CN117351011B - Screen defect detection method, apparatus, and readable storage medium - Google Patents
Screen defect detection method, apparatus, and readable storage medium Download PDFInfo
- Publication number
- CN117351011B CN117351011B CN202311641891.4A CN202311641891A CN117351011B CN 117351011 B CN117351011 B CN 117351011B CN 202311641891 A CN202311641891 A CN 202311641891A CN 117351011 B CN117351011 B CN 117351011B
- Authority
- CN
- China
- Prior art keywords
- image
- defect
- screen
- determining
- target
- 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
- 230000007547 defect Effects 0.000 title claims abstract description 354
- 238000001514 detection method Methods 0.000 title claims abstract description 35
- 238000003860 storage Methods 0.000 title claims abstract description 15
- 238000000034 method Methods 0.000 claims abstract description 26
- 238000010586 diagram Methods 0.000 claims description 20
- 230000000694 effects Effects 0.000 abstract description 11
- 238000005516 engineering process Methods 0.000 abstract description 6
- 230000003287 optical effect Effects 0.000 abstract description 3
- 230000006870 function Effects 0.000 description 19
- 230000002950 deficient Effects 0.000 description 9
- 238000004590 computer program Methods 0.000 description 7
- 238000003708 edge detection Methods 0.000 description 7
- 238000004422 calculation algorithm Methods 0.000 description 6
- 238000004458 analytical method Methods 0.000 description 5
- 238000004891 communication Methods 0.000 description 5
- 238000012986 modification Methods 0.000 description 5
- 230000004048 modification Effects 0.000 description 5
- 238000000605 extraction Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000003044 adaptive effect Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 239000000945 filler Substances 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 230000001629 suppression Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/751—Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30121—CRT, LCD or plasma display
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Geometry (AREA)
- Health & Medical Sciences (AREA)
- Quality & Reliability (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
The application discloses a screen defect detection method, equipment and a readable storage medium, and relates to the field of detection of optical equipment, wherein the method comprises the following steps: determining a binary image corresponding to image information of a screen to be detected, and determining a target contour image according to gray value jump information in the binary image; determining a filling image after gray value filling of the target contour image; performing Gaussian difference processing on the target contour image and the filling image respectively to determine a first defect image and a second defect image; and judging whether a target defect exists or not based on the gray level difference value graph of the first defect image and the gray level difference graph of the second defect image. The technical problem that the defects positioned at the edges of the screen in the related technology are easily misjudged as a part of the contours of the screen, so that the omission ratio is high is effectively solved, and the technical effect of separating the edge defects from the contours and accurately extracting the edge defects is realized.
Description
Technical Field
The present application relates to the field of detection of optical devices, and in particular, to a method and apparatus for detecting a screen defect, and a readable storage medium.
Background
In order to ensure the display effect of VR (Virtual Reality), high-end VR devices use an OLED (Organic Light-Emitting Diode) as a screen material. In order to ensure the display effect of VR, manufacturers need to detect products of the OLED screen when the equipment leaves the factory, and the probability that defective products flow into the market is reduced due to the fact that dead pixels and dirt are not found.
In the related art, a manufacturer generally obtains an image of an OLED screen, calls a machine vision function on the image through a Halcon software library to detect a defect point, and then determines why the defect type is based on the position of the defect point and the gray value of the processed defect point.
However, the edge defect is very close to the contour, and is easily misjudged to be part of the contour in the detection process, so that the defect is difficult to extract, and the omission ratio is high.
Disclosure of Invention
The embodiment of the application solves the technical problem that the defects at the edges of the screen in the related technology are easily misjudged as part of the contours of the screen, so that the omission ratio is high, and the technical effect of separating the edge defects from the contours and accurately extracting the edge defects is realized by providing the method, the device and the readable storage medium for detecting the screen defects.
The embodiment of the application provides a screen defect detection method, which comprises the following steps:
determining a binary image corresponding to image information of a screen to be detected, and determining a target contour image according to gray value jump information in the binary image;
determining a filling image after gray value filling of the target contour image;
performing Gaussian difference processing on the target contour image and the filling image respectively to determine a first defect image and a second defect image;
and judging whether a target defect exists or not based on the gray level difference value graph of the first defect image and the gray level difference graph of the second defect image.
Optionally, the step of determining a binary image corresponding to the image information of the screen to be detected and determining the target contour image according to the gray value jump information in the binary image includes:
performing self-adaptive binarization processing on the image information of the screen to be detected, and determining the binary image;
determining a contour part and a screen part based on adjacent pixel points with gray value jump in the binary image;
when the area of the contour part is larger than or equal to a preset threshold value, determining a target area in the binary image as the target contour image;
Otherwise, executing the step of carrying out self-adaptive binarization processing on the image information of the screen to be detected and determining the binary image.
Optionally, when the area of the contour portion is greater than or equal to a preset threshold, the step of determining the target area in the binary image as the target contour image includes:
when the area of the outline part is larger than or equal to a preset threshold value, determining outline lines corresponding to the outline part and the screen part;
taking the minimum circumscribed rectangle of the contour line as the target area;
and determining the binary image of the target area as the target contour image.
Optionally, the step of performing gaussian difference processing on the target contour image and the filling image respectively to determine a first defect image and a second defect image includes:
determining an effective area corresponding to the target contour image as a first target image;
performing Gaussian difference processing on the first target image to determine first defect information;
and determining the first defect image corresponding to the first defect information based on a binarization threshold.
Optionally, the step of performing gaussian difference processing on the target contour image and the filling image respectively, and determining the first defect image and the second defect image further includes:
Determining an effective area corresponding to the filling image as a second target image;
performing Gaussian difference processing on the second target image to determine second defect information;
and determining the second defect image corresponding to the second defect information based on a binarization threshold.
Optionally, the step of determining whether the target defect exists based on the gray level difference map of the first defect image and the second defect image includes:
subtracting the gray values of the first defect image and the second defect image to determine the gray difference value map;
determining a defect to be selected in a contour line in the gray level difference map;
and judging whether the defect to be selected is the target defect or not based on a matching result of the characteristic value of the defect to be selected and a standard interval.
Optionally, the step of determining the candidate defect in the gray level difference map, which is located in the contour line, includes:
determining a coordinate sequence of a pixel point corresponding to a screen edge contour line in the gray level difference value diagram;
determining pixel coordinates of suspected defects in the gray difference map;
and determining the defect to be selected according to the pixel coordinates and the coordinate sequence.
Optionally, the step of determining whether the defect to be selected is the target defect based on the matching result of the feature value and the standard interval of the defect to be selected includes:
Performing image recognition on the defects to be selected, and determining the characteristic value corresponding to each preset characteristic attribute;
when the characteristic values are all in the standard interval, judging that the defect to be selected is the target defect;
otherwise, judging that the defect to be selected is not the target defect.
In addition, the application also provides a screen defect detection device, which comprises a memory, a processor and a screen defect detection program stored on the memory and capable of running on the processor, wherein the processor realizes the steps of the screen defect detection method when executing the screen defect detection program.
Furthermore, the present application proposes a computer-readable storage medium having stored thereon a screen defect detection program which, when executed by a processor, implements the steps of the screen defect detection method as described above.
One or more technical solutions provided in the embodiments of the present application at least have the following technical effects or advantages:
1. because the binary image corresponding to the image information of the screen to be detected is determined, and the target contour image is determined according to the gray value jump information in the binary image; determining a filling image after gray value filling of the target contour image; performing Gaussian difference processing on the target contour image and the filling image respectively to determine a first defect image and a second defect image; based on the gray level difference value graph of the first defect image and the second defect image, whether the target defect exists or not is judged, so that the technical problem that the defect positioned at the edge of the screen in the related technology is easily misjudged to be a part of the contour of the screen, and the omission ratio is high is effectively solved, and the technical effects of separating the edge defect from the contour and accurately extracting the edge defect are achieved.
2. The gray value of the first defect image which is obtained by further Gaussian difference determination of the target contour image and the gray value of the second defect image which is obtained by Gaussian difference determination after gray value filling of the target contour image are adopted, and the gray values of the first defect image and the second defect image are subtracted to determine the gray difference image; determining a defect to be selected in a contour line in the gray level difference map; and judging whether the defect to be selected is the target defect or not based on a matching result of the characteristic value of the defect to be selected and a standard interval. The method effectively solves the technical problem that when the binary image is analyzed in the related technology, the binarized pixels of the defect are easy to adhere to the outline of the screen, so that the defect is misjudged as a part of the outline, and further the technical effect of separating the defect from the outline in the binary image is achieved.
Drawings
FIG. 1 is a flowchart of a screen defect detection method according to an embodiment of the present disclosure;
FIG. 2 is a diagram illustrating image information of a screen to be inspected according to a first embodiment of the present disclosure;
FIG. 3 is a schematic diagram of a target contour image according to a first embodiment of a screen defect detection method of the present application;
FIG. 4 is a schematic diagram of a filling image in a first embodiment of a screen defect detection method according to the present application;
FIG. 5 is a schematic diagram of a first defect image in a third embodiment of a screen defect detection method according to the present application;
FIG. 6 is a schematic diagram of a second defect image in a third embodiment of a screen defect detection method according to the present application;
fig. 7 is a schematic flowchart of refinement of step S140 in the fourth embodiment of the screen defect detection method of the present application;
FIG. 8 is a diagram of a gray scale difference map in a fourth embodiment of a screen defect detection method according to the present application;
FIG. 9 is a diagram of an image with a defect to be selected in a fourth embodiment of a screen defect detection method of the present application;
fig. 10 is a schematic diagram of a hardware structure related to an embodiment of the screen defect detecting apparatus of the present application.
Detailed Description
In the related art, when the VR screen detects, because the edge defect is too close to the outline of the interface of the screen and the shell, when the defect position is positioned, the defect and the outline are adhered when the Gaussian filter is performed, so that the defect problem of the screen cannot be accurately extracted, and defective products are caused to flow into the market. The main technical scheme adopted by the embodiment of the application is as follows: firstly, a binary image is determined according to image information of a screen to be detected, a contour line is determined according to the binary image, then a target contour image is determined according to the vicinity of the contour line as a target area, two defect images are determined according to the target contour image and the filled image, further Gaussian difference and binarization, and then a binarization image of defect and contour separation is determined according to the binarization difference of the two defect images. Therefore, the technical effects of separating the edge defects from the outline and accurately extracting the edge defects are achieved, the accuracy is effectively increased while the same time consumption is ensured, the omission ratio is reduced, and the method is convenient to apply in engineering.
In order to better understand the above technical solution, exemplary embodiments of the present application will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present application are shown in the drawings, it should be understood that the present application can 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.
Example 1
An embodiment of the present application discloses a method for detecting a screen defect, referring to fig. 1, the method for detecting a screen defect includes:
step S110, a binary image corresponding to the image information of the screen to be detected is determined, and a target contour image is determined according to gray value jump information in the binary image.
In this embodiment, the screen to be detected is not limited to the display screen of the VR device, and the material thereof is not limited to the OLED. When the screen has edges, both are applicable to the present method. The image information is a picture of the screen to be detected, which is acquired by the image acquisition module, and the picture can completely comprise the whole screen to be detected, or can be a picture containing the corresponding areas of the edges of the upper, lower, left and right sides of the screen to be detected. The binary image is an image obtained by binarizing image information, wherein the gray value of each pixel is 0 or 255, namely black and white. And then according to the gray value of each pixel, the adjacent pixel points with gray value jump can be determined, and then all or part of the outline of the screen to be detected can be determined by the pixel points. The target contour image is a binary image containing all or part of the contour of the screen to be detected.
As an alternative embodiment, the screen to be detected is placed on a preset rack, and the image information of the screen to be detected is collected by using the image collecting device, and referring to fig. 2, the image information at least includes the screen to be detected and a screen contour. According to a self-defined binarization algorithm, carrying out gray value binarization on each pixel point in the image information, determining a binary image, and determining a contour line based on adjacent pixel points with gray value conversion in the binary image, wherein gray values on two sides of the contour line are different. Due to the limitation of the screen image information to be detected, the pixel duty ratio of the device shell which belongs to the outer side of the screen in the binary image is not larger than the pixel duty ratio which belongs to the screen. At the moment, the screen and the shell are distinguished according to the contour line determined by the binary image, and when the area of the pixel point belonging to the shell is larger than a preset threshold value, the contour line corresponding to the binary image is determined to be effective. At this time, the binary image is taken as a target contour image, and fig. 3 is referred to.
As another alternative implementation manner, after determining that the contour line of the binary image is valid, the image corresponding to the binary image may be appropriately cut, so that the pixel duty ratio of the screen is further increased, that is, four sides of the image are cut at equal distances, and the length of each cut edge is related to the area duty ratio of the shell, that is, the contour portion.
Illustratively, the length of the crop is the minimum distance of the image edge to the contour line.
In this embodiment, the collection range of the image collection device may be updated according to the length of clipping in the historical working information, that is, the collection range of the image collection device may be updated according to the historical working information, so that the pixel duty ratio of the collected image information belonging to the shell is reduced, and the computing power is reduced.
Step S120, determining a filling image after gray value filling of the target contour image.
In this embodiment, the filling image is also a binary image, and is used for filling the gray values belonging to the corresponding pixels of the screen in the target contour image.
Illustratively, a screen portion and a contour portion in the target contour image are determined, wherein the screen portion corresponds to a pixel point of the screen portion and the contour portion corresponds to a pixel point outside the screen portion. The pixel points corresponding to the screen part are determined, the gray values of the pixel points of the screen part are filled according to the gray values 255, a filling image is generated, and referring to fig. 4, fig. 4 is a filling image obtained by filling the gray values 255 of the pixel points of the screen part in fig. 3.
And step S130, performing Gaussian difference processing on the target contour image and the filling image respectively to determine a first defect image and a second defect image.
In the present embodiment, the gaussian difference is an edge detection method used in image processing and computer vision. Based on the principle of Gaussian filtering and differential operation, the method can effectively detect boundary and detail information in the image. Specifically, the gaussian difference algorithm first gaussian filters the original image to smooth the image and suppress noise. Then, convolution is performed on the images using gaussian kernel images of different scales to obtain a set of filtered images. And then, carrying out differential operation on the filtered images of the two adjacent scales to obtain an edge intensity or edge response image. Finally, boundaries in the image can be extracted by performing non-maximum suppression and thresholding on the resulting edge-responsive image. The Gaussian difference algorithm has the advantages of being capable of detecting fine boundary details in an image, providing a wider edge response range and having certain robustness to noise. Therefore, it is widely used in tasks such as edge detection, object detection, feature point extraction, and the like in image processing and computer vision. The defect image is an image which highlights defect information, and may be a binary image or a picture containing defect marks.
As an alternative implementation manner, based on the target contour image or the effective image corresponding to the target contour image, performing gaussian difference processing on the image to obtain an image with prominent defect information, and further binarizing the image to obtain a binary image with prominent defect information, namely the first defect image. And similarly, carrying out Gaussian difference processing on the filling image or an effective image corresponding to the filling image to obtain an image with prominent defect information, and further binarizing the image to obtain a binary image with prominent defect information, namely a second defect image.
Step S140, determining whether a target defect exists based on the gray level difference map of the first defect image and the second defect image.
In the present embodiment, differentiating the two binary maps may highlight a difference portion between the two binary maps. Further eliminating the sticking of the defect and the screen contour, so that the defect and the screen contour are separated in the binary image. And then, according to the two-value graph with the adhesion eliminated, determining the position of the defect in the image, further carrying out image recognition on the image information of the screen to be detected, and determining whether the defect exists at the corresponding position.
Illustratively, a first defect image a and said second defect image B are read in. Element-by-element operation at the pixel level is performed on image a and image B, and the difference is calculated to obtain the pixel value of image C. If the corresponding pixels of A and B are both 0 or both 1, then the corresponding pixel of C is 0. If the corresponding pixel of A is 0 and the corresponding pixel of B is 1, then the corresponding pixel of C is 1. If the corresponding pixel of A is 1 and the corresponding pixel of B is 0, then the corresponding pixel of C is-1 or 255, depending on the particular situation. If the binary image is stored using 0 and 255 to represent 0 and 1, then the difference may be made by assigning the inconsistent pixel value to 255 to highlight the different portions.
Further, binarization processing is performed on the difference image C, and non-zero pixels are set to 1 to obtain a binary difference image D. The difference image C or the binary difference image D is rendered or displayed to observe a difference portion between the two binary maps.
As an alternative implementation manner, referring to fig. 5, after determining the difference portion, that is, the gray difference value graph, according to a pixel point in the gray difference value graph, which is opposite to a gray value of a pixel point corresponding to the screen portion, determining the pixel point as a suspected defect, determining position information of the suspected defect, performing image recognition on image information of a screen to be detected, obtaining a feature value of the suspected defect, and determining whether the suspected feature is a target feature according to a matching condition of the feature value and a preset feature threshold.
For example, when the feature value is within the preset feature threshold, determining that the suspected feature is the target feature; otherwise, determining the suspected feature as a normal screen. The preset characteristic threshold value is a characteristic value interval in which the defective screen pixel points exist, and can be an open interval or a closed interval.
In this embodiment, the screen image information to be detected is read in and converted into a gray image. And (3) performing binarization processing according to a certain threshold value, and converting the gray level image into a binary image. The foreground and background on the screen are determined by a threshold. In the binary image, jump information of gray values is detected, and a target contour is found. The contours can be obtained using the findContours function in OpenCV. And drawing a filling outline on a new black image according to the found target outline, and generating a filling image. Contours can be drawn using the drawContours function in OpenCV. This results in a filled-in image for subsequent processing. And respectively carrying out Gaussian blur processing on the target contour image and the filling image. Gaussian blur can remove noise and smooth the image. And carrying out differential operation on the original image and the Gaussian blurred image. This makes it possible to obtain a first defective image for highlighting defective portions in the original image. And performing differential operation on the filled image and the Gaussian blurred image of the filled image. This allows a second defect image to be obtained for detecting defective portions in the filled image. Based on the gray level difference map of the first defect image and the second defect image, an appropriate threshold may be set to determine whether the target defect exists. And comparing the average value or the proper statistical characteristic of the gray level difference value diagram with a preset threshold value, judging that the target defect exists if the threshold value is exceeded, and otherwise, detecting no defect.
The technical scheme in the embodiment of the application at least has the following technical effects or advantages:
because the binary image corresponding to the image information of the screen to be detected is determined, and the target contour image is determined according to the gray value jump information in the binary image; determining a filling image after gray value filling of the target contour image; performing Gaussian difference processing on the target contour image and the filling image respectively to determine a first defect image and a second defect image; based on the gray level difference value graph of the first defect image and the second defect image, whether the target defect exists or not is judged, so that the technical problem that the defect positioned at the edge of the screen in the related technology is easily misjudged to be a part of the contour of the screen, and the omission ratio is high is effectively solved, and the technical effects of separating the edge defect from the contour and accurately extracting the edge defect are achieved.
Based on the first embodiment, a second embodiment of the present application provides a method for detecting a screen defect, and step S110 includes:
step S210, performing self-adaptive binarization processing on the image information of the screen to be detected, and determining the binary image.
In this embodiment, features of pixels of image information are extracted, a binarization threshold is determined according to the features, and gray values corresponding to each pixel are determined based on each pixel and the binarization threshold, so as to generate a binary image of the image information.
Illustratively, it is converted into a binary image, and pixels having a gray value greater than the threshold T are set to white (255), and pixels having a gray value less than or equal to the threshold T are set to black (0). In this example, the picture is first read in grayscale mode using the cv2.Imread function. Then, a threshold is defined that determines which pixels in the image should be considered foreground (white) or background (black). Next, the image is binarized using a cv2.Threshold function, and a binary image is returned as a result. Finally, the binary image is displayed using the cv2.imshowe function. The cv2.Imread function is one of the most basic and common methods in the OpenCV Python library for reading image files and converting them into numpy arrays. numpy (Numerical Python, number) is an open source Numerical calculation extension of Python. Such tools can be used to store and process large matrices. The three parameters of this function are the path, read mode and channel number of the image file, respectively.
As an alternative embodiment, the acquired color image is converted into a gray image, the tri-primary color values of the color image are weighted and averaged by using a graying algorithm, and the gray image is binarized by using an adaptive threshold. The self-adaptive thresholding is to determine a threshold according to the gray value of a local area of an image, namely, dividing a picture corresponding to image information into a plurality of areas, and regarding pixel points in each area, taking the average value of three primary color values in the area as a binarization threshold of the area, so as to determine the gray value corresponding to each pixel point. And determining a binary image of the region of interest in the image according to the binary image obtained after the self-adaptive thresholding.
As another optional implementation manner, dividing the picture corresponding to the image information into a plurality of areas, and regarding the pixel point in each area, taking the average value of the trichromatic values in the area as the local threshold value of the area; acquiring the average value of the tristimulus values of each pixel point in the image information as a global threshold value; determining the weight of each region and the weight corresponding to the global threshold, and determining the weighted threshold according to the global threshold, the local threshold and the corresponding weight value; and determining the gray value of each pixel point based on the weighted threshold value, and further determining a binary image corresponding to the image information.
Illustratively, when the tristimulus value of the pixel point is greater than the weighting threshold, it is determined to be 1, i.e., 255; otherwise, the gray value of the pixel point is determined to be 0. And further determining a binary image corresponding to the image information.
As another alternative implementation way, gaussian difference processing is carried out on the image information, suspected defects are determined according to the processed image, the average value of the tristimulus values of the pixels in the neighborhood determined by the suspected defects is determined to be a local threshold value, wherein the neighborhood completely wraps the suspected defects and is in a round shape or a shape formed by enclosing an arc and an image boundary. Acquiring the average value of the tristimulus values of each pixel point in the image after Gaussian difference processing as a global threshold value; determining the weight of each region and the weight corresponding to the global threshold, and determining the weighted threshold according to the global threshold, the local threshold and the corresponding weight value; and determining the gray value of each pixel point based on the weighted threshold value, and further determining a binary image corresponding to the image information. Wherein the sum of the weight of each local threshold and the weight of the global threshold is 1.
Step S220, determining a contour part and a screen part based on the adjacent pixel points with the gray value jump in the binary image.
In this embodiment, each pixel point and surrounding pixels are traversed, adjacent pixels with gray value jump are determined, the pixels with gray value 255 or gray value 0 are used as target pixels, the target pixels are connected in series according to the adjacent pixels, a screen contour is determined, and a binary image is divided into a screen portion and a contour portion according to the screen contour, wherein the contour portion is an area except the screen portion. At this time, various situations may occur, for example, the target pixel points enclose a closed pattern, and the gray values of the pixel points in the closed pattern are inconsistent with those of the pixel points in the normal area of the screen, that is, the closed pattern is used as a suspected defect. For example, the target pixel points are connected in series to form a curve, and the curve is regarded as a contour line.
And step S230, when the area of the contour part is larger than or equal to a preset threshold value, determining a target area in the binary image as the target contour image.
In the present embodiment, when the area of the contour portion is greater than or equal to a preset threshold value set in advance, a binary image is determined as the target contour image. Or the four sides of the binary image are cut equidistantly, so that the area of the outline part is reduced as much as possible. Because the defect of sticking to the outline appears to protrude inwards, the cutting of the four sides of the binary image does not affect the corresponding position of the defect. The picture is cut, so that more pixel points occupied by defect information can be occupied as much as possible, and the recognition accuracy is improved.
Step S240, if not, executing the step of performing adaptive binarization processing on the image information of the screen to be detected, and determining the binary image.
In this embodiment, if the area of the contour portion is not greater than the preset threshold, the binarization is considered as failure, the binarization threshold is redetermined, the image information is binarized, and the binary image is determined until the condition shown in step S230 is satisfied.
As an alternative embodiment, the image information of the screen to be detected is read in. And performing self-adaptive binarization processing on the image information to obtain a binary image. And carrying out edge detection on the binary image, and finding out adjacent pixel points with gray value jump as an outline. And calculating the area of the contour, and taking the contour as a target contour image if the area is larger than a preset threshold value. And if the area of the contour is not greater than the preset threshold value, returning to the step 2, and carrying out self-adaptive binarization processing again to determine a new binary image. The target contour image may be further processed, such as filtering, morphological operations, etc., as desired.
Optionally, step S230 includes:
and step S231, when the area of the outline part is larger than or equal to a preset threshold value, determining outline lines corresponding to the outline part and the screen part.
In this embodiment, when the area of the contour portion is greater than or equal to the preset threshold, it indicates that the result of binarizing the image by the selected binarization threshold meets the requirement of performing defect detection, because when the area of the contour portion is too small, a part of the contour portion is easily taken as a defect on the screen, and erroneous judgment is caused. Therefore, when the area of the contour part is larger than or equal to a preset threshold value, a pixel point at the center position of the picture is taken as a screen part according to the contour line, and a contour line corresponding to the screen part is determined.
And step S232, taking the minimum circumscribed rectangle of the contour line as the target area.
In this embodiment, based on up-down-left-right or other dividing methods, the binary image is divided into a plurality of target binary images that do not overlap each other, and then, for each target binary image, a minimum circumscribed rectangle based on a contour line is used as a target area.
Step S233, determining the binary image of the target area as the target contour image.
In this embodiment, after the target area is divided, a binary image corresponding to the target area is used as the target contour image.
For each found contour, its corresponding area is calculated, for example. The area of the outline may be calculated using the contourArea function of OpenCV. A threshold value is preset according to the requirement, and the threshold value represents the minimum value of the area of the contour. For example, the target area may be marked when the area of the contour is set to 100 pixels or more. Traversing all contours, and determining the minimum bounding rectangle of the contour with the area larger than or equal to a preset threshold value, wherein the minimum bounding rectangle can be obtained by using a minAreRect function of OpenCV. And drawing the minimum circumscribed rectangle of the target area onto a new image to form a target contour image. And displaying the target contour image to view the processing result.
In this embodiment, a binary image is determined according to image information of a screen to be detected, and whether a target contour image exists is determined by detecting the area of a contour region. According to different application requirements, the follow-up processing or the re-adaptive binarization processing can be performed according to the target contour image.
Based on the first embodiment, a third embodiment of the present application provides a method for detecting a screen defect, and step S130 includes:
step S310, determining an effective area corresponding to the target contour image as a first target image.
In this embodiment, the effective area refers to an area in the target contour image that meets the condition, and may be the target contour image itself.
As an alternative embodiment, the target contour image is taken as the first target image.
As another optional implementation manner, determining a contour line in the target contour image, and taking an image corresponding to the minimum circumscribed rectangle of the contour line as an effective area, namely the first target image.
Step S320, performing gaussian differential processing on the first target image, and determining first defect information.
In the present embodiment, the first defect information refers to an image containing prominent defect information.
Step S330, determining the first defect image corresponding to the first defect information based on a binarization threshold.
As an alternative embodiment, a target contour image is acquired, and the target contour image is a binary image. Contours in the image are found using functions in the image processing software or programming language. This step may be implemented using the findContours function in OpenCV. For each found contour, its smallest bounding rectangle is determined. The minimum bounding rectangle may be obtained using the minAreatact function of OpenCV, and the first target image may be subjected to Gaussian difference processing as the first target image, and the Gaussian Blur function of OpenCV may be used. This step can help to highlight defect information in the image. The first defect image is determined using a binarization threshold according to a preset condition, referring to fig. 5. Thresholding may be performed using the threshold function of OpenCV.
In this embodiment, the contours may be further processed, analyzed, or screened, or other image processing techniques may be used to extract defect information. The present embodiment is not limited to a specific defect extraction method.
Step S340, determining an effective area corresponding to the filling image as a second target image.
In this embodiment, the effective area refers to an area in the filled image that meets the condition, and may be the filled image itself.
As an alternative embodiment, the filler image is used as the first target image.
As another optional implementation manner, determining a contour line in the filling image, and taking an image corresponding to the minimum circumscribed rectangle of the contour line as an effective area, namely the first target image.
And step S350, performing Gaussian difference processing on the second target image to determine second defect information.
In this embodiment, the second defect information is substantially an outline portion corresponding image, and is the pixel points of the outline portion and the outline line according to the binarized and determined information.
Step S360, determining the second defect image corresponding to the second defect information based on a binarization threshold.
As an alternative embodiment, a binary image corresponding to the filling image is determined, wherein the contour line of an object is included. And determining an effective area corresponding to the contour line, and extracting defect information of the area. The minimum bounding rectangle of the contour is used to determine the active area. The minimum bounding rectangle is the smallest rectangle that can completely enclose the contour. And calculating the position and the size of the minimum circumscribed rectangle, and taking the position and the size as an effective area. And carrying out Gaussian difference processing on the second target image. By subtracting the original image from the Gaussian filtered image, an image is obtained that highlights the change. In the gaussian differential image, second defect information is determined. Such information may be a brightness change or a color change, etc. We can use thresholding to convert the gaussian difference image into a binary image, where the defective areas are marked white and the other areas black. Finally, a second defect image is obtained, see fig. 6, in which only defect information in the second target image is included. This image can be used for further analysis and processing.
In this embodiment, the effective area of the target contour image or the filling image is determined, so that the pixel portion of the screen portion is further highlighted, the interference of the contour portion and the contour line is reduced, the first or second target image is determined, the target contour image and the filling image are further subjected to gaussian difference processing, and then binarization processing is performed to determine the first defect image and the second defect image, so that the defect information and the contour portion information of the screen portion are both highlighted.
Based on the first embodiment, a fourth embodiment of the present application proposes a method for detecting a screen defect, referring to fig. 7, step S140 includes:
step S410, subtracting the gray values of the first defect image and the second defect image, and determining the gray difference map.
In this embodiment, the sizes of the first defect image and the second defect image are consistent, the pixel coordinates of each pixel are consistent, and then a gray level difference map is determined according to the difference between the gray level values of the corresponding pixels, and referring to fig. 8, the gray level difference map further removes the pixel values corresponding to the contour portion. Since the first defect image is substantially the defect information of the screen part and the second defect image is substantially the defect information of the contour part, the defect which is adhered to the contour line originally is separated from the contour line in the gray level difference value diagram obtained by difference between the first defect image and the second defect image.
Step S420, determining a defect to be selected in the contour line in the gray level difference map.
In this embodiment, since the defect of sticking of the contour line is separated from the contour line, the defect in the gray level difference map is displayed in the form of a closed pattern, and the gray level of the defect portion is 255 on the assumption that the gray level of the normal region is 0, which is represented as a white bright block in the map. These bright blocks are used as candidate defects. And determining the position information of the defect to be selected in the screen to be tested according to the pixel coordinates corresponding to the defect to be selected.
Optionally, step S420 includes:
step S421, determining a coordinate sequence of a pixel point corresponding to a screen edge contour line in the gray level difference map;
step S422, determining the pixel coordinates of the suspected defect in the gray level difference map;
step S423, determining the candidate defect according to the pixel coordinates and the coordinate sequence.
In this embodiment, the contour line corresponding pixel point and the suspected defective pixel point are already determined, so that a coordinate sequence is generated according to the contour line corresponding pixel point, and the pixel coordinate of the suspected defective center pixel point is determined; the suspected defect with the pixel coordinate within the coordinate frame corresponding to the coordinate sequence is taken as the candidate defect, and referring to fig. 9, fig. 9 is the candidate defect determined according to fig. 7.
As an optional implementation manner, determining a coordinate sequence of a pixel point corresponding to a screen edge contour line in the gray level difference map: and processing the gray level difference image by using an edge detection algorithm, such as Canny edge detection, so as to obtain a binarized edge image. And carrying out connected region analysis on the edge map to find all the connected regions. And traversing each connected region, finding the coordinates of the pixel points closest to the image edge, and adding the coordinates into a coordinate sequence. And (3) carrying out binarization processing on the gray level difference value graph, selecting a proper threshold value, setting the pixel with the brightness higher than the threshold value as 255, and setting other pixels as 0. And (3) carrying out connected region analysis on the binarized image, and finding out each connected region, wherein the connected region is the suspected defect. And traversing each connected region, finding the coordinates of the central pixel point of each connected region, and adding the coordinates into a coordinate sequence. For each pixel coordinate of the suspected defect, its shortest distance to all points in the coordinate sequence is calculated. If the shortest distance is less than a certain threshold, the pixel coordinates are determined as the defects to be selected.
Step S430, judging whether the defect to be selected is the target defect or not based on the matching result of the characteristic value of the defect to be selected and the standard interval.
In this embodiment, image analysis is performed on an original image corresponding to the gray level difference image, each feature value of the feature to be selected is determined, when the feature value is matched with the standard interval, the defect to be selected is determined to be a target defect, otherwise, the defect to be selected is determined to be misjudged, and the screen is a normal screen.
Optionally, step S430 includes:
step S431, performing image recognition on the defect to be selected, and determining the feature value corresponding to each preset feature attribute.
In this embodiment, after determining the suspected defect based on the gray level difference map, determining a neighborhood corresponding to the suspected defect, that is, a suspected defect area, positioning a corresponding position area of the image information corresponding to the screen to be detected according to the suspected defect area, and extracting feature information, such as a gray level value, an area, and the like, of the suspected defect by performing image recognition on the position area. And acquiring standard information corresponding to each piece of characteristic information, and determining that the suspected defect is a true defect when the characteristic information is matched with the corresponding standard information, or determining that the suspected defect is a normal region when the suspected defect is misjudged.
And step S432, when the characteristic values are all in the standard interval, judging that the defect to be selected is the target defect.
Step S433, if not, determining that the candidate defect is not the target defect.
As an alternative embodiment, the characteristic properties, such as size, shape, color, etc., are preset for the target defect. For each preset characteristic attribute, a standard interval is set, including a minimum value and a maximum value. For example, for a size feature attribute, the standard interval may be between 20-50 pixels. For each defect to be selected, a region is extracted on the original image with the pixel coordinates of the defect to be selected as the center. And extracting the characteristics of the extracted region, and calculating corresponding characteristic values according to preset characteristic attributes. For example, for the size feature attribute, the number of pixels of the extraction area is calculated. And comparing the corresponding characteristic value with a preset standard interval for each characteristic attribute. And if all the characteristic values of the defects to be selected are in the standard interval, judging the defects to be selected as target defects. Otherwise, it is determined that the candidate defect is not the target defect.
In this embodiment, the feature extraction and feature value determination methods may be adjusted and optimized according to the specific requirements and the characteristics of the target defects. Different image processing and analysis methods can be used to extract more accurate features and set a proper standard interval to judge whether the feature attribute of the target defect meets the requirement.
As an example of the present embodiment, a first defect image and a second defect image are acquired, each pixel is traversed, a gradation difference value of a corresponding position is calculated, and a gradation difference map is generated. The calculation was performed using the following formula: gray difference = pixel gray value on the second defect image-pixel gray value on the first defect image. And processing the gray level difference value graph, and removing pixel values corresponding to the contour part. And using an edge detection algorithm, such as Canny edge detection, to find out the contour line in the gray level difference value graph, and setting the corresponding pixel value to zero. Bright block areas in the gray difference map are found, which represent possible defects. And (3) carrying out binarization processing on the gray level difference value graph, selecting a proper threshold value, setting the pixel with the brightness higher than the threshold value as 255, and setting other pixels as 0. And carrying out connected region analysis on the binarized gray level difference map, and finding out the position information of each connected region, such as the central coordinate of the region or the circumscribed rectangle of the region. And determining the position of the defect in the screen to be tested according to the position information of the defect to be selected. And extracting the characteristics of the original image corresponding to the gray level difference value graph, and extracting the characteristic value of each defect to be selected. Features may include the area, perimeter, shape, etc. of the defect. And matching the characteristic value of the defect to be selected with a standard interval defined in advance. The standard interval is defined according to the range of characteristic values of known target defect and normal area. If the characteristic value of the defect to be selected is matched with the standard interval, judging that the defect is a target defect; otherwise, the defect is determined as a false judgment, i.e., a normal screen.
The gray value of the first defect image which is obtained by further Gaussian difference determination of the target contour image and the gray value of the second defect image which is obtained by Gaussian difference determination after gray value filling of the target contour image are adopted, and the gray values of the first defect image and the second defect image are subtracted to determine the gray difference image; determining a defect to be selected in a contour line in the gray level difference map; and judging whether the defect to be selected is the target defect or not based on a matching result of the characteristic value of the defect to be selected and a standard interval. The method effectively solves the technical problem that when the binary image is analyzed in the related technology, the binarized pixels of the defect are easy to adhere to the outline of the screen, so that the defect is misjudged as a part of the outline, and further the technical effect of separating the defect from the outline in the binary image is achieved.
The application further provides a screen defect detection device, referring to fig. 10, fig. 10 is a schematic structural diagram of the screen defect detection device in a hardware running environment according to an embodiment of the application.
As shown in fig. 10, the screen defect detecting apparatus may include: a processor 1001, such as a central processing unit (Central Processing Unit, CPU), a communication bus 1002, a user interface 1003, a network interface 1004, a memory 1005. Wherein the communication bus 1002 is used to enable connected communication between these components. The user interface 1003 may include a Display, an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may further include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a WIreless interface (e.g., a WIreless-FIdelity (WI-FI) interface). The Memory 1005 may be a high-speed random access Memory (Random Access Memory, RAM) Memory or a stable nonvolatile Memory (NVM), such as a disk Memory. The memory 1005 may also optionally be a storage device separate from the processor 1001 described above.
It will be appreciated by those skilled in the art that the structure shown in fig. 10 does not constitute a limitation of the screen defect detection apparatus, and may include more or fewer components than shown, or may combine certain components, or may have a different arrangement of components.
Optionally, the memory 1005 is electrically connected to the processor 1001, and the processor 1001 may be configured to control operation of the memory 1005, and may also read data in the memory 1005 to implement screen defect detection.
Alternatively, as shown in fig. 10, an operating system, a data storage module, a network communication module, a user interface module, and a screen defect detection program may be included in the memory 1005 as one storage medium.
Alternatively, in the screen defect detecting apparatus shown in fig. 10, the network interface 1004 is mainly used for data communication with other apparatuses; the user interface 1003 is mainly used for data interaction with a user; the processor 1001 and the memory 1005 in the screen defect detection apparatus of the present application may be provided in the screen defect detection apparatus.
As shown in fig. 10, the screen defect detecting apparatus calls a screen defect detecting program stored in a memory 1005 through a processor 1001, and performs the related step operations of the screen defect detecting method provided in the embodiment of the present application:
Determining a binary image corresponding to image information of a screen to be detected, and determining a target contour image according to gray value jump information in the binary image;
determining a filling image after gray value filling of the target contour image;
performing Gaussian difference processing on the target contour image and the filling image respectively to determine a first defect image and a second defect image;
and judging whether a target defect exists or not based on the gray level difference value graph of the first defect image and the gray level difference graph of the second defect image.
Alternatively, the processor 1001 may call the screen defect detection program stored in the memory 1005, and also perform the following operations: performing self-adaptive binarization processing on the image information of the screen to be detected, and determining the binary image;
determining a contour part and a screen part based on adjacent pixel points with gray value jump in the binary image;
when the area of the contour part is larger than or equal to a preset threshold value, determining a target area in the binary image as the target contour image;
otherwise, executing the step of carrying out self-adaptive binarization processing on the image information of the screen to be detected and determining the binary image.
Alternatively, the processor 1001 may call the screen defect detection program stored in the memory 1005, and also perform the following operations: when the area of the outline part is larger than or equal to a preset threshold value, determining outline lines corresponding to the outline part and the screen part;
Taking the minimum circumscribed rectangle of the contour line as the target area;
and determining the binary image of the target area as the target contour image.
Alternatively, the processor 1001 may call the screen defect detection program stored in the memory 1005, and also perform the following operations: determining an effective area corresponding to the target contour image as a first target image;
performing Gaussian difference processing on the first target image to determine first defect information;
and determining the first defect image corresponding to the first defect information based on a binarization threshold.
Alternatively, the processor 1001 may call the screen defect detection program stored in the memory 1005, and also perform the following operations: determining an effective area corresponding to the filling image as a second target image;
performing Gaussian difference processing on the second target image to determine second defect information;
and determining the second defect image corresponding to the second defect information based on a binarization threshold.
Alternatively, the processor 1001 may call the screen defect detection program stored in the memory 1005, and also perform the following operations: subtracting the gray values of the first defect image and the second defect image to determine the gray difference value map;
Determining a defect to be selected in a contour line in the gray level difference map;
and judging whether the defect to be selected is the target defect or not based on a matching result of the characteristic value of the defect to be selected and a standard interval.
Alternatively, the processor 1001 may call the screen defect detection program stored in the memory 1005, and also perform the following operations:
determining a coordinate sequence of a pixel point corresponding to a screen edge contour line in the gray level difference value diagram;
determining pixel coordinates of suspected defects in the gray difference map;
and determining the defect to be selected according to the pixel coordinates and the coordinate sequence.
Alternatively, the processor 1001 may call the screen defect detection program stored in the memory 1005, and also perform the following operations:
performing image recognition on the defects to be selected, and determining the characteristic value corresponding to each preset characteristic attribute;
when the characteristic values are all in the standard interval, judging that the defect to be selected is the target defect;
otherwise, judging that the defect to be selected is not the target defect.
In addition, the embodiment of the application also provides a computer readable storage medium, wherein the computer readable storage medium stores a screen defect detection program, and the screen defect detection program realizes the relevant steps of any embodiment of the screen defect detection method when being executed by a processor.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flowchart and/or block of the flowchart illustrations and/or block diagrams, and combinations of flowcharts and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It should be noted that in the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The application may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The usage of the words first, second and third, etcetera do not indicate any ordering. These words may be interpreted as names.
While preferred embodiments of the present application have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. It is therefore intended that the following claims be interpreted as including the preferred embodiments and all such alterations and modifications as fall within the scope of the application.
It will be apparent to those skilled in the art that various modifications and variations can be made in the present application without departing from the spirit or scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the claims and the equivalents thereof, the present application is intended to cover such modifications and variations.
Claims (9)
1. A screen defect detection method, characterized in that the screen defect detection method comprises:
performing self-adaptive binarization processing on image information of a screen to be detected, and determining a binary image;
determining a contour part and a screen part based on adjacent pixel points of gray value jump in the binary image, wherein the screen part corresponds to the pixel points of the screen part, and the contour part corresponds to the pixel points outside the screen part;
when the area of the outline part is larger than or equal to a preset threshold value, determining outline lines corresponding to the outline part and the screen part;
Taking the minimum circumscribed rectangle of the contour line as a target area;
determining a binary image of the target area as a target contour image;
filling pixel points of the screen part in the target contour image based on the gray value 255 to generate a filling image;
performing Gaussian difference processing on the target contour image and the filling image respectively to determine a first defect image and a second defect image, wherein the first defect image and the second defect image are binary images;
and judging whether a target defect exists or not based on gray level difference maps of the first defect image and the second defect image, wherein gray level values of the first defect image and the second defect image are subtracted, and the gray level difference maps are determined.
2. The screen defect detecting method of claim 1, wherein after the step of determining the contour lines corresponding to the contour portion and the screen portion when the area of the contour portion is greater than or equal to a preset threshold value, comprising:
otherwise, executing the self-adaptive binarization processing of the image information of the screen to be detected, and determining a binary image.
3. The screen defect detection method of claim 1, wherein the step of determining the first defect image and the second defect image by performing gaussian differential processing on the target contour image and the fill image, respectively, comprises:
Determining an effective area corresponding to the target contour image as a first target image;
performing Gaussian difference processing on the first target image to determine first defect information;
and determining the first defect image corresponding to the first defect information based on a binarization threshold.
4. The screen defect detection method of claim 1, wherein the step of determining the first defect image and the second defect image by performing gaussian differential processing on the target contour image and the fill image, respectively, further comprises:
determining an effective area corresponding to the filling image as a second target image;
performing Gaussian difference processing on the second target image to determine second defect information;
and determining the second defect image corresponding to the second defect information based on a binarization threshold.
5. The screen defect detection method of claim 1, wherein the step of determining whether a target defect exists based on a gray-scale difference map of the first defect image and the second defect image comprises:
determining a defect to be selected in a contour line in the gray level difference map;
and judging whether the defect to be selected is the target defect or not based on a matching result of the characteristic value of the defect to be selected and a standard interval.
6. The screen defect detection method of claim 5, wherein the step of determining the candidate defect in the gray level difference map that is within the contour line comprises:
determining a coordinate sequence of a pixel point corresponding to a screen edge contour line in the gray level difference value diagram;
determining pixel coordinates of suspected defects in the gray difference map;
and determining the defect to be selected according to the pixel coordinates and the coordinate sequence.
7. The screen defect detection method of claim 5, wherein the step of determining whether the defect to be selected is the target defect based on a result of matching the feature value of the defect to be selected and a standard interval comprises:
performing image recognition on the defects to be selected, and determining the characteristic value corresponding to each preset characteristic attribute;
when the characteristic values are all in the standard interval, judging that the defect to be selected is the target defect;
otherwise, judging that the defect to be selected is not the target defect.
8. A screen defect detecting apparatus comprising a memory, a processor and a screen defect detecting program stored on the memory and executable on the processor, the processor implementing the steps of the screen defect detecting method according to any one of claims 1 to 7 when executing the screen defect detecting program.
9. A computer-readable storage medium, wherein a screen defect detection program is stored on the computer-readable storage medium, which when executed by a processor, implements the steps of the screen defect detection method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311641891.4A CN117351011B (en) | 2023-12-04 | 2023-12-04 | Screen defect detection method, apparatus, and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311641891.4A CN117351011B (en) | 2023-12-04 | 2023-12-04 | Screen defect detection method, apparatus, and readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117351011A CN117351011A (en) | 2024-01-05 |
| CN117351011B true CN117351011B (en) | 2024-03-12 |
Family
ID=89371383
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311641891.4A Active CN117351011B (en) | 2023-12-04 | 2023-12-04 | Screen defect detection method, apparatus, and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117351011B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111340752B (en) * | 2019-12-04 | 2024-08-06 | 京东方科技集团股份有限公司 | Screen detection method and device, electronic equipment and computer readable storage medium |
| CN117974605B (en) * | 2024-02-02 | 2024-08-02 | 山东福茂装饰材料有限公司 | Method for detecting edge sealing defect of plate based on image |
| CN118096732B (en) * | 2024-04-22 | 2024-06-21 | 高视科技(苏州)股份有限公司 | Display screen light leakage detection method, electronic equipment and storage medium |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102183525A (en) * | 2011-01-20 | 2011-09-14 | 单宝华 | Bridge apparent state automatic detection device and method based on charge coupled device (CCD) array photographic technique |
| CN109242852A (en) * | 2018-10-30 | 2019-01-18 | 长春光华学院 | A kind of automobile engine oil circuit copper sheathing defective vision detection method |
| CN109300127A (en) * | 2018-09-21 | 2019-02-01 | 中兴新通讯有限公司 | Defect inspection method, device, computer equipment and storage medium |
| CN110009633A (en) * | 2019-04-19 | 2019-07-12 | 湖南大学 | A kind of detection method of surface flaw of steel rail based on reversed difference of Gaussian |
| CN111310558A (en) * | 2019-12-28 | 2020-06-19 | 北京工业大学 | Pavement disease intelligent extraction method based on deep learning and image processing method |
| CN111627009A (en) * | 2020-05-27 | 2020-09-04 | 歌尔股份有限公司 | Screen detection method and device and head-mounted display equipment |
| CN111768348A (en) * | 2020-05-29 | 2020-10-13 | 合肥联宝信息技术有限公司 | Defect detection method, device and computer readable storage medium |
| CN112767326A (en) * | 2021-01-07 | 2021-05-07 | 湖南大学 | Steel rail surface defect detection method, device, equipment and storage medium |
| CN113160103A (en) * | 2021-04-22 | 2021-07-23 | 展讯通信（上海）有限公司 | Image processing method and device, storage medium and terminal |
| CN115018797A (en) * | 2022-06-13 | 2022-09-06 | 歌尔股份有限公司 | Screen defect detection method, screen defect detection device and computer-readable storage medium |
| CN115631210A (en) * | 2022-12-21 | 2023-01-20 | 深圳市华汉伟业科技有限公司 | Edge detection method and device |
| CN115984230A (en) * | 2023-01-09 | 2023-04-18 | 纳威尔(长沙)智能科技有限公司 | Aluminum foil sealing quality detection method, computer device, product and storage medium |
| CN116993731A (en) * | 2023-09-27 | 2023-11-03 | 山东济矿鲁能煤电股份有限公司阳城煤矿 | Shield tunneling machine tool bit defect detection method based on image |
-
2023
- 2023-12-04 CN CN202311641891.4A patent/CN117351011B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102183525A (en) * | 2011-01-20 | 2011-09-14 | 单宝华 | Bridge apparent state automatic detection device and method based on charge coupled device (CCD) array photographic technique |
| CN109300127A (en) * | 2018-09-21 | 2019-02-01 | 中兴新通讯有限公司 | Defect inspection method, device, computer equipment and storage medium |
| CN109242852A (en) * | 2018-10-30 | 2019-01-18 | 长春光华学院 | A kind of automobile engine oil circuit copper sheathing defective vision detection method |
| CN110009633A (en) * | 2019-04-19 | 2019-07-12 | 湖南大学 | A kind of detection method of surface flaw of steel rail based on reversed difference of Gaussian |
| CN111310558A (en) * | 2019-12-28 | 2020-06-19 | 北京工业大学 | Pavement disease intelligent extraction method based on deep learning and image processing method |
| CN111627009A (en) * | 2020-05-27 | 2020-09-04 | 歌尔股份有限公司 | Screen detection method and device and head-mounted display equipment |
| CN111768348A (en) * | 2020-05-29 | 2020-10-13 | 合肥联宝信息技术有限公司 | Defect detection method, device and computer readable storage medium |
| CN112767326A (en) * | 2021-01-07 | 2021-05-07 | 湖南大学 | Steel rail surface defect detection method, device, equipment and storage medium |
| CN113160103A (en) * | 2021-04-22 | 2021-07-23 | 展讯通信（上海）有限公司 | Image processing method and device, storage medium and terminal |
| CN115018797A (en) * | 2022-06-13 | 2022-09-06 | 歌尔股份有限公司 | Screen defect detection method, screen defect detection device and computer-readable storage medium |
| CN115631210A (en) * | 2022-12-21 | 2023-01-20 | 深圳市华汉伟业科技有限公司 | Edge detection method and device |
| CN115984230A (en) * | 2023-01-09 | 2023-04-18 | 纳威尔(长沙)智能科技有限公司 | Aluminum foil sealing quality detection method, computer device, product and storage medium |
| CN116993731A (en) * | 2023-09-27 | 2023-11-03 | 山东济矿鲁能煤电股份有限公司阳城煤矿 | Shield tunneling machine tool bit defect detection method based on image |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117351011A (en) | 2024-01-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117351011B (en) | Screen defect detection method, apparatus, and readable storage medium | |
| CN111627009B (en) | Screen detection method and device and head-mounted display equipment | |
| CN110717489B (en) | Method, device and storage medium for identifying text region of OSD (on Screen display) | |
| CN115908269B (en) | Visual defect detection method, visual defect detection device, storage medium and computer equipment | |
| CN111179243A (en) | Small-size chip crack detection method and system based on computer vision | |
| CN112614062B (en) | Colony counting method, colony counting device and computer storage medium | |
| CN111915704A (en) | Apple hierarchical identification method based on deep learning | |
| US9965695B1 (en) | Document image binarization method based on content type separation | |
| CN106920245B (en) | Boundary detection method and device | |
| CN113379680B (en) | Defect detection method, defect detection device, electronic device and computer readable storage medium | |
| CN116503388B (en) | Defect detection method, device and storage medium | |
| CN110197180B (en) | Character defect detection method, device and equipment | |
| CN110070523B (en) | Foreign matter detection method for bottle bottom | |
| JP2018506046A (en) | Method for detecting defects on the tire surface | |
| US20170178341A1 (en) | Single Parameter Segmentation of Images | |
| CN110599453A (en) | Panel defect detection method and device based on image fusion and equipment terminal | |
| CN113537037A (en) | Pavement disease identification method, system, electronic device and storage medium | |
| CN113283439B (en) | Intelligent counting method, device and system based on image recognition | |
| WO2024016632A1 (en) | Bright spot location method, bright spot location apparatus, electronic device and storage medium | |
| CN115908988B (en) | Defect detection model generation method, device, equipment and storage medium | |
| CN112669300A (en) | Defect detection method and device, computer equipment and storage medium | |
| CN114898161A (en) | Method and device for detecting dirt of camera and electronic equipment | |
| CN115690089A (en) | Image enhancement preprocessing method and system for weak defect detection | |
| CN108877030B (en) | Image processing method, device, terminal and computer readable storage medium | |
| CN115100648B (en) | Method and device for filtering multi-channel fluorescent impurities in cell microscopic image |
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 |