linear filter kernel, and the first filter parameter of the first linear filter kernel is larger than the second filter parameter of the second linear filter kernel;
determining the position of the linear defect according to the N first filter response graphs;
the determining the position of the line type defect according to the N first filter response graphs comprises the following steps:
respectively carrying out linear interference filtering processing according to N detection angles on the N first filtering response graphs to obtain N target response graphs;
respectively carrying out dust filtration on the N target response graphs;
the performing dust filtering on the N target response maps respectively includes:
acquiring an LCD entity graph to be detected, and extracting dust information of the LCD entity graph to be detected through threshold segmentation to obtain a dust response graph;
comparing the dust response diagram with the N target response diagrams respectively, and determining the dust position of each target response diagram;
and respectively eliminating the dust positions of the target response graphs to obtain N response graphs to be segmented, wherein the response graphs to be segmented are binary graphs.
2. The LCD grayscale frame offline defect detection method of claim 1,
the respectively performing linear interference filtering processing according to the N detection angles on the target detection image comprises:
when the ith detection angle is detected on the target detection image, controlling linear filtering cores in the same direction with the rest N-1 detection angles to perform linear spatial filtering on the target detection image, wherein i is an integer greater than 0.
3. The LCD grayscale frame offline defect detection method of claim 1,
after obtaining the N response maps to be segmented, the method includes:
acquiring a minimum rotation circumscribed rectangle of the response region outline in the N response graphs to be segmented;
calculating the width and height values of the response region of the minimum rotation circumscribed rectangle and the area of the response region of the minimum rotation circumscribed rectangle;
comparing the width and height values of the response regions and the areas of the response regions with a linear defect standard mapping table, wherein the linear defect standard mapping table is a set of response region width and height thresholds and response region area thresholds corresponding to the linear defects, and the response region contours are determined under the size of each target detection image;
and determining the position of the linear defect according to the comparison result.
4. The LCD grayscale frame offline defect detection method of claim 1,
the method for obtaining the target detection image according to the LCD image to be detected under the gray scale picture comprises the following steps:
if the LCD image to be detected is an LCD main view, performing threshold segmentation on the LCD image to be detected to obtain an LCD area;
if the LCD image to be detected is an LCD oblique view, after the LCD image to be detected is affine transformed into the LCD main view, threshold segmentation is carried out on the LCD image to be detected, and the LCD area is obtained.
5. The LCD grayscale frame offline defect detection method of claim 4,
after the LCD area is obtained, the method comprises the following steps:
performing Gaussian pyramid downsampling on the LCD area to obtain an M-layer downsampling result graph, wherein M is an integer larger than 1;
respectively calculating Hessian matrixes for the M layers of down-sampling result graphs to obtain M down-sampling response graphs;
respectively calculating the areas of the maximum response ranges in the M downsampling response graphs to obtain M areas of the maximum response ranges;
and respectively calculating the ratio of the area of each maximum response range to the area of the LCD area, and selecting the down-sampling result image corresponding to the down-sampling response image with the maximum ratio as the target detection image.
6. The LCD grayscale frame offline defect detection method of claim 5,
after the down-sampling result image corresponding to the down-sampling response image with the largest ratio is selected as the target detection image, the method comprises the following steps:
and after connecting the non-target detection objects in the target detection image through a closing operation, removing the non-target detection objects through threshold segmentation.
7. 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 1-6.
8. 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 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110275858.9A CN112666733B (en) | 2021-03-15 | 2021-03-15 | LCD gray scale picture offline defect detection method, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110275858.9A CN112666733B (en) | 2021-03-15 | 2021-03-15 | LCD gray scale picture offline defect detection method, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112666733A CN112666733A (en) | 2021-04-16 |
| CN112666733B true CN112666733B (en) | 2021-06-04 |
Family
ID=75399362
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110275858.9A Active CN112666733B (en) | 2021-03-15 | 2021-03-15 | LCD gray scale picture offline defect detection method, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112666733B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103913858A (en) * | 2013-01-07 | 2014-07-09 | 北京兆维电子(集团)有限责任公司 | Filtering method in automatic optical detection of TFT-LCD (thin film transistor-liquid crystal display) screen |
| CN108876733A (en) * | 2018-05-30 | 2018-11-23 | 上海联影医疗科技有限公司 | A kind of image enchancing method, device, equipment and storage medium |
| CN112184744A (en) * | 2020-11-29 | 2021-01-05 | 惠州高视科技有限公司 | Display screen edge defect detection method and device |
| CN112419228A (en) * | 2020-10-14 | 2021-02-26 | 惠州高视科技有限公司 | Method and device for detecting three-dimensional edge defect of cover plate |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP5180608B2 (en) * | 2008-01-30 | 2013-04-10 | 株式会社日立ハイテクノロジーズ | Disk surface defect inspection method and defect inspection apparatus |
-
2021
- 2021-03-15 CN CN202110275858.9A patent/CN112666733B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103913858A (en) * | 2013-01-07 | 2014-07-09 | 北京兆维电子(集团)有限责任公司 | Filtering method in automatic optical detection of TFT-LCD (thin film transistor-liquid crystal display) screen |
| CN108876733A (en) * | 2018-05-30 | 2018-11-23 | 上海联影医疗科技有限公司 | A kind of image enchancing method, device, equipment and storage medium |
| CN112419228A (en) * | 2020-10-14 | 2021-02-26 | 惠州高视科技有限公司 | Method and device for detecting three-dimensional edge defect of cover plate |
| CN112184744A (en) * | 2020-11-29 | 2021-01-05 | 惠州高视科技有限公司 | Display screen edge defect detection method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112666733A (en) | 2021-04-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP4657869B2 (en) | Defect detection apparatus, image sensor device, image sensor module, image processing apparatus, digital image quality tester, defect detection method, defect detection program, and computer-readable recording medium | |
| CN111612781A (en) | Screen defect detection method and device and head-mounted display equipment | |
| CN106027851B (en) | Method and system for processing images | |
| US8391585B2 (en) | Defect detecting device, defect detecting method, image sensor device, image sensor module, defect detecting program, and computer-readable recording medium | |
| CN111968144B (en) | Image edge point acquisition method and device | |
| KR100265875B1 (en) | Method of and apparatus for processing an image | |
| CN112858318B (en) | Method for distinguishing screen foreign matter defect from dust, electronic equipment and storage medium | |
| CN106062824A (en) | Edge detection device, edge detection method, and program | |
| CN113205474A (en) | Screen detection and screen detection model training method, device and equipment | |
| CN113781393B (en) | Screen defect detection method, device, equipment and storage medium | |
| CN113706607B (en) | Subpixel positioning method, computer equipment and device based on circular array diagram | |
| CN117152165B (en) | Photosensitive chip defect detection method and device, storage medium and electronic equipment | |
| CN112802022B (en) | Method for intelligently detecting defective glass image, electronic device and storage medium | |
| CN111476750A (en) | Method, device and system for carrying out stain detection on imaging module and storage medium | |
| JP2011008482A (en) | Defect detection method, defect detection device and defect detection program | |
| CN116503414B (en) | Screen defect detection method, device, computer equipment and storage medium | |
| CN112666733B (en) | LCD gray scale picture offline defect detection method, electronic equipment and storage medium | |
| Yu et al. | Optimized self-adapting contrast enhancement algorithm for wafer contour extraction | |
| CN113272857A (en) | Defect image generating device and method | |
| CN117197527A (en) | Defect detection classification method and device for glass substrate of liquid crystal display screen | |
| CN116071304A (en) | Article edge line positioning method and device and electronic equipment | |
| CN114219758A (en) | Defect detection method, system, electronic device and computer readable storage medium | |
| JP2008171142A (en) | Spot defect detection method and device | |
| CN114119594A (en) | Oil leakage detection method and device based on deep learning | |
| CN111524102A (en) | Method and device for detecting screen contamination of liquid crystal display |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP03 | Change of name, title or address |
Address after: 215163 rooms 101, 102, 901 and 902, floor 1, building 11, 198 Jialingjiang Road, high tech Zone, Suzhou City, Jiangsu Province Patentee 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 Patentee before: HUIZHOU GOVION TECHNOLOGY Co.,Ltd. |
|
| CP03 | Change of name, title or address | ||
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20210416 Assignee: Suzhou Gaoshi Semiconductor Technology Co.,Ltd. Assignor: Gaoshi Technology (Suzhou) Co.,Ltd. Contract record no.: X2021990000430 Denomination of invention: LCD gray scale picture offline defect detection method, electronic equipment and storage medium Granted publication date: 20210604 License type: Common License Record date: 20210722 |
|
| EE01 | Entry into force of recordation of patent licensing contract | ||
| 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. |
|
| CP03 | Change of name, title or address |