CN113205480A - Periodic extraction method, device and system for detecting defects of display panel - Google Patents
Periodic extraction method, device and system for detecting defects of display panel Download PDFInfo
- Publication number
- CN113205480A CN113205480A CN202110295369.XA CN202110295369A CN113205480A CN 113205480 A CN113205480 A CN 113205480A CN 202110295369 A CN202110295369 A CN 202110295369A CN 113205480 A CN113205480 A CN 113205480A
- Authority
- CN
- China
- Prior art keywords
- feature points
- periodic
- period
- display panel
- extraction
- 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.)
- Pending
Links
- 230000000737 periodic effect Effects 0.000 title claims abstract description 131
- 238000000605 extraction Methods 0.000 title claims abstract description 88
- 230000007547 defect Effects 0.000 title claims abstract description 57
- 238000001514 detection method Methods 0.000 claims abstract description 33
- 238000000034 method Methods 0.000 claims abstract description 18
- 230000002159 abnormal effect Effects 0.000 claims description 31
- 230000001502 supplementing effect Effects 0.000 claims description 16
- 238000012216 screening Methods 0.000 claims description 14
- 238000009826 distribution Methods 0.000 claims description 12
- 238000006243 chemical reaction Methods 0.000 claims description 10
- 238000000926 separation method Methods 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 9
- 238000012163 sequencing technique Methods 0.000 claims description 8
- 238000003860 storage Methods 0.000 claims description 8
- 238000004422 calculation algorithm Methods 0.000 claims description 7
- 238000005311 autocorrelation function Methods 0.000 abstract description 7
- 238000004364 calculation method Methods 0.000 abstract description 4
- 230000002093 peripheral effect Effects 0.000 abstract description 4
- 238000005520 cutting process Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 25
- 230000003287 optical effect Effects 0.000 description 8
- 238000005516 engineering process Methods 0.000 description 5
- 230000000007 visual effect Effects 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 3
- 239000011521 glass Substances 0.000 description 3
- 239000000758 substrate Substances 0.000 description 3
- 239000000284 extract Substances 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 238000011179 visual inspection Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- AMGQUBHHOARCQH-UHFFFAOYSA-N indium;oxotin Chemical compound [In].[Sn]=O AMGQUBHHOARCQH-UHFFFAOYSA-N 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 229910052751 metal Inorganic materials 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 238000012634 optical imaging Methods 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 239000010409 thin film Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
- G06T7/0006—Industrial image inspection using a design-rule based approach
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/211—Selection of the most significant subset of features
- G06F18/2113—Selection of the most significant subset of features by ranking or filtering the set of features, e.g. using a measure of variance or of feature cross-correlation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- 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
- G06T7/10—Segmentation; Edge detection
- G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
- G06V10/462—Salient features, e.g. scale invariant feature transforms [SIFT]
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20048—Transform domain processing
- G06T2207/20056—Discrete and fast Fourier transform, [DFT, FFT]
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Multimedia (AREA)
- Quality & Reliability (AREA)
- Testing Of Optical Devices Or Fibers (AREA)
Abstract
The invention provides a periodic extraction method, a device and a system for detecting defects of a display panel, and relates to the technical field of defect detection of display panels. The invention discloses a periodic extraction method for detecting defects of a display panel, which comprises the following steps: determining a periodic characteristic point according to the periodic characteristic of the display panel; and extracting a period according to the period feature points. According to the technical scheme, the period is extracted by cutting in a mode of period feature points, the calculation of repeated data is reduced by replacing peripheral areas with the points, and compared with the fact that time consumption is long due to the fact that an image is transformed from a time domain to a frequency domain through Fourier transform in an autocorrelation function method, the efficiency of period extraction is effectively improved, and therefore the efficiency of defect detection of the display panel is improved.
Description
Technical Field
The invention relates to the technical field of display panel defect detection, in particular to a method, a device and a system for periodically extracting defect detection of a display panel.
Background
Glass substrates are important raw materials for producing Thin film transistor liquid crystal displays (TFT-LCDs), and during the production process, parts inevitably have defects of various types, such as scratches, hole dislocation, scratches, short circuits, broken circuits, pollution and the like on printed circuit boards, and regular areas of the glass substrates and the surfaces of optical filters have defects of pinholes, scratches, particles, dirt, uneven brightness and the like. The defects not only affect the performance of the product and cause huge economic loss to manufacturers, but also even endanger the personal safety of users in severe cases. The detection of the product is particularly important, and for the display panels such as glass substrates, the traditional defect detection method is a manual visual detection method, but the method has the defects of strong subjectivity, limited human eye space and time resolution, large detection uncertainty, easy generation of ambiguity, low efficiency and the like, and the detection requirements of high speed and high resolution in modern industry are difficult to meet.
In the field of display panel detection, the automatic optical (visual) inspection technology (AOI) for surface defects based on optical image sensing is used to replace manual visual inspection of surface defects, and has gradually become an important means for surface defect detection; in the surface defect automatic optical (visual) detection technology, an autocorrelation function method is often adopted for analysis and extraction of the period, but the autocorrelation function method needs to transform an image from a time domain to a frequency domain through Fourier transform, so that the time consumption of the step is long, and the efficiency of detecting the defects of the display panel is influenced.
Disclosure of Invention
The invention solves the problem of how to improve the efficiency of detecting the defects of the display panel.
In order to solve the above problems, the present invention provides a method for periodically extracting defect detection of a display panel, comprising: determining a periodic characteristic point according to the periodic characteristic of the display panel; and extracting a period according to the period feature points.
According to the period extraction method for detecting the defects of the display panel, the period is extracted by cutting in a mode of the period characteristic points, the calculation of repeated data is reduced by replacing peripheral areas with the points, and compared with the fact that the time consumption is long as an image is converted from a time domain to a frequency domain through Fourier transform in an autocorrelation function method, the efficiency of period extraction is effectively improved, and therefore the efficiency of detecting the defects of the display panel is improved.
Optionally, the determining the periodic feature points according to the sensing image of the display panel includes: amplifying the contrast of periodic features in the sensing image by adopting gray scale conversion; dividing the periodic characteristic region by a gray threshold; and separating the connected regions in the periodic feature region by adopting an on operation to form a separated region, and determining the periodic feature point from the separated region.
The period extraction method for detecting the defects of the display panel, disclosed by the invention, has the advantages that the contrast of the period characteristics in the sensing image is amplified by adopting gray scale conversion, the period characteristics are convenient to segment, the period characteristic region is segmented by adopting the gray scale threshold value, the connected regions in the period characteristic region are separated by adopting the open operation to form the separated region, the subsequent extraction period is facilitated, and the period extraction efficiency is effectively improved.
Optionally, the determining the periodic feature points from the separation region includes: and screening the separation region according to a preset screening condition to determine the periodic feature points.
The periodic extraction method for detecting the defects of the display panel, disclosed by the invention, screens the separation area according to the preset screening condition to determine the periodic characteristic points, reduces the interference points and improves the accuracy of periodic extraction.
Optionally, the extracting a cycle according to the cycle feature point includes: extracting the central coordinates of the periodic feature points from the sensing image, and arranging the periodic feature points in rows according to the central coordinates; removing abnormal feature points from the periodic feature points and supplementing missing feature points; and extracting a period according to the period feature points after the abnormal feature points are removed and the missing feature points are supplemented.
According to the period extraction method for detecting the defects of the display panel, the center coordinates are extracted, the period feature points are arranged in rows according to the center coordinates, the abnormal feature points are removed from the period feature points and the missing feature points are supplemented, and the period is extracted according to the period feature points after the abnormal feature points are removed and the missing feature points are supplemented, so that the orderliness of the period feature points is improved, and the accuracy of period extraction is improved.
Optionally, the arranging the periodic feature points in rows according to the central coordinates includes: and sequencing the central coordinates by adopting a sequencing algorithm to arrange the periodic feature points in rows.
The periodic extraction method for detecting the defects of the display panel, disclosed by the invention, is used for sequencing the central coordinates by adopting a sequencing algorithm so as to arrange the periodic characteristic points in rows, thereby improving the orderliness of the periodic characteristic points and being beneficial to improving the accuracy of periodic extraction.
Optionally, the removing abnormal feature points from the periodic feature points and supplementing missing feature points includes: and counting the distance distribution of the periodic feature points, removing the abnormal feature points according to the distance distribution and supplementing the missing feature points.
According to the period extraction method for detecting the defects of the display panel, disclosed by the invention, the interval distribution of the period characteristic points is counted, the abnormal characteristic points are removed according to the interval distribution, the missing characteristic points are supplemented, and the accuracy of period extraction is improved.
Optionally, the extracting a cycle according to the cycle feature point further includes: and determining the extraction range of the period in the sensing image, and extracting the period according to the period feature points in the extraction range.
According to the period extraction method for detecting the defects of the display panel, the extraction range of the period is determined and the period is extracted in the extraction range, so that the extraction range of the period is determined, the accuracy of the period extraction is improved, and the efficiency of the period extraction is effectively improved.
The present invention also provides a cycle extraction apparatus for defect detection of a display panel, comprising: the determining module is used for determining a periodic characteristic point according to the periodic characteristic of the display panel; and the extraction module is used for extracting the period according to the period feature points. The advantages of the period extraction device for detecting the defects of the display panel and the period extraction method for detecting the defects of the display panel are the same as the advantages of the period extraction method for detecting the defects of the display panel in comparison with the prior art, and are not repeated herein.
The invention also provides a period extraction system for detecting the defects of the display panel, which comprises a computer readable storage medium and a processor, wherein the computer readable storage medium is used for storing a computer program, and the computer program is read by the processor and runs to realize the period extraction method for detecting the defects of the display panel. The advantages of the period extraction system for detecting the defects of the display panel and the period extraction method for detecting the defects of the display panel are the same as the advantages of the period extraction method for detecting the defects of the display panel in comparison with the prior art, and are not repeated herein.
The present invention also provides a computer-readable storage medium storing a computer program which, when read and executed by a processor, implements the periodic extraction method for display panel defect detection as described above. The advantages of the computer-readable storage medium and the above-mentioned period extraction method for detecting defects of a display panel are the same as those of the prior art, and are not described herein again.
Drawings
FIG. 1 is a first schematic diagram of a periodic extraction method according to an embodiment of the present invention;
FIG. 2 is a second schematic diagram of a periodic extraction method according to an embodiment of the present invention;
FIG. 3 is a third schematic diagram of a periodic extraction method according to an embodiment of the present invention;
FIG. 4 is a fourth schematic diagram of the periodic extraction method according to the embodiment of the present invention;
FIG. 5 is a fifth schematic diagram of a periodic extraction method according to an embodiment of the present invention;
FIG. 6 is a sixth schematic diagram of a periodic extraction method according to an embodiment of the present invention;
FIG. 7 is a seventh schematic diagram illustrating a periodic extraction method according to an embodiment of the present invention;
FIG. 8 is a schematic diagram of the periodic characteristics before gray scale conversion according to an embodiment of the present invention;
FIG. 9 is a schematic diagram of the periodic characteristics after gray scale conversion according to the embodiment of the present invention;
FIG. 10 is a schematic diagram of the cycle characteristics after passing through the gray level thresholding in accordance with an embodiment of the present invention;
FIG. 11 is a schematic diagram illustrating the cycle characteristics after the ON operation according to the embodiment of the present invention;
FIG. 12 is a schematic diagram of the cycle characteristics after screening according to the preset screening conditions according to the embodiment of the present invention;
FIG. 13 is a schematic diagram of out-of-order periodic feature points according to an embodiment of the present invention;
FIG. 14 is a diagram illustrating sorted periodic feature points according to an embodiment of the present invention;
FIG. 15 is a schematic diagram of missing feature points according to an embodiment of the present invention;
FIG. 16 is a diagram illustrating abnormal feature points according to an embodiment of the present invention;
FIG. 17 is a diagram illustrating an extraction range of a determination period according to an embodiment of the present invention;
FIG. 18 is a schematic diagram of another periodic feature of an embodiment of the present invention.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in detail below.
As shown in fig. 1, an embodiment of the present invention provides a method for periodically extracting defect detection of a display panel, including: determining a periodic characteristic point according to the periodic characteristic of the display panel; and extracting a period according to the period feature points.
Specifically, in the present embodiment, the cycle extraction method for detecting defects of a display panel includes: determining periodic characteristic points according to a sensing image of the display panel, wherein the sensing image refers to an image of the display panel acquired by an optical camera based on a surface defect automatic optical detection technology; and according to the period characteristic point extraction period, the period is independently detected after the period is extracted, so that the defect detection of the display panel is realized. The periodic features refer to shapes similar to those of fig. 8-17, differing in different product configurations, and possibly of various other shapes, such as shown in fig. 18, where the periodic features include slit-shaped apertures; the periodic feature points are the points distributed in fig. 8 to 17, and taking fig. 11 as an example, the periodic feature points are periodically distributed in a lattice form; a color filter is formed on the display panel, the color filter having a transmissive pattern formed in a metal layer, the transmissive pattern including a plurality of sub-wavelength holes having a period (i.e., periodic feature points), and outputting light of a desired color by selectively transmitting light of a specific wavelength using surface plasmon. In the field of display panel detection, the automatic optical (visual) inspection (AOI) technology for surface defects based on optical image sensing instead of manual visual inspection of surface defects has gradually become an important means for surface defect detection, because the method has the advantages of automation, non-contact, high speed, high precision, high stability and the like.
The ITO (indium tin oxide) circuit area on the display panel is divided into a periodic area and a non-periodic area according to the arrangement structure, the periodic area occupies most of the display panel, the non-periodic area is generally distributed at the periphery of the periodic area, the periodic area and the non-periodic area can be separately detected during defect detection, and the periodic area can extract single or multiple periods to carry out independent detection.
The size of the display panel is developed from 300mm × 400mm in the first generation line to 2850mm × 3050mm in the tenth generation line, and as the size of the display panel is larger, the detection accuracy is higher and higher, and the requirement on the AOI technology is higher and higher. Due to the requirement of high precision, optical imaging systems with high magnification, such as 3.5 times, 5 times and the like, are often adopted, the tiny periodic structure of the display panel can be shot clearly through the high magnification, and the detection of the periodic area often extracts one or more periods for independent detection. In the display panel detection, an autocorrelation function method is often adopted for analyzing and extracting the period, but the autocorrelation function method needs to transform an image from a time domain to a frequency domain through Fourier transform, the time consumption of the step is long, the embodiment cuts in the period characteristic points to extract the period, and the calculation of repeated data is reduced by replacing peripheral areas with the points, so that the efficiency of period extraction is effectively improved.
In the embodiment, the cut-in is performed in a mode of periodic feature points to extract the period, the calculation of repeated data is reduced by replacing peripheral regions with the points, and compared with the fact that the time consumption is long when an image is transformed from a time domain to a frequency domain through Fourier transform in an autocorrelation function method, the efficiency of period extraction is effectively improved.
Optionally, the determining the periodic feature points according to the sensing image of the display panel includes: amplifying the contrast of periodic features in the sensing image by adopting gray scale conversion; dividing the periodic characteristic region by a gray threshold; and separating the connected regions in the periodic feature region by adopting an on operation to form a separated region, and determining the periodic feature point from the separated region.
Specifically, in the present embodiment, as shown in fig. 2, determining the periodic feature points from the sensed image of the display panel includes: amplifying the contrast of periodic characteristics in the sensing image by adopting gray scale conversion; dividing the periodic characteristic region by a gray threshold; and separating connected regions in the periodic feature region by adopting an on operation to form a separated region, and determining periodic feature points from the separated region.
Referring to fig. 8 and 9, schematic diagrams of periodic characteristics before and after gray scale conversion are shown, respectively, to enlarge the contrast of the periodic characteristics by gray scale conversion, thereby facilitating the segmentation of the periodic characteristics.
As shown in fig. 10, the periodic feature region is segmented by the gray threshold, so that the initial segmentation of the periodic feature region is realized, which is beneficial to the subsequent extraction period, and thus the efficiency of period extraction is effectively improved.
As shown in fig. 11, since the feature regions of a part of the product cycle are connected, the step of adding the on operation is to separate the connected regions, thereby facilitating the subsequent extraction cycle.
In the embodiment, the contrast of the period features in the sensing image is amplified by adopting gray scale conversion, the period features are convenient to segment, the period feature regions are segmented by adopting a gray scale threshold value, and the connected regions in the period feature regions are separated by adopting open operation to form a separated region, so that the subsequent extraction period is facilitated, the efficiency of period extraction is effectively improved, and the efficiency of defect detection of the display panel is improved.
Optionally, the determining the periodic feature points from the separation region includes: and screening the separation region according to a preset screening condition to determine the periodic feature points.
Specifically, in this embodiment, as shown in fig. 3, the determining the periodic feature points from the separation region includes: and screening the separation areas according to preset screening conditions to determine periodic characteristic points.
Referring to fig. 12, the periodic feature points are determined by screening the attributes such as size and roundness, fig. 12 has fewer small interference points than fig. 11, and besides the size (area) and roundness, the screened attributes include, but are not limited to, the area width, the area height, the perimeter, the convexity, the number of holes, the minimum circumscribed circle radius, the minimum inscribed circle radius, the minimum circumscribed rectangle length, the minimum circumscribed rectangle width, and the like.
In this embodiment, the period feature points are determined by screening from the separation region according to the preset screening conditions, so that the number of interference points is reduced, and the accuracy of period extraction is improved.
Optionally, the extracting a cycle according to the cycle feature point includes: extracting the central coordinates of the periodic feature points from the sensing image, and arranging the periodic feature points in rows according to the central coordinates; removing abnormal feature points from the periodic feature points and supplementing missing feature points; and extracting a period according to the period feature points after the abnormal feature points are removed and the missing feature points are supplemented.
Specifically, in the present embodiment, as shown in fig. 4, the cycle feature point extraction cycle includes: extracting a central coordinate, and arranging periodic feature points in rows according to the central coordinate; removing abnormal feature points from the periodic feature points and supplementing missing feature points; and extracting a period according to the period feature points after the abnormal feature points are removed and the missing feature points are supplemented.
Referring to fig. 13 and 14, which are respectively a disordered periodic feature point schematic diagram and a sequenced periodic feature point schematic diagram, in fig. 13 and 14, a small circle represents a feature point, each feature point has its own image coordinate (x, y), but the feature points are not sequenced from left to right in a row-by-row-column manner, but are disordered as shown in fig. 13, and each periodic feature point has a number, but the number has disorder, so that the periodic feature points need to be arranged in rows according to the central coordinate, thereby improving the ordering of the periodic feature points and being beneficial to improving the accuracy of periodic extraction.
Referring to fig. 15 and 16, a schematic diagram of a missing feature point and a schematic diagram of an abnormal feature point are shown, respectively, and the frame selection portions are a schematic position of the missing feature point and a schematic position of the abnormal feature point, respectively, the missing feature point and the abnormal feature point only occupy a majority in a general situation, and the order of the periodic feature points can be improved by removing the abnormal feature points and supplementing the missing feature points.
In this embodiment, the order of the periodic feature points is improved and the accuracy of periodic extraction is improved by extracting the central coordinates of the periodic feature points from the sensing image, arranging the periodic feature points in rows according to the central coordinates, removing the abnormal feature points from the periodic feature points and supplementing the missing feature points, and extracting the periods according to the periodic feature points after removing the abnormal feature points and supplementing the missing feature points.
Optionally, the arranging the periodic feature points in rows according to the central coordinates includes: and sequencing the central coordinates by adopting a sequencing algorithm to arrange the periodic feature points in rows.
Specifically, in the present embodiment, as shown in conjunction with fig. 5, 13, and 14, arranging the periodic feature points in lines according to the center coordinates includes: and sorting the central coordinates by adopting a sorting algorithm to arrange the periodic feature points in rows.
The feature point center coordinates are extracted, because the extracted coordinates are out of order or connected together, the center point coordinates are arranged in rows and similar to a two-dimensional array, that is, after a sorting algorithm, as shown in fig. 14, the feature points are sorted from left to right in rows and columns, and the row sequence numbers and the column sequence numbers can be used for positioning quickly, for example, the feature points in the fifth column of the second row need to be positioned, and the index in the fifth column of the second row can be input by the extraction method of the array for extraction.
In this embodiment, the central coordinates are sorted by using a sorting algorithm to arrange the periodic feature points in rows, so that the order of the periodic feature points is improved, and the accuracy of periodic extraction is improved.
Optionally, the removing abnormal feature points from the periodic feature points and supplementing missing feature points includes: and counting the distance distribution of the periodic feature points, removing the abnormal feature points according to the distance distribution and supplementing the missing feature points.
Specifically, in this embodiment, as shown in fig. 6, the removing abnormal feature points from the periodic feature points and supplementing missing feature points includes: and counting the distance distribution of the periodic feature points, removing abnormal feature points according to the distance distribution and supplementing missing feature points.
With reference to fig. 15 and 16, a schematic diagram of a missing feature point and a schematic diagram of an abnormal feature point are respectively shown, the frame selection portions are respectively a schematic position of the missing feature point and a schematic position of the abnormal feature point, the missing feature point and the abnormal feature point only occupy a majority in a general situation, a distance threshold is set by counting an average distance of normal feature points, and the abnormal feature point and the supplementary missing feature point can be removed and supplemented by the average distance and the distance threshold when traversing each feature point.
Because a certain angle exists between the display panel and the camera collecting direction, the phenomenon that the characteristic points of the edge are not enough to form a row or a column of complete characteristic point groups is caused, and therefore characteristic point elimination of the edge is also required.
In this embodiment, the accuracy of period extraction is improved by counting the distance distribution of the period feature points, eliminating abnormal feature points according to the distance distribution and supplementing missing feature points.
Optionally, the extracting a cycle according to the cycle feature point further includes: and determining the extraction range of the period in the sensing image, and extracting the period according to the period feature points in the extraction range.
Specifically, in this embodiment, as shown in fig. 7, the extracting cycle of feature points according to the cycle further includes: and determining the extraction range of the period in the sensing image, and extracting the period according to the period feature points in the extraction range.
As shown in fig. 17, the frame of the frame-selected period feature point is the minimum period range, but since the actual image processing may need a period with a larger area, the period needs to be enlarged by a multiple to extract the period; when the extraction range of the period is determined, the period frame selection starting point is input, and the period end point coordinate can be obtained by multiplying the calculated transverse period length and the longitudinal period length by the magnification factor, so that the extraction range of the period is determined, and the required period is extracted in the extraction range.
In the embodiment, the extraction range of the period is determined and the period is extracted in the extraction range, so that the extraction range of the period is determined, the accuracy of the period extraction is improved, and the efficiency of the period extraction is effectively improved.
Another embodiment of the present invention provides a cycle extracting apparatus for detecting defects of a display panel, including: the determining module is used for determining a periodic characteristic point according to the periodic characteristic of the display panel; and the extraction module is used for extracting the period according to the period feature points.
Another embodiment of the present invention provides a cycle extraction system for display panel defect detection, including a computer-readable storage medium storing a computer program and a processor, where the computer program is read by the processor and executed to implement the cycle extraction method for display panel defect detection as described above.
Another embodiment of the present invention provides a computer-readable storage medium storing a computer program, which when read and executed by a processor, implements the periodic extraction method for display panel defect detection as described above.
Although the present disclosure has been described above, the scope of the present disclosure is not limited thereto. Various changes and modifications may be effected therein by one of ordinary skill in the pertinent art without departing from the spirit and scope of the present disclosure, and these changes and modifications are intended to be within the scope of the present disclosure.
Claims (10)
1. A cycle extraction method for detecting defects of a display panel is characterized by comprising the following steps:
determining a period characteristic point according to a sensing image of a display panel;
and extracting a period according to the period feature points.
2. The method of claim 1, wherein the determining periodic feature points from the sensed image of the display panel comprises:
amplifying the contrast of periodic features in the sensing image by adopting gray scale conversion;
dividing the periodic characteristic region by a gray threshold;
and separating the connected regions in the periodic feature region by adopting an on operation to form a separated region, and determining the periodic feature point from the separated region.
3. The method of claim 2, wherein the determining the periodic feature points from the separation region comprises:
and screening the separation region according to a preset screening condition to determine the periodic feature points.
4. The method according to any one of claims 1 to 3, wherein the extracting the period according to the period feature points comprises:
extracting the central coordinates of the periodic feature points from the sensing image, and arranging the periodic feature points in rows according to the central coordinates;
removing abnormal feature points from the periodic feature points and supplementing missing feature points;
and extracting a period according to the period feature points after the abnormal feature points are removed and the missing feature points are supplemented.
5. The method of claim 4, wherein the arranging the periodic feature points in rows according to the center coordinates comprises:
and sequencing the central coordinates by adopting a sequencing algorithm to arrange the periodic feature points in rows.
6. The method according to claim 4, wherein the removing abnormal feature points from the periodic feature points and supplementing missing feature points comprises:
and counting the distance distribution of the periodic feature points, removing the abnormal feature points according to the distance distribution and supplementing the missing feature points.
7. The method of claim 4, wherein the extracting the period according to the period feature points further comprises:
and determining the extraction range of the period in the sensing image, and extracting the period according to the period feature points in the extraction range.
8. A cycle extraction device for detecting defects of a display panel, comprising:
the determining module is used for determining the periodic characteristic points according to the sensing image of the display panel;
and the extraction module is used for extracting the period according to the period feature points.
9. A cycle extraction system for defect detection of a display panel, comprising a computer-readable storage medium storing a computer program and a processor, the computer program being read and executed by the processor to implement the cycle extraction method for defect detection of a display panel according to any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that it stores a computer program which, when read and executed by a processor, implements the periodic extraction method for display panel defect detection according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110295369.XA CN113205480A (en) | 2021-03-19 | 2021-03-19 | Periodic extraction method, device and system for detecting defects of display panel |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110295369.XA CN113205480A (en) | 2021-03-19 | 2021-03-19 | Periodic extraction method, device and system for detecting defects of display panel |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113205480A true CN113205480A (en) | 2021-08-03 |
Family
ID=77025538
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110295369.XA Pending CN113205480A (en) | 2021-03-19 | 2021-03-19 | Periodic extraction method, device and system for detecting defects of display panel |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113205480A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113936002A (en) * | 2021-12-17 | 2022-01-14 | 成都数之联科技有限公司 | Period extraction method and device, computer equipment and readable storage medium |
| CN115880280A (en) * | 2023-02-01 | 2023-03-31 | 山东建筑大学鉴定检测中心有限公司 | Detection method for quality of steel structure weld joint |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102623368A (en) * | 2012-03-31 | 2012-08-01 | 上海集成电路研发中心有限公司 | Wafer defect detection method |
| CN103217438A (en) * | 2013-04-02 | 2013-07-24 | 天津大学 | Accurate circuit board element location and detection method based on image feature |
| CN104331693A (en) * | 2014-10-28 | 2015-02-04 | 武汉大学 | Symmetry detecting method and system of printing matter |
| CN106056608A (en) * | 2016-06-01 | 2016-10-26 | 武汉精测电子技术股份有限公司 | Image dot-line defect detection method and device |
| CN106037655A (en) * | 2016-06-17 | 2016-10-26 | 美的集团股份有限公司 | Separation and cycle calculation method and device of sleep cycle signals |
| CN106204517A (en) * | 2015-04-17 | 2016-12-07 | 铭传大学 | Automatic optical detection method for periodic pattern |
| CN110136161A (en) * | 2019-05-31 | 2019-08-16 | 苏州精观医疗科技有限公司 | Image characteristics extraction analysis method, system and device |
| CN111161264A (en) * | 2019-10-29 | 2020-05-15 | 福州大学 | Method for segmenting TFT circuit image with defects |
-
2021
- 2021-03-19 CN CN202110295369.XA patent/CN113205480A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102623368A (en) * | 2012-03-31 | 2012-08-01 | 上海集成电路研发中心有限公司 | Wafer defect detection method |
| CN103217438A (en) * | 2013-04-02 | 2013-07-24 | 天津大学 | Accurate circuit board element location and detection method based on image feature |
| CN104331693A (en) * | 2014-10-28 | 2015-02-04 | 武汉大学 | Symmetry detecting method and system of printing matter |
| CN106204517A (en) * | 2015-04-17 | 2016-12-07 | 铭传大学 | Automatic optical detection method for periodic pattern |
| CN106056608A (en) * | 2016-06-01 | 2016-10-26 | 武汉精测电子技术股份有限公司 | Image dot-line defect detection method and device |
| CN106037655A (en) * | 2016-06-17 | 2016-10-26 | 美的集团股份有限公司 | Separation and cycle calculation method and device of sleep cycle signals |
| CN110136161A (en) * | 2019-05-31 | 2019-08-16 | 苏州精观医疗科技有限公司 | Image characteristics extraction analysis method, system and device |
| CN111161264A (en) * | 2019-10-29 | 2020-05-15 | 福州大学 | Method for segmenting TFT circuit image with defects |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113936002A (en) * | 2021-12-17 | 2022-01-14 | 成都数之联科技有限公司 | Period extraction method and device, computer equipment and readable storage medium |
| CN115880280A (en) * | 2023-02-01 | 2023-03-31 | 山东建筑大学鉴定检测中心有限公司 | Detection method for quality of steel structure weld joint |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105894036B (en) | A kind of characteristics of image template matching method applied to mobile phone screen defects detection | |
| CN113646801B (en) | Defect detection method, device and computer readable storage medium for defect image | |
| Li et al. | Wavelet-based defect detection in solar wafer images with inhomogeneous texture | |
| JP4562126B2 (en) | Defect detection apparatus and defect detection method | |
| CN113205480A (en) | Periodic extraction method, device and system for detecting defects of display panel | |
| JP4616864B2 (en) | Appearance inspection method and apparatus, and image processing evaluation system | |
| Rahaman et al. | Automatic defect detection and classification technique from image: a special case using ceramic tiles | |
| CN109449093A (en) | Wafer detection method | |
| CN111179225A (en) | Test paper surface texture defect detection method based on gray gradient clustering | |
| CN110648330B (en) | Defect detection method for camera glass | |
| CN115661148B (en) | Wafer grain arrangement detection method and system | |
| CN114519714B (en) | Method and system for judging smudgy defect of display screen | |
| CN115131348A (en) | Method and system for detecting textile surface defects | |
| CN104331695A (en) | Robust round identifier shape quality detection method | |
| CN111681213A (en) | Light guide plate line scratch defect detection method based on deep learning | |
| CN107895371B (en) | Textile flaw detection method based on peak coverage value and Gabor characteristics | |
| CN117871545A (en) | Method and device for detecting defects of circuit board components, terminal and storage medium | |
| CN115205291A (en) | Circuit board detection method, device, equipment and medium | |
| CN112069974B (en) | Image recognition method and system for recognizing defects of components | |
| CN113487569B (en) | Complex background image defect detection method and system based on combination of frequency domain and space domain | |
| CN108615039A (en) | Cartridge case defect automatic testing method based on computer vision | |
| KR101109351B1 (en) | Metal pad state detection method using Gabor filter | |
| CN111192261A (en) | Method for identifying lens defect types | |
| CN112669322B (en) | Industrial component surface light defect detection method based on SVM classification | |
| CN114486916A (en) | Mobile phone glass cover plate defect detection method based on machine vision |
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 |