CN110717902A - Processing method for displaying image edge - Google Patents

Processing method for displaying image edge Download PDF

Info

Publication number
CN110717902A
CN110717902A CN201910933070.5A CN201910933070A CN110717902A CN 110717902 A CN110717902 A CN 110717902A CN 201910933070 A CN201910933070 A CN 201910933070A CN 110717902 A CN110717902 A CN 110717902A
Authority
CN
China
Prior art keywords
display area
image
boundary
straight line
qualified
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN201910933070.5A
Other languages
Chinese (zh)
Other versions
CN110717902B (en
Inventor
方学民
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Zhongshan Rifda Touch Display Technology Co Ltd
Original Assignee
Zhongshan Rifda Touch Display Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Zhongshan Rifda Touch Display Technology Co Ltd filed Critical Zhongshan Rifda Touch Display Technology Co Ltd
Priority to CN201910933070.5A priority Critical patent/CN110717902B/en
Publication of CN110717902A publication Critical patent/CN110717902A/en
Application granted granted Critical
Publication of CN110717902B publication Critical patent/CN110717902B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/0002Inspection of images, e.g. flaw detection
    • G06T7/0004Industrial image inspection
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/10Segmentation; Edge detection
    • G06T7/13Edge detection
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/20Special algorithmic details
    • G06T2207/20048Transform domain processing
    • G06T2207/20056Discrete and fast Fourier transform, [DFT, FFT]
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/30Subject of image; Context of image processing
    • G06T2207/30108Industrial image inspection
    • G06T2207/30121CRT, LCD or plasma display
    • YGENERAL 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
    • Y02TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02PCLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/30Computing systems specially adapted for manufacturing

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Quality & Reliability (AREA)
  • Image Analysis (AREA)
  • Image Processing (AREA)

Abstract

The invention is suitable for the field of image processing, and provides a processing method for displaying image edges, which comprises the following steps: determining a boundary line between a display area and a non-display area; extracting a display area image of a preset value adjacent to the boundary line, and mirroring the display area image to a non-display area by taking the boundary line as an axis; the continuous image processed in step S2; and (4) processing the images of the continuous images intercepted in the step (S3), judging whether the processed images are qualified, if the images are qualified, the products are qualified, and if the images are unqualified, the products are unqualified. The whole image is changed into a continuous image by mirroring part of the display area to the non-display area, and the condition that the detection of the display area is influenced due to sudden change of the image boundary can not occur after the FFT algorithm is carried out, so that the detection result is more accurate.

Description

Processing method for displaying image edge
Technical Field
The invention belongs to the field of image processing, and particularly relates to a processing method for displaying an image edge.
Background
The FFT (fast Fourier transform) algorithm is widely applied in the field of computer image processing, wherein one important application is to filter regularly and repeatedly appearing textures in an image and extract irregular image features. When it is checked whether an image displayed by one display device is defective, the image is clearly divided into an array display area and a non-display area. Inspection of the display area of the product array is an important item for product quality control. The FFT filtering of the image requires that the image must be continuous and regular throughout the filtering area, for example, the dot matrix area of the image appears continuously and regularly, but the boundary between the display area and the non-display area appears suddenly. The FFT filtering of such an image may cause a sharp jump at the boundary between the display area and the non-display area, which affects the detection of the display area.
Disclosure of Invention
The invention aims to provide a method for processing the edge of a display image, and aims to solve the problem that the subsequent product detection is influenced because the sudden change occurs after an FFT algorithm due to the discontinuity of the boundary image of a display area on a display device.
The invention is realized in such a way that a processing method for displaying image edges comprises the following steps:
s1: determining a boundary line between a display area and a non-display area;
s2: extracting a display area image of a preset value adjacent to the boundary line, and mirroring the display area image to a non-display area by taking the boundary line as an axis;
s3: intercepting the continuous image processed in the step S2;
s4: and (4) processing the images of the continuous images intercepted in the step (S3), judging whether the processed images are qualified, if the images are qualified, the products are qualified, and if the images are unqualified, the products are unqualified.
The further technical scheme of the invention is as follows: the step S1 includes the steps of:
s11: moving the center of the display area to the center of the image;
s12: and extracting the boundary of the display area, and fitting an approximate boundary straight line.
The further technical scheme of the invention is as follows: the step S11 includes the steps of:
S11A: positioning the center and the inclination angle of the display area through an image matching algorithm;
S11B: the center of the display area is moved to the image center by affine transformation.
The further technical scheme of the invention is as follows: the step S12 includes the steps of:
S12A: extracting the boundary of the display area through a boundary extraction algorithm;
S12B: and fitting a boundary straight line by using the inclination angle between the boundary and the display area and the curvature of the boundary.
The further technical scheme of the invention is as follows: the preset values in step S2 include a preset value width and a preset value height.
The further technical scheme of the invention is as follows: the step S2 includes the steps of:
s21: extracting a display area with a preset width on the right side of the left boundary, mirroring the display area to a non-display area on the left side of the left boundary straight line by taking the left boundary straight line as an axis, extracting a display area with a preset width on the left side of the right boundary, and mirroring the display area to a non-display area on the right side of the right boundary straight line by taking the right boundary straight line as an axis;
s22: and extracting a display area with preset width and height on the lower side of the upper boundary, taking the upper boundary straight line as an axis, mirroring the display area to the non-display area on the upper side of the upper boundary straight line, extracting a display area with preset height on the upper side of the lower boundary, taking the lower boundary straight line as an axis, and mirroring the display area to the non-display area on the lower side of the lower boundary straight line.
The further technical scheme of the invention is as follows: the preset value width is determined by the filtering parameters of the image processing in step S4 and the size of the lattice unit of the display area.
The further technical scheme of the invention is as follows: the step S21 and the step S22 may be interchanged in order.
The further technical scheme of the invention is as follows: the width of the continuous image cut out in the step S3 is the width of the display area plus two times the preset value width, and the height of the continuous image cut out in the step S3 is the height of the display area plus two times the preset value height.
The further technical scheme of the invention is as follows: the step S4 includes the steps of:
s41: performing time domain and frequency domain transformation on the image intercepted in the step S3, and converting the image into a frequency domain image;
s42: filtering the frequency domain image to filter out common frequencies;
s43: performing frequency domain and time domain transformation on the frequency domain image processed in the step S42 to convert the frequency domain image into a time domain image;
s44: denoising the time domain image, and intercepting a detection area according to the image size of the practical application equipment;
s45: if the image outside the detection area and the detection area is not defective, or the detection area is not defective, and the image outside the detection area is defective, the image processing is qualified, and the product is qualified; if the detection area is defective, the image processing is not qualified, and the product is not qualified.
The invention has the beneficial effects that: the whole image is changed into a continuous image by mirroring part of the display area to the non-display area, and the condition that the detection of the display area is influenced due to sudden change of the image boundary can not occur after the FFT algorithm is carried out, so that the detection result is more accurate.
Drawings
FIG. 1 is a general flow chart of the present invention;
FIG. 2 is a flowchart of step S1 of the present invention;
FIG. 3 is a flowchart of step S11 of the present invention;
FIG. 4 is a flowchart of step S12 of the present invention;
FIG. 5 is a flowchart of step S2 of the present invention;
fig. 6 is a flowchart of step S4 of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be noted that the terms "front," "back," "left," "right," "upper" and "lower" used in the following description refer to directions in the drawings, and the terms "bottom" and "top," "inner" and "outer" refer to directions toward and away from, respectively, the geometric center of a particular component.
Fig. 1 illustrates a processing method for displaying an image edge according to the present invention, which includes the following steps:
s1: determining a boundary line between a display area and a non-display area;
s2: extracting a display area image of a preset value adjacent to the boundary line, and mirroring the display area image to a non-display area by taking the boundary line as an axis;
s3: intercepting the continuous image processed in the step S2;
s4: and (4) processing the images of the continuous images intercepted in the step (S3), judging whether the processed images are qualified, if the images are qualified, the products are qualified, and if the images are unqualified, the products are unqualified.
Preferably, the step S1 includes the steps of:
s11: moving the center of the display area to the center of the image;
s12: and extracting the boundary of the display area, and fitting an approximate boundary straight line.
Preferably, the step S11 includes the steps of:
S11A: positioning the center and the inclination angle of the display area through an image matching algorithm;
S11B: the center of the display area is moved to the image center by affine transformation.
Preferably, the step S12 includes the steps of:
S12A: extracting the boundary of the display area through a boundary extraction algorithm;
S12B: and fitting a boundary straight line by using the inclination angle between the boundary and the display area and the curvature of the boundary.
Preferably, the preset value in step S2 includes a preset value width and a preset value height.
Preferably, the step S2 includes the steps of:
s21: extracting a display area with a preset width on the right side of the left boundary, mirroring the display area to a non-display area on the left side of the left boundary straight line by taking the left boundary straight line as an axis, extracting a display area with a preset width on the left side of the right boundary, and mirroring the display area to a non-display area on the right side of the right boundary straight line by taking the right boundary straight line as an axis;
s22: and extracting a display area with preset width and height on the lower side of the upper boundary, taking the upper boundary straight line as an axis, mirroring the display area to the non-display area on the upper side of the upper boundary straight line, extracting a display area with preset height on the upper side of the lower boundary, taking the lower boundary straight line as an axis, and mirroring the display area to the non-display area on the lower side of the lower boundary straight line.
Preferably, the preset value width is determined by the filtering parameter of the image processing in step S4 and the size of the lattice unit of the display area.
Preferably, the step S21 and the step S22 may be interchanged in order.
Preferably, the width of the continuous image cut out in the step S3 is the width of the display area plus two times the preset value width, and the height of the continuous image cut out in the step S3 is the height of the display area plus two times the preset value height.
Preferably, the step S4 includes the steps of:
s41: performing time domain and frequency domain transformation on the image intercepted in the step S3, and converting the image into a frequency domain image;
s42: filtering the frequency domain image to filter out common frequencies;
s43: performing frequency domain and time domain transformation on the frequency domain image processed in the step S42 to convert the frequency domain image into a time domain image;
s44: denoising the time domain image, and intercepting a detection area according to the image size of the practical application equipment;
s45: if the image outside the detection area and the detection area is not defective, or the detection area is not defective, and the image outside the detection area is defective, the image processing is qualified, and the product is qualified; if the detection area is defective, the image processing is not qualified, and the product is not qualified.
The display function of the display is the core function of the display, so the processing of the display image is an important step before the product leaves factory, and the FFT (fast Fourier transform) algorithm is widely applied in the field of computer image processing, and filters the regularly and repeatedly appeared textures in the image to extract the irregular image characteristics, so that the defect points of the image can be visually found out from the visual image for improvement. However, when the FFT algorithm is used at the edge of the display area, since the edge is not a continuous and regular image, when the FFT algorithm is performed, a defect occurs, such as an image that is too dark or too bright, or an image that changes suddenly, and a detection person cannot determine whether the defect is in the display area or the image that changes suddenly due to the edge of the display area.
As shown in fig. 1-4, the invention provides a method for processing the edge of a displayed image, which includes, first, determining the boundary line between the displayed area and the non-displayed area through the step S1, locating the center and the inclination of the displayed area through an image matching algorithm in the step S1, moving the center of the displayed area to the center of the whole image through affine transformation, extracting the boundary of the displayed area through a boundary extraction algorithm, and fitting four boundary straight lines, i.e., upper, lower, left and right, as the axes of the mirror image in the subsequent steps.
As shown in fig. 5, in step S2, the non-display area on the left side of the display area is mirror-covered by the display area with the preset width on the right side of the left boundary line, the non-display area on the right side of the display area is mirror-covered by the display area with the preset width on the left side of the right boundary line, the non-display area on the upper side of the display area is mirror-covered by the display area with the preset height on the lower side of the upper boundary line, and the non-display area on the lower side of the display area is mirror-. In actual production, the clipped pattern texture of the edge region is incomplete, that is, it is impossible to cut out a complete dot matrix unit image, and then it is abnormal in the FFT. The invention aims to enable the incomplete cutting to occur in areas which do not need to be checked, wherein the preset width is the width which can be determined by people and has sudden change, the preset height is the height which can be determined by people and has sudden change, the parameter is related to an FFT filtering parameter, and the filtering is to filter out continuous image lattices, so the size is directly related to the size of lattice units, the filtering of lattice images is incomplete when the size is too small, and real defect areas can be filtered out when the size is too large. The dimensions of the width and height of the preset value determine the size of the outside of the display area, and the selection of the size is not beneficial as long as the mutation area can be outside the inspection area. Preferably, the preset value width and height are 1.5 times of the size of the display lattice unit. Thus, the non-display area and the display area are both continuous and regular images, so that the whole image can be subjected to FFT processing.
As shown in fig. 6, the continuous image after the mirror image processing is cut, the width of the cut continuous image is the width of the display area plus two times of the preset value width, and the height of the cut continuous image in step S3 is the height of the display area plus two times of the preset value height. Finally, FFT algorithm change is carried out on the intercepted image, the time domain image is converted into a frequency domain image, then filtering processing is carried out on the frequency domain image, continuous and regular frequency is filtered, irregular frequency, namely defect points, are remained, then the frequency domain image is converted into an observable time domain image, the defect points on the displayed image can be clearly seen, at the moment, a detection area frame is selected from the image according to parameters such as the display size and the resolution of a display, and if the defect points fall in the detection area frame, the product is unqualified; and if the defect point is located outside the detection area frame and no defect point is located in the detection area frame, or the images outside the detection area and the detection area frame are both free of defects, the product is qualified.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents and improvements made within the spirit and principle of the present invention are intended to be included within the scope of the present invention.

Claims (10)

1. A method of processing edges of a displayed image, the method comprising the steps of:
s1: determining a boundary line between a display area and a non-display area;
s2: extracting a display area image of a preset value adjacent to the boundary line, and mirroring the display area image to a non-display area by taking the boundary line as an axis;
s3: intercepting the continuous image processed in the step S2;
s4: and (4) processing the images of the continuous images intercepted in the step (S3), judging whether the processed images are qualified, if the images are qualified, the products are qualified, and if the images are unqualified, the products are unqualified.
2. The method for processing the edge of the display image according to claim 1, wherein the step S1 comprises the following steps:
s11: moving the center of the display area to the center of the image;
s12: and extracting the boundary of the display area, and fitting an approximate boundary straight line.
3. The method for processing the edge of the display image according to claim 2, wherein the step S11 comprises the following steps:
S11A: positioning the center and the inclination angle of the display area through an image matching algorithm;
S11B: the center of the display area is moved to the image center by affine transformation.
4. The method according to claim 3, wherein the step S12 comprises the following steps:
S12A: extracting the boundary of the display area through a boundary extraction algorithm;
S12B: and fitting a boundary straight line by using the inclination angle between the boundary and the display area and the curvature of the boundary.
5. The method according to claim 1, wherein the preset values in step S2 include a preset value width and a preset value height.
6. The method according to claim 5, wherein the step S2 comprises the following steps:
s21: extracting a display area with a preset width on the right side of the left boundary, mirroring the display area to a non-display area on the left side of the left boundary straight line by taking the left boundary straight line as an axis, extracting a display area with a preset width on the left side of the right boundary, and mirroring the display area to a non-display area on the right side of the right boundary straight line by taking the right boundary straight line as an axis;
s22: and extracting a display area with preset width and height on the lower side of the upper boundary, taking the upper boundary straight line as an axis, mirroring the display area to the non-display area on the upper side of the upper boundary straight line, extracting a display area with preset height on the upper side of the lower boundary, taking the lower boundary straight line as an axis, and mirroring the display area to the non-display area on the lower side of the lower boundary straight line.
7. The method of claim 6, wherein the predetermined width is determined by the filter parameters of the image processing and the size of the lattice unit of the display area in step S4.
8. The method as claimed in claim 7, wherein the sequence of step S21 and step S22 can be interchanged.
9. The method of claim 8, wherein the width of the continuous image cut out in step S3 is the width of the display area plus two times the preset value width, and the height of the continuous image cut out in step S3 is the height of the display area plus two times the preset value height.
10. The method according to claim 9, wherein the step S4 includes the following steps:
s41: performing time domain and frequency domain transformation on the image intercepted in the step S3, and converting the image into a frequency domain image;
s42: filtering the frequency domain image to filter out common frequencies;
s43: performing frequency domain and time domain transformation on the frequency domain image processed in the step S42 to convert the frequency domain image into a time domain image;
s44: denoising the time domain image, and intercepting a detection area according to the image size of the practical application equipment;
s45: if the image outside the detection area and the detection area is not defective, or the detection area is not defective, and the image outside the detection area is defective, the image processing is qualified, and the product is qualified; if the detection area is defective, the image processing is not qualified, and the product is not qualified.
CN201910933070.5A 2019-09-29 2019-09-29 Processing method for display image edge Active CN110717902B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910933070.5A CN110717902B (en) 2019-09-29 2019-09-29 Processing method for display image edge

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910933070.5A CN110717902B (en) 2019-09-29 2019-09-29 Processing method for display image edge

Publications (2)

Publication Number Publication Date
CN110717902A true CN110717902A (en) 2020-01-21
CN110717902B CN110717902B (en) 2023-06-09

Family

ID=69212055

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910933070.5A Active CN110717902B (en) 2019-09-29 2019-09-29 Processing method for display image edge

Country Status (1)

Country Link
CN (1) CN110717902B (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100053204A1 (en) * 2008-08-26 2010-03-04 Lg Display Co., Ltd. Method for setting compensation region for irregular deffect region in manage display device
US20100271549A1 (en) * 2007-10-16 2010-10-28 Panasonic Corporation Image display device and image display method
CN109325930A (en) * 2018-09-12 2019-02-12 苏州优纳科技有限公司 Detection method, device and the detection device of boundary defect
CN110223296A (en) * 2019-07-08 2019-09-10 山东建筑大学 A kind of screw-thread steel detection method of surface flaw and system based on machine vision

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100271549A1 (en) * 2007-10-16 2010-10-28 Panasonic Corporation Image display device and image display method
US20100053204A1 (en) * 2008-08-26 2010-03-04 Lg Display Co., Ltd. Method for setting compensation region for irregular deffect region in manage display device
CN109325930A (en) * 2018-09-12 2019-02-12 苏州优纳科技有限公司 Detection method, device and the detection device of boundary defect
CN110223296A (en) * 2019-07-08 2019-09-10 山东建筑大学 A kind of screw-thread steel detection method of surface flaw and system based on machine vision

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
余加俊;骆文韬;徐飞鸿;魏长;: "智能清漂船河道边界图像识别算法" *

Also Published As

Publication number Publication date
CN110717902B (en) 2023-06-09

Similar Documents

Publication Publication Date Title
CN107657606B (en) Method and device for detecting brightness defect of display device
CN111815630B (en) Defect detection method and device for LCD screen
JP6358351B1 (en) Surface defect inspection method and surface defect inspection apparatus
CN109345528A (en) A kind of display screen defect inspection method and device based on human-eye visual characteristic
CN115456956B (en) Method, equipment and storage medium for detecting scratches of liquid crystal display
CN116188462B (en) Noble metal quality detection method and system based on visual identification
CN109741324B (en) Detection method, detection device and terminal equipment
CN105913415A (en) Image sub-pixel edge extraction method having extensive adaptability
CN108509908B (en) Pupil diameter real-time measurement method based on binocular stereo vision
CN112215810B (en) Fatigue test crack monitoring method and device
CN109557101A (en) A kind of defect detecting device and method of nonstandard high reflection curve surface work pieces
CN108447058B (en) Image quality evaluation method and system
CN113643276B (en) Textile texture defect automatic detection method based on statistical analysis
CN116152261B (en) Visual inspection system for quality of printed product
CN114646381B (en) Rotary mechanical vibration measuring method, system, equipment and storage medium
CN116468726B (en) Online foreign matter line detection method and system
CN109410197B (en) Method and device for positioning detection area of liquid crystal display
CN107230200A (en) A kind of method for extracting rotor coil contour feature
CN110717902A (en) Processing method for displaying image edge
Jeon et al. Defect detection algorithm for corner cracks in steel billet using discrete wavelet transform
CN117036266A (en) Industrial image anomaly detection method and system based on knowledge distillation
Maheshwari et al. Non-destructive quality analysis of Indian Basmati Oryza sativa SSP indica (Rice) using image processing
CN115761606A (en) Box electric energy meter identification method and device based on image processing
CN111008968A (en) Picture processing method and device and storage medium
CN118037726B (en) Railway accessory defect detection method and system

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