CN116485788A - Image processing method and mobile phone PET (polyethylene terephthalate) protective film priming process quality detection method - Google Patents

Image processing method and mobile phone PET (polyethylene terephthalate) protective film priming process quality detection method Download PDF

Info

Publication number
CN116485788A
CN116485788A CN202310713260.2A CN202310713260A CN116485788A CN 116485788 A CN116485788 A CN 116485788A CN 202310713260 A CN202310713260 A CN 202310713260A CN 116485788 A CN116485788 A CN 116485788A
Authority
CN
China
Prior art keywords
gray
light
image
light source
pixel points
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
CN202310713260.2A
Other languages
Chinese (zh)
Other versions
CN116485788B (en
Inventor
禹利文
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.)
Dongguan Huachi Polymer Material Co ltd
Original Assignee
Dongguan Huachi Polymer Material 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 Dongguan Huachi Polymer Material Co ltd filed Critical Dongguan Huachi Polymer Material Co ltd
Priority to CN202310713260.2A priority Critical patent/CN116485788B/en
Publication of CN116485788A publication Critical patent/CN116485788A/en
Application granted granted Critical
Publication of CN116485788B publication Critical patent/CN116485788B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

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
    • G06T7/90—Determination of colour characteristics
    • 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
    • Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A30/00—Adapting or protecting infrastructure or their operation

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 Processing (AREA)

Abstract

The invention relates to the technical field of image processing, in particular to an image processing method and a mobile phone PET (polyethylene terephthalate) protective film priming process quality detection method. The method comprises the following steps: obtaining the corresponding light influence degree of each pixel point according to the gray values of the pixel points in the gray images of the sprayed mobile phone PET protective film under the irradiation of light sources with different incidence angles; constructing a corresponding light influence similarity distribution diagram according to the light influence degree corresponding to the pixel points in the window corresponding to each pixel point; and obtaining abnormal spraying characteristic values corresponding to each pixel point based on the light influence similarity distribution map, further obtaining weights corresponding to each coordinate position on the protective film under the irradiation of light sources of each incident angle, determining target gray values of each coordinate position on the protective film according to the weights, further obtaining a target image, and judging whether the mobile phone PET protective film is uniformly sprayed based on the target image. The invention improves the detection precision of the uniformity detection of the mobile phone PET protective film priming process.

Description

Image processing method and mobile phone PET (polyethylene terephthalate) protective film priming process quality detection method
Technical Field
The invention relates to the technical field of image processing, in particular to an image processing method and a mobile phone PET (polyethylene terephthalate) protective film priming process quality detection method.
Background
The PET protective film material is mainly used for protecting the surfaces of mobile phones and other electronic products, and has the advantages of light weight, high strength, good transparency, good gas barrier property, no toxicity, no smell and the like. The PET protective film material surface is generally sprayed with a coating to improve the adhesive force, scratch resistance, wear resistance and the like of the protective film. In order to achieve the corresponding purpose, the sprayed coating should be thin and uniform, and the problems of accumulation of coating materials, incomplete coverage and the like are avoided. After the PET protection film of the mobile phone is sprayed with the coating, the uniformity of spraying needs to be detected so as to ensure that the PET protection film material can meet the protection effect requirement on the surface of an electronic product. At present, the quality detection of the coating on the surface of a material generally focuses on the defect detection of the surface of the coating, such as black spots, crystal spots, scratches and the like, and a neural network is generally used for extracting the characteristics of the coating defects, so that the spray uniformity is judged, the characteristic that a mobile phone PET protective film has certain glossiness is ignored, because of the existence of the characteristics, the acquired image is inevitably interfered by a light source, so that the judgment of the spray uniformity is influenced, and therefore, the influence of light rays is required to be judged in the analysis process. In the process of judging the influence of light on the uniformity of a coating of a PET (polyethylene terephthalate) protective film of a mobile phone, generally, a surface image of the protective film under irradiation of a multi-angle light source is obtained, the gray average value of pixel points corresponding to the same position is used as a correction gray value corresponding to the position, the interference of illumination is reduced to a certain extent, but the average value is easily influenced by an extreme value, so that the uniformity detection precision of the process of base coating of the PET protective film of the mobile phone is lower.
Disclosure of Invention
In order to solve the problem of lower detection precision in the existing method for detecting the uniformity of the mobile phone PET protection film priming process, the invention aims to provide an image processing method and a mobile phone PET protection film priming process quality detection method, and the adopted technical scheme is as follows:
in a first aspect, the present invention provides an image processing method comprising the steps of:
acquiring gray images of the sprayed mobile phone PET protective film under the irradiation of light sources with different incidence angles;
obtaining the light influence degree corresponding to each pixel point in the gray level image under the irradiation of the light source of each incident angle according to the gray level value of each pixel point in the gray level image; constructing windows corresponding to all pixel points by taking the pixel points in the gray level image as the centers, and determining the light influence similarity index of each two pixel points in the gray level image under the irradiation of the light source with the same incident angle according to the light influence degree corresponding to the pixel points in the windows corresponding to all pixel points; constructing a light influence similarity distribution diagram corresponding to each pixel point in the gray image under the irradiation of the light source of each incident angle based on the light influence similarity index;
Screening suspected abnormal pixel points in the gray level image irradiated by the light source at each incident angle based on the light influence similarity distribution map; according to the suspected abnormal pixel points and the light influence similarity distribution diagram, spraying abnormal characteristic values corresponding to the pixel points in the gray level image irradiated by the light source at each incident angle are obtained; obtaining corresponding weights of all coordinate positions on the PET protection film of the mobile phone under the irradiation of light sources of all incident angles based on the abnormal spraying characteristic values, and determining target gray values of all coordinate positions on the PET protection film of the mobile phone according to the weights and gray values of all pixel points in gray images under the irradiation of the light sources of all the incident angles; and obtaining a target image of the PET protection film of the mobile phone based on the target gray value.
Preferably, the obtaining the light influence degree corresponding to each pixel point in the gray scale image under the irradiation of the light source of each incident angle according to the gray scale value of each pixel point in the gray scale image includes:
for the firstThe coordinates in the gray-scale image under the irradiation of the light source with the respective incidence angles are +.>Is a pixel of (1):
calculating the coordinates of the gray level image irradiated by the light source at all incident angles asThe average gray value of the pixel points is recorded as a first gray average value; calculate- >The coordinates in the gray-scale image under the irradiation of the light source with the respective incidence angles are +.>Gray of pixel point of (2)Absolute value of difference between the degree value and the first gray average value, said absolute value of difference being recorded as +.>The coordinates in the gray-scale image under the irradiation of the light source with the respective incidence angles are +.>The first difference index corresponding to the pixel points of (2) is calculated, and the coordinates in the gray level image irradiated by the light source at all incident angles are +.>The sum of the first difference indexes corresponding to the pixel points is marked as a first characteristic index, and the sum of the preset adjustment parameters and the first characteristic index is marked as a first characteristic value;
calculate the firstThe coordinates in the gray-scale image under the irradiation of the light source with the respective incidence angles are +.>The ratio of the first difference index corresponding to the pixel point of (2) to the first characteristic value is taken as the +.>The coordinates in the gray-scale image under the irradiation of the light source with the respective incidence angles are +.>A fluctuation index corresponding to the pixel point of (2); calculating the sum of the fluctuation index and a constant 1, and recording the sum as a second characteristic value;
calculate the firstThe coordinates in the gray-scale image under the irradiation of the light source with the respective incidence angles are +.>The product of the first difference index corresponding to the pixel point of (2) and the second characteristic value is taken as the +.>The coordinates in the gray-scale image under the irradiation of the light source with the respective incidence angles are +. >The light effect corresponding to the pixel points.
Preferably, the determining, according to the light influence degree corresponding to the pixel points in the window corresponding to each pixel point, a light influence similarity index of each two pixel points in the gray scale image irradiated by the light source with the same incident angle includes:
gray scale image under illumination of light source at any angle of incidence:
constructing a light influence degree sequence corresponding to each pixel point according to the light influence degrees corresponding to all the pixel points in the window corresponding to each pixel point in the gray level image; calculating the Pearson correlation coefficient of the light influence degree sequence corresponding to every two pixel points; calculating the absolute value of the difference value of the light influence degree corresponding to each two pixel points, and marking the absolute value as the light influence degree difference; recording the sum of the difference between the constant 1 and the light influence degree as a third characteristic value, calculating the ratio between the absolute value of the pearson correlation coefficient and the third characteristic value, and taking the ratio as the light influence similarity of two corresponding pixel points; and carrying out normalization processing on the light influence similarity to obtain light influence similarity indexes corresponding to the two pixel points.
Preferably, the constructing a light influence similarity distribution map corresponding to each pixel point in the gray scale image under the irradiation of the light source of each incident angle based on the light influence similarity index includes:
For the firstThe coordinates in the gray-scale image under the irradiation of the light source with the respective incidence angles are +.>Is a pixel of (1):
will be the firstEach pixel point and coordinate in gray level image under the irradiation of light source with various incident angles are +.>The light ray influence similarity index of the pixel points of (2) is filled in the corresponding position of each pixel point; marking the filled image as +.>The coordinates in the gray-scale image under the irradiation of the light source with the respective incidence angles are +.>The light corresponding to the pixel points of (c) affects the similarity distribution map.
Preferably, according to the suspected abnormal pixel point and the light influence similarity distribution diagram, a spraying abnormal characteristic value corresponding to each pixel point in the gray image under the irradiation of the light source of each incident angle is obtained, including:
marking any light ray influence similarity distribution graph as an image to be analyzed, and marking a region formed by suspected abnormal pixel points in the image to be analyzed as a suspected abnormal region;
calculating the average value of the light influence similarity indexes corresponding to all pixel points in a suspected abnormal region in an image to be analyzed, and marking the average value as a first similarity index average value; and calculating the product of the number of the pixel points in the suspected abnormal region in the image to be analyzed and the first similar index mean value, and taking the product as a spraying abnormal characteristic value corresponding to the corresponding pixel point.
Preferably, the obtaining the weight corresponding to each coordinate position on the mobile phone PET protection film under the light source irradiation of each incident angle based on the abnormal spraying characteristic value includes:
according to the spraying abnormal characteristic values corresponding to the pixel points at the same coordinate position in the gray image irradiated by the light source at each incident angle, constructing a characteristic matrix corresponding to each coordinate position on the PET protective film of the mobile phone; based on the feature matrix, the corresponding weight of each coordinate position on the PET protection film of the mobile phone under the irradiation of the light source of each incident angle is obtained.
Preferably, the determining the target gray value of each coordinate position on the PET protection film of the mobile phone according to the weight and the gray value of each pixel point in the gray image irradiated by the light source of each incident angle includes:
for the mobile phone PET protection film, the coordinates are as followsIs defined by the position of:
calculating the coordinates of the gray level image irradiated by the light source at each incident angle asThe product of the gray value of the pixel point and the corresponding weight is taken as the coordinate of +.>The position of the first characteristic index corresponds to the second characteristic index under each incident angle; coordinates on a PET protective film of the mobile phone are +.>The sum of the second characteristic indexes corresponding to the positions of the mobile phone PET protective film at all incidence angles is used as the coordinate of +. >Is a target gray value for the position of (a).
Preferably, the obtaining the target image of the PET protection film of the mobile phone based on the target gray value includes:
and (3) selecting one gray level image from the gray level images irradiated by the light sources with all incidence angles as an image to be corrected, replacing the gray level value of each pixel point in the image to be corrected with a corresponding target gray level value, and marking the replaced image as a target image of the PET protective film of the mobile phone.
Preferably, the screening the suspected abnormal pixel points in the gray scale image under the irradiation of the light source with each incident angle based on the light influence similarity distribution map includes:
will be the firstLight of various incident anglesThe coordinates in the gray image under source illumination are +.>The light influence similarity distribution diagram corresponding to the pixel points of the image is marked as an image to be analyzed, and coordinates in the image to be analyzed are +.>The pixel point of (2) is used as the center point, and the coordinate is judged to be +.>If so, selecting the pixel points with the light influence similarity index larger than or equal to the similarity index threshold, taking each selected pixel point as a center point, continuing to select the pixel points in the eight neighborhood until the light influence similarity indexes corresponding to all the pixel points in the eight neighborhood are smaller than the similarity index threshold, and marking the selected pixel points as suspected abnormal pixel points.
In a second aspect, the invention provides a method for detecting the quality of a primer coating process of a PET protective film of a mobile phone, which comprises the following steps: the target image of the PET protective film of the mobile phone is obtained by adopting the image processing method; judging whether the PET protection film of the mobile phone is uniformly sprayed according to the target image of the PET protection film of the mobile phone.
The invention has at least the following beneficial effects:
according to the invention, in order to reduce the influence of a light source on a spraying uniformity detection result of the mobile phone PET protection film, the gray values of the pixel points in the acquired image are required to be corrected, firstly, the gray images of the sprayed mobile phone PET protection film under the irradiation of light sources with different angles are analyzed, when light interference is generated under the irradiation of the light source with a certain incident angle, the gray values obtained under the irradiation of the light source with the incident angle are greatly different from the gray values obtained under the irradiation of the light source without interference, and according to the gray values of the pixel points in each gray image, the light influence degree corresponding to the pixel points in the gray images under the irradiation of the light source with the incident angle is used for representing the interference degree of the gray values of each coordinate position on the mobile phone PET protection film under the irradiation of the light source with each incident angle; in order to improve the judgment of the interference degree of the pixel points interfered by light, the invention combines the characteristics that the light influence exists in a region form and is not discretely distributed, constructs a light influence similarity distribution diagram corresponding to each pixel point in the gray level image irradiated by the light source of each incident angle according to the characteristics that the light influence degree corresponding to each pixel point in the region affected by the light is relatively close and relatively large, screens out suspected abnormal pixel points based on the light influence similarity distribution diagram, and further obtains a spraying abnormal characteristic value corresponding to each pixel point in the gray level image irradiated by the light source of each incident angle, wherein the spraying abnormal characteristic value reflects the abnormal significance of the spraying of the position of the pixel point; the invention is based on the spraying abnormal characteristic value, and corrects the gray value of the pixel point in the image by the rule of giving smaller weight to the gray value which is more influenced by the light and giving larger weight to the gray value which is not influenced by the light, thereby obtaining the target image of the PET protective film of the mobile phone, and the gray value of the pixel point in the target image furthest reduces the influence of the light.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions and advantages of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flowchart of an image processing method according to an embodiment of the present invention;
fig. 2 is a schematic diagram of the reference signs of the light influence degree of all the pixels in the window corresponding to any one pixel.
Detailed Description
In order to further describe the technical means and effects adopted by the invention to achieve the preset aim, the image processing method and the mobile phone PET protection film priming process quality detection method according to the invention are described in detail below with reference to the accompanying drawings and the preferred embodiments.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The specific scheme of the image processing method and the mobile phone PET protection film priming process quality detection method provided by the invention is specifically described below with reference to the accompanying drawings.
An embodiment of an image processing method:
the present embodiment proposes an image processing method, as shown in fig. 1, including the following steps:
step S1, gray images of the sprayed mobile phone PET protective film under the irradiation of light sources with different incidence angles are obtained.
The specific scene aimed at by this embodiment is: after the PET protection film of the mobile phone is coated, images corresponding to the PET protection film of the mobile phone under the irradiation of light sources with different angles are obtained, gray values of the same coordinate position on the surface of the PET protection film of the mobile phone under the irradiation of the light sources with different incidence angles are analyzed, gray values of each coordinate position on the surface of the PET protection film of the mobile phone are corrected, corrected images are obtained, interference of light is eliminated by the corrected images, and image quality is improved.
Based on the working principle of online image scanning of an industrial CCD camera, using a high-brightness LED industrial linear light-focusing light source with specific wavelength to irradiate the surface of the PET protection film of the mobile phone from different angles under the PET protection film of the mobile phone after spraying, using the industrial camera to collect RGB images of the surface of the PET protection film of the mobile phone under the irradiation of light sources with different incidence angles above the PET protection film after spraying in real time, carrying out graying treatment on the collected RGB images to obtain corresponding gray images, carrying out denoising treatment on the gray images by using Gaussian filtering, improving the quality of the images, and marking the denoised gray images as gray images of the PET protection film of the mobile phone under the irradiation of the light sources with different incidence angles; in this embodiment, the incident angles of the light sources are respectively 0 degrees, 15 degrees, 30 degrees, 45 degrees, 60 degrees, and 75 degrees, and in specific applications, the operator can adjust the incident angles according to specific situations. The image graying processing and the Gaussian filtering denoising are well known techniques and will not be repeated here. It should be noted that, the size of the mobile phone PET protection film to be detected may be larger, so that it is necessary to perform regional detection on the mobile phone PET protection film to be detected, the gray images of the mobile phone PET protection film under the irradiation of the light sources with different incident angles obtained in this embodiment are all images of the same region of the mobile phone PET protection film, and next, this embodiment will take a region as an example to describe, and the method provided in this embodiment can be used to process other regions of the mobile phone PET protection film to be detected.
So far, the gray level image of the sprayed mobile phone PET protective film under the irradiation of light sources with different incidence angles is obtained.
Step S2, obtaining the light influence degree corresponding to each pixel point in the gray level image under the irradiation of the light source of each incident angle according to the gray level value of each pixel point in the gray level image; constructing windows corresponding to all pixel points by taking the pixel points in the gray level image as the centers, and determining the light influence similarity index of each two pixel points in the gray level image under the irradiation of the light source with the same incident angle according to the light influence degree corresponding to the pixel points in the windows corresponding to all pixel points; and constructing a light influence similarity distribution diagram corresponding to each pixel point in the gray image under the irradiation of the light source of each incident angle based on the light influence similarity index.
According to the method, gray images of the sprayed mobile phone PET protection film under the irradiation of light sources with different incidence angles are analyzed, the significance that gray values of all positions on the mobile phone PET protection film are affected by light is obtained according to the characteristic that the light influence generated by the light sources with different angles is not in the same position and the gray value difference is small when the light influence is not affected by the light, the gray values of the positions greatly affected by the light are given with small weight, the gray values of the positions not affected by the light are given with large weight, the target gray values corresponding to all positions on the mobile phone PET protection film are obtained, and then the influence of the light on the spraying uniformity detection result of the mobile phone PET protection film is reduced to the maximum extent.
When the RGB images of the surface of the PET protection film of the mobile phone are collected under the irradiation of light sources with different incidence angles, the positions and the visual fields of the cameras are fixed, so that the images collected under the irradiation of the light sources with different incidence angles are all images of the same position of the surface of the PET protection film of the mobile phone, namely the gray images of the PET protection film of the mobile phone under the irradiation of the light sources with each incidence angle are all images of the same area of the surface of the PET protection film of the mobile phone, the images collected in the embodiment are rectangular, the pixel points at the top left corner vertex of each gray image are respectively taken as coordinate origins, the upper edge line of each gray image is taken as the transverse axis of the plane rectangular coordinate system, and the left edge line of each gray image is taken as the longitudinal axis of the plane rectangular coordinate system, so as to construct the plane rectangular coordinate system; by adopting the method provided by the embodiment, the rectangular coordinate system is constructed, so that the coordinate information of the same position on the PET protective film of the mobile phone in each gray level image is the same, namely, the pixel points in all gray level images are in one-to-one correspondence.
For any position on the PET protective film of the mobile phone, when the pixel point of the position is not interfered by light in the image, the gray value of the pixel point of the position is relatively close to the gray value of the same position under the irradiation of light sources with other incident angles; when the pixel point of the position is interfered by light rays irradiated by a light source with a certain incident angle, the gray value obtained under the incident angle of the light source is larger in difference from the gray value obtained when the pixel point is not interfered, and the larger the interfered pixel point is, the larger the gray value difference is; therefore, the present embodiment will analyze the consistency degree of the gray value corresponding to the position under the irradiation of the light source at each incident angle relative to the gray value corresponding to the light source at other incident angles, and when the consistency degree is larger, the light source corresponding to the incident angle is described The gray values obtained under irradiation are less likely to be affected by light. Based on this, in this embodiment, according to the gray value of each pixel point in the gray image irradiated by the light source of each incident angle, the light influence degree corresponding to each pixel point in the gray image irradiated by the light source of each incident angle is determined respectively; specifically, the coordinates in the gray scale image under the irradiation of the light source according to each incident angle areCalculating the gray value of the pixel point of the (B) and the coordinates of the gray image irradiated by the light source with all the incident angles as +.>The average gray value of the pixel points of (1) is recorded as a first gray average value, and the (i) th gray level is calculated>The coordinates in the gray-scale image under the irradiation of the light source with the respective incidence angles are +.>The absolute value of the difference between the gray value of the pixel point of (c) and the first gray average value reflects the coordinate of +.>Is positioned at->The difference between the corresponding gray value under the light source irradiation of each incident angle and the average gray value of the position under the light source irradiation of all incident angles is recorded as +.>The coordinates in the gray level image irradiated by the light source with various incident angles are as followsA first difference index corresponding to the pixel points of (a); calculating the coordinates of +. >The sum of the first difference indexes corresponding to the pixel points is marked as a first characteristic index, and the sum of the preset adjustment parameters and the first characteristic index is marked as a first characteristic value; calculate->The coordinates in the gray-scale image under the irradiation of the light source with the respective incidence angles are +.>The ratio of the first difference index corresponding to the pixel point of (2) to the first characteristic value is taken as the +.>The coordinates in the gray-scale image under the irradiation of the light source with the respective incidence angles are +.>A fluctuation index corresponding to the pixel point of (2); calculating the sum of the fluctuation index and a constant 1, recording the sum as a second characteristic value, and calculating the +.>The coordinates in the gray-scale image under the irradiation of the light source with the respective incidence angles are +.>The product of the first difference index and the second characteristic value corresponding to the pixel point of (2) is taken as the +.>The coordinates in the gray-scale image under the irradiation of the light source with the respective incidence angles are +.>Light influence degree corresponding to the pixel points of the display panel; first->The coordinates in the gray-scale image under the irradiation of the light source with the respective incidence angles are +.>The specific calculation formula of the light influence degree corresponding to the pixel points is as follows:
wherein, the liquid crystal display device comprises a liquid crystal display device,is->The coordinates in the gray-scale image under the irradiation of the light source with the respective incidence angles are +.>Light influence degree corresponding to pixel points of +.>Is->The coordinates in the gray-scale image under the irradiation of the light source with the respective incidence angles are +. >Fluctuation index corresponding to pixel point of +.>Is->The coordinates in the gray-scale image under the irradiation of the light source with the respective incidence angles are +.>Gray value of pixel of +.>Mid-position of gray scale image illuminated by light sources at all angles of incidenceMarked as->Average gray value of pixel of +.>For the total number of angles of incidence +.>For presetting the adjustment parameters, < >>To take absolute value symbols.
Representing a first gray mean>Indicate->The coordinates in the gray-scale image under the irradiation of the light source with the respective incidence angles are +.>The smaller the first difference index is, the coordinate on the PET protection film of the mobile phone is indicated as +.>Is positioned at->The closer the corresponding gray value is to the average gray value under the irradiation of the light source with the incident angle, the +.>The coordinates of the light source with the incidence angle on the PET protective film of the mobile phone are +.>The smaller the gray scale disturbance of the position of (2); />Representing a second characteristic value; />Representing a first characteristic index->The first characteristic value is represented, where the preset adjustment parameter is introduced to prevent the denominator from being 0, and the preset adjustment parameter is set to be 0.01 in this embodiment, and in a specific application, an implementer can set according to a specific situation; first->The coordinates in the gray-scale image under the irradiation of the light source with the respective incidence angles are +. >The light influence corresponding to the pixel points of (2) reflects the +.>The coordinates at each incident angle areThe larger the fluctuation of the gray value corresponding to the pixel point relative to the gray values corresponding to other incident angles, the larger the gray value difference of the gray value at the position relative to the gray value obtained by other incident angles is, and the more likely the gray value of the pixel point obtained by the incident angle is affected by light. When the first difference index is larger, the coordinates on the PET protective film of the mobile phone are shown asIs positioned at->The larger the difference between the corresponding gray value and the average gray value under the irradiation of the light source with the incidence angle is, the larger the corresponding fluctuation index is, and the coordinate on the PET protection film of the mobile phone is +.>The gray value of the position of (2) is subjected toFirst->The greater the interference of light rays at the individual angles of incidence, the greater the degree of light ray influence.
By adopting the method, the light influence degree corresponding to each pixel point in the gray image irradiated by the light source at each incident angle can be obtained.
When the surface of the PET protection film of the mobile phone is affected by light, the affected part generally appears in one area, and is not discretely distributed on the surface of the PET protection film of the mobile phone; in addition, the light influence degree corresponding to each pixel point in the affected area is relatively close and relatively large, so that the embodiment evaluates the regional characteristics of the affected light of each pixel point in the gray image irradiated by the light source at each incident angle based on the characteristics.
For the firstGray scale image under illumination of light source at various angles of incidence:
respectively taking each pixel point in the gray level image as a center point, constructing a window with the size of n x n, and setting the value of n as 3 in the embodiment as a window corresponding to each pixel point, wherein in the specific application, an implementer can set according to specific conditions; for any pixel point in the gray level image, acquiring the light influence degree corresponding to each pixel point in a window corresponding to the pixel point, marking the light influence degree from 1 to 9 according to the positions of the pixel points corresponding to the light influence degree in the window from left to right and from top to bottom, and marking a sequence consisting of the light influence degrees as a light influence degree sequence corresponding to the pixel point as shown in fig. 2; by adopting the method, the light influence degree sequence corresponding to each pixel point in the gray image under the irradiation of the light source with the incidence angle can be obtained, the pearson correlation coefficient of the light influence degree sequence corresponding to each two pixel points in the gray image under the irradiation of the light source with the incidence angle is calculated, the similarity of the light influence degree of surrounding pixel points corresponding to the two pixel points is used for representing, and the calculation method of the pearson correlation coefficient is used for calculating In the prior art, the details are not repeated here; considering whether the pearson correlation coefficient of the light influence degree sequences corresponding to the two pixel points can reflect the consistency of the degree of the light interference of the two pixel points and surrounding pixel points, when the absolute value of the pearson correlation coefficient of the light influence degree sequences corresponding to the two pixel points approaches to 1, the greater the correlation degree of the two light influence degree sequences is illustrated; the smaller the difference of the light influence degree corresponding to two pixel points in the same gray level image, the more similar the two pixel points are subjected to the interference degree of light; based on this, the coordinates in the gray-scale image irradiated with the light source for the incident angle areAccording to the pearson correlation coefficient of the light influence degree sequence corresponding to each pixel point in the gray level image where the pixel point is positioned and the difference of the light influence degree corresponding to each pixel point in the gray level image where the pixel point is positioned, calculating the light influence similarity of the pixel point and each pixel point in the gray level image where the pixel point is positioned; specifically, the coordinates in the gray-scale image under the irradiation of the light source for calculating the incident angle are +.>The light influence and the coordinates corresponding to the pixel points of (2) are +. >The absolute value of the difference value of the light influence degree corresponding to the pixel point of (2), the absolute value is recorded as the light influence degree difference, the sum of the constant 1 and the light influence degree difference is calculated, the absolute value is recorded as the third characteristic value, and the coordinate is calculated as +.>The pixel points and coordinates of (2) are +.>The ratio of the absolute value of the pearson correlation coefficient of the light influence degree sequence corresponding to the pixel point of (2) to the third characteristic value is taken as the coordinate of +_ in the gray image under the irradiation of the light source of the incident angle>The pixel points and coordinates of (2) are +.>The light of the pixel points of (a) affects the similarity; first->The coordinates in the gray-scale image under the irradiation of the light source with the respective incidence angles are +.>The pixel points and coordinates of (2) are +.>The specific calculation formula of the light influence similarity of the pixel points is as follows:
wherein, the liquid crystal display device comprises a liquid crystal display device,is->The coordinates in the gray-scale image under the irradiation of the light source with the respective incidence angles are +.>The pixel points and coordinates of (2) are +.>Light influence similarity of pixels of +.>Is->The coordinates in the gray-scale image under the irradiation of the light source with the respective incidence angles are +.>The pixel points and coordinates of (2) are +.>The pixels of (2) correspond to the pearson correlation coefficient of the light influence sequence,/o->Is->The coordinates in the gray-scale image under the irradiation of the light source with the respective incidence angles are +.>Light influence degree corresponding to pixel points of +. >Is->The coordinates in the gray-scale image under the irradiation of the light source with the respective incidence angles are +.>The light effect corresponding to the pixel points.
In this embodiment, when calculating the similarity of light influence, the absolute value of the pearson correlation coefficient is taken to prevent the influence of the positive and negative signs on the subsequent analysis, and the greater the correlation between the two light influence sequences, the greater the absolute value of the corresponding pearson correlation coefficient.Representing a third characteristic value. First->The coordinates in the gray-scale image under the irradiation of the light source with the respective incidence angles are +.>Each pixel point in the gray level image of the pixel point (C) and the pixel point (C) has a light influence similarity, and the light influence similarity reflects the light influence degree between the pixel point and other pixel pointsThe similarity between the two pixel points and the degree to which the pixel points are affected by light rays are that when the features presented by the two pixel points are similar and the difference of the light ray influence degrees corresponding to the two pixel points is smaller, the greater the similarity of the light ray influence of the pixel points relative to other pixel points is indicated, namely the more likely the two pixel points are the pixel points in the same area affected by the light rays.
By adopting the method, the first step can be obtainedThe coordinates in the gray-scale image under the irradiation of the light source with the respective incidence angles are +. >The light influence similarity of the pixel points of (2) and all the pixel points in the gray level image where the pixel points are positioned is normalized, the normalized light influence similarity is marked as a light influence similarity index, and the eenthitem is obtained>The coordinates in the gray-scale image under the irradiation of the light source with the respective incidence angles are +.>The light of the pixel points in the gray level image and the pixel points in the gray level image affects the similarity index. For->Any pixel point in gray level image under the irradiation of light source with multiple incident angles is set as +.>The light ray influence similarity index of the pixel point is filled in the corresponding position of the pixel point; filling the numerical value of each coordinate position in the image by adopting the method, and marking the filled image as the +.>The coordinates in the gray-scale image under the irradiation of the light source with the respective incidence angles are +.>The light corresponding to the pixel points of (c) affects the similarity distribution map.
By adopting the method, the light influence similarity distribution map corresponding to each pixel point in the gray level image under the irradiation of the light source with each incident angle can be obtained, and the fact that each pixel point in the gray level image under the irradiation of the light source with each incident angle has a corresponding light influence similarity distribution map is needed to be explained.
Step S3, screening suspected abnormal pixel points in the gray level image irradiated by the light source at each incident angle based on the light influence similarity distribution map; according to the suspected abnormal pixel points and the light influence similarity distribution diagram, spraying abnormal characteristic values corresponding to the pixel points in the gray level image irradiated by the light source at each incident angle are obtained; obtaining corresponding weights of all coordinate positions on the PET protection film of the mobile phone under the irradiation of light sources of all incident angles based on the abnormal spraying characteristic values, and determining target gray values of all coordinate positions on the PET protection film of the mobile phone according to the weights and gray values of all pixel points in gray images under the irradiation of the light sources of all the incident angles; and obtaining a target image of the PET protection film of the mobile phone based on the target gray value.
In the embodiment, in step S2, a light influence similarity distribution map corresponding to each pixel point in the gray scale image irradiated by the light source at each incident angle is obtained, followed by the following stepsThe coordinates in the gray-scale image under the irradiation of the light source with the respective incidence angles are +.>For example, a light influence similarity distribution diagram corresponding to the pixel points of (a) is described, and a similarity index threshold value is set +.>In this embodiment +.>The value of (2) is 0.8, In a specific application, the practitioner can set +.>Is a value of (2); will be->The coordinates in the gray-scale image under the irradiation of the light source with the respective incidence angles are +.>The light influence similarity distribution diagram corresponding to the pixel points of the image is marked as an image to be analyzed, and coordinates in the image to be analyzed are +.>The pixel point of (2) is used as the center point, and the coordinate is judged to be +.>Whether the light influence similarity index exists in eight adjacent domains of the pixel points of (2) is greater than or equal to +.>If the pixel points exist, selecting the light influence similarity index to be greater than or equal to +.>Taking each selected pixel as a central point, and continuing to select the pixels in the eight neighborhood until the light influence similarity index corresponding to all the pixels in the eight neighborhood is less than +.>Marking the selected pixels as suspected abnormal pixels, marking the region formed by all the suspected abnormal pixels in the image to be analyzed as a suspected abnormal region, wherein all the pixels in the suspected abnormal region and coordinates are +.>The light influence similarity of the pixel points of (2) is larger. When the number of pixels in the suspected abnormal region is larger, the suspected abnormal region is more likely to be subjected to lightThe more affected area and affected by light. Acquiring the number of pixels in a suspected abnormal region in an image to be analyzed, simultaneously calculating the average value of the light influence similarity indexes corresponding to all the pixels in the suspected abnormal region in the image to be analyzed according to the light influence similarity indexes corresponding to each pixel in the suspected abnormal region in the image to be analyzed, recording the average value as a first similarity index average value, calculating the product of the number of the pixels in the suspected abnormal region in the image to be analyzed and the first similarity index average value, and taking the product as the first similarity index average value >The coordinates in the gray-scale image under the irradiation of the light source with the respective incidence angles are +.>The spraying abnormal characteristic value corresponding to the pixel point reflects the significance of abnormal spraying at the position of the pixel point; when the number of the pixel points in the suspected abnormal region is larger and the average value of the first similarity index is larger, the coordinate is described as +.>The greater the similarity of the light influence between the pixel points of (a) and the suspected abnormal pixel points, the more likely the abnormal position is in spraying, namely the greater the abnormal spraying characteristic value is.
By adopting the method, the spraying abnormal characteristic value corresponding to each pixel point in the gray image irradiated by the light source at each incident angle can be obtained; it should be noted that, each pixel point in the gray image irradiated by the light source at each incident angle has a corresponding abnormal spraying characteristic value.
For the mobile phone PET protection film, the coordinates are as followsIs defined by the position of: the coordinates in the gray-scale image under illumination by the light source according to each angle of incidence are +.>Abnormal spraying characteristic value corresponding to pixel point of (3)Constructing a mobile phone PET protective film with a coordinate of +.>Is>The coordinates on the PET protective film of the mobile phone are +.>Is >The method comprises the following steps:
wherein, the liquid crystal display device comprises a liquid crystal display device,the coordinate of the PET protective film of the mobile phone is +.>Is a feature matrix corresponding to the position of->The coordinates in the gray-scale image under irradiation of the light source for the 1 st incident angle are +.>Spraying abnormal characteristic value corresponding to pixel points of (a), is added>The coordinates in the gray-scale image under irradiation of the light source for the 2 nd incident angle are +.>Spraying abnormal characteristic value corresponding to pixel points of (a), is added>Is->The coordinates in the gray-scale image under the irradiation of the light source with the respective incidence angles are +.>Spraying abnormal characteristic values corresponding to the pixel points.
The embodiment is directed to a feature matrixCalculating each weight by using an entropy weight method, namely obtaining the coordinate of +.>Corresponding weights of the positions of the lens are irradiated by the light source at each incident angle; the entropy weight method is an objective weighting method, the entropy weight of each index is calculated by utilizing information entropy according to the dispersion degree of data provided by each index, and then the entropy weight is corrected to a certain extent according to each index, so that objective index weight is obtained. The entropy weighting method is the prior art and will not be described in detail here. As other embodiments, other methods can be adopted to obtain the coordinate of +.>The positions of the mobile phone PET protective film are irradiated by the light source at each incident angle with corresponding weights, the spraying abnormal characteristic value and the weights are in negative correlation, and the sum of the weights corresponding to all gray images at each position on the mobile phone PET protective film is 1. When the abnormal spraying characteristic value is larger, the influence degree of light is larger, and the given weight is smaller, namely the influence on the correction gray value is smaller. According to the coordinate of +.about.on the PET protection film of the mobile phone >Corresponding weight under the irradiation of the light source of each incident angle, and the coordinates in the gray scale image under the irradiation of the light source of each incident angle are +.>Correcting gray values of pixel points of the mobile phone PET protective film, and determining that coordinates on the mobile phone PET protective film areTarget gray values for the positions of (a); specifically, coordinates in the gray-scale image under the irradiation of the light source at each incident angle are calculated asThe product of the spraying abnormal characteristic value corresponding to the pixel point and the corresponding weight is taken as the upper coordinate of the PET protective film of the mobile phoneThe corresponding second characteristic index of the position of the mobile phone PET protective film under each incident angle is calculated to be the coordinate of +.>The sum of the second characteristic indexes corresponding to the positions of all incidence angles is used as the coordinate of +.>Target gray values for the positions of (a); the coordinate on the PET protective film of the mobile phone is +.>The specific expression of the target gray value of the position of (a) is:
wherein, the liquid crystal display device comprises a liquid crystal display device,the coordinate of the PET protective film of the mobile phone is +.>Target gray value of the position of +.>For the total number of angles of incidence +.>Is->The coordinates in the gray-scale image under the irradiation of the light source with the respective incidence angles are +.>Gray value of pixel of +.>The coordinate of the PET protective film of the mobile phone is +.>Is positioned at->The light sources of the respective incident angles illuminate the corresponding weights. / >Representing that the coordinate on the PET protective film of the mobile phone is +.>Is positioned at->And the second characteristic index corresponds to the incidence angle.
By adopting the method, the target gray value of each coordinate position on the PET protection film of the mobile phone can be obtained, one gray image is selected from the gray images irradiated by the light sources at all incident angles and is recorded as an image to be corrected, the gray value of each pixel point in the image to be corrected is replaced by the corresponding target gray value, the image after the replacement is recorded as the target image of the PET protection film of the mobile phone, the interference of light is eliminated from the target image of the PET protection film of the mobile phone, and the image quality is improved.
An embodiment of a quality detection method for a mobile phone PET protective film priming process comprises the following steps:
in the embodiment, the method provided in step S1 to step S3 is adopted to obtain the target image of the mobile phone PET protection film, and then the spraying quality of the mobile phone PET protection film is detected based on the target image of the mobile phone PET protection film.
Processing a target image of a PET (polyethylene terephthalate) protective film of a mobile phone by adopting an LC (liquid Crystal) saliency algorithm to obtain a saliency image, wherein the saliency image is a gray level image, the LC saliency algorithm is one of image saliency detection algorithms, and the basic idea of the algorithm is as follows: calculating the global contrast of a certain pixel on the whole image, namely, taking the sum of the distances of the pixel and all other pixels in the image in color as the salient value of the pixel, and finally obtaining a salient image; the LC saliency algorithm is prior art and will not be described in detail here; setting gray threshold Sum quantity threshold->In this embodiment +.>Has a value of 100>A value of 20, which may be set by the practitioner according to the particular situation in a particular application; gray value in the salient image is more than or equal to +.>The pixel points of the PET protective film are marked as abnormal pixel points, and the abnormal pixel points are the pixel points of uneven spraying positions on the surface of the PET protective film of the mobile phone; when the number of abnormal pixel points in the salient image is more than or equal to +.>When the spraying quality of the PET protection film of the mobile phone is not uniform, namely the spraying quality of the PET protection film of the mobile phone is not qualified; when the number of abnormal pixels in the salient image is less than +.>And when the mobile phone PET protection film is sprayed uniformly, the mobile phone PET protection film spraying quality is qualified.
So far, by adopting the method provided by the embodiment, the detection of the quality of the mobile phone PET protection film priming process is completed.
In the embodiment, in order to reduce the influence of the light source on the spraying uniformity detection result of the mobile phone PET protection film, the gray values of the pixel points in the acquired image need to be corrected, and the gray images of the sprayed mobile phone PET protection film under the irradiation of light sources with different angles are analyzed first, when light interference is generated under the irradiation of the light source with a certain incident angle, the gray values obtained under the irradiation of the light source with the incident angle and the gray values obtained under the irradiation of the light source without interference have larger differences, and according to the gray values of the pixel points in each gray image, the light influence degree corresponding to the pixel points in the gray image under the irradiation of the light source with the incident angle is obtained, and the light influence degree is used for representing the degree of the interference of the gray values of each coordinate position on the mobile phone PET protection film under the irradiation of the light source with each incident angle; in order to improve the judgment of the interference degree of the pixel points interfered by the light, the embodiment combines the characteristics that the light influence exists in a region form and is not discretely distributed, constructs a light influence similarity distribution diagram corresponding to each pixel point in the gray level image irradiated by the light source of each incident angle according to the characteristic that the light influence degree corresponding to each pixel point in the region affected by the light is relatively close and relatively large, screens out suspected abnormal pixel points based on the light influence similarity distribution diagram, further obtains a spraying abnormal characteristic value corresponding to each pixel point in the gray level image irradiated by the light source of each incident angle, and the spraying abnormal characteristic value reflects the abnormal significance of the spraying of the position of the pixel point; according to the embodiment, based on the spraying abnormal characteristic value, the gray value of the pixel point in the image is corrected by the rule of giving smaller weight to the gray value which is more influenced by the light and giving larger weight to the gray value which is not influenced by the light, so that the target image of the PET protection film of the mobile phone is obtained, the influence of the light is furthest reduced by the gray value of the pixel point in the target image, and therefore, the uniformity detection is carried out on the PET protection film of the mobile phone after the spraying is finished on the basis of the target image, the interference of the light to the uniformity detection process is avoided, and the detection precision of the uniformity detection of the primer process of the PET protection film of the mobile phone is improved.

Claims (10)

1. An image processing method, characterized in that the method comprises the steps of:
acquiring gray images of the sprayed mobile phone PET protective film under the irradiation of light sources with different incidence angles;
obtaining the light influence degree corresponding to each pixel point in the gray level image under the irradiation of the light source of each incident angle according to the gray level value of each pixel point in the gray level image; constructing windows corresponding to all pixel points by taking the pixel points in the gray level image as the centers, and determining the light influence similarity index of each two pixel points in the gray level image under the irradiation of the light source with the same incident angle according to the light influence degree corresponding to the pixel points in the windows corresponding to all pixel points; constructing a light influence similarity distribution diagram corresponding to each pixel point in the gray image under the irradiation of the light source of each incident angle based on the light influence similarity index;
screening suspected abnormal pixel points in the gray level image irradiated by the light source at each incident angle based on the light influence similarity distribution map; according to the suspected abnormal pixel points and the light influence similarity distribution diagram, spraying abnormal characteristic values corresponding to the pixel points in the gray level image irradiated by the light source at each incident angle are obtained; obtaining corresponding weights of all coordinate positions on the PET protection film of the mobile phone under the irradiation of light sources of all incident angles based on the abnormal spraying characteristic values, and determining target gray values of all coordinate positions on the PET protection film of the mobile phone according to the weights and gray values of all pixel points in gray images under the irradiation of the light sources of all the incident angles; and obtaining a target image of the PET protection film of the mobile phone based on the target gray value.
2. The method for processing an image according to claim 1, wherein the obtaining the light influence corresponding to each pixel in the gray image under the irradiation of the light source with each incident angle according to the gray value of each pixel in the gray image comprises:
for the firstThe coordinates in the gray-scale image under the irradiation of the light source with the respective incidence angles are +.>Is a pixel of (1):
calculating the coordinates of the gray level image irradiated by the light source at all incident angles asThe average gray value of the pixel points is recorded as a first gray average value; calculate->The coordinates in the gray-scale image under the irradiation of the light source with the respective incidence angles are +.>The absolute value of the difference between the gray value of the pixel point of (2) and the first gray average value is recorded as +.>The coordinates in the gray-scale image under the irradiation of the light source with the respective incidence angles are +.>The first difference index corresponding to the pixel points of (2) is calculated, and the coordinates in the gray level image irradiated by the light source at all incident angles are +.>The sum of the first difference indexes corresponding to the pixel points is marked as a first characteristic index, and the sum of the preset adjustment parameters and the first characteristic index is marked as a first characteristic value;
calculate the firstThe coordinates in the gray-scale image under the irradiation of the light source with the respective incidence angles are +. >The ratio of the first difference index corresponding to the pixel point of (2) to the first characteristic value is taken as the +.>The coordinates in the gray-scale image under the irradiation of the light source with the respective incidence angles are +.>A fluctuation index corresponding to the pixel point of (2); calculating the sum of the fluctuation index and a constant 1, and recording the sum as a second characteristic value;
calculate the firstThe coordinates in the gray-scale image under the irradiation of the light source with the respective incidence angles are +.>The product of the first difference index corresponding to the pixel point of (2) and the second characteristic value is taken as the +.>The coordinates in the gray-scale image under the irradiation of the light source with the respective incidence angles are +.>The light effect corresponding to the pixel points.
3. The method for processing an image according to claim 1, wherein determining a similar index of light influence of each two pixels in a gray scale image under illumination of a light source at the same incident angle according to the light influence degree corresponding to the pixels in the window corresponding to each pixel comprises:
gray scale image under illumination of light source at any angle of incidence:
constructing a light influence degree sequence corresponding to each pixel point according to the light influence degrees corresponding to all the pixel points in the window corresponding to each pixel point in the gray level image; calculating the Pearson correlation coefficient of the light influence degree sequence corresponding to every two pixel points; calculating the absolute value of the difference value of the light influence degree corresponding to each two pixel points, and marking the absolute value as the light influence degree difference; recording the sum of the difference between the constant 1 and the light influence degree as a third characteristic value, calculating the ratio between the absolute value of the pearson correlation coefficient and the third characteristic value, and taking the ratio as the light influence similarity of two corresponding pixel points; and carrying out normalization processing on the light influence similarity to obtain light influence similarity indexes corresponding to the two pixel points.
4. The method of claim 1, wherein the constructing a light influence similarity distribution map corresponding to each pixel point in the gray scale image under the irradiation of the light source at each incident angle based on the light influence similarity index comprises:
for the firstThe coordinates in the gray-scale image under the irradiation of the light source with the respective incidence angles are +.>Is a pixel of (1):
will be the firstEach pixel point and coordinate in gray level image under the irradiation of light source with various incident angles are +.>The light ray influence similarity index of the pixel points of (2) is filled in the corresponding position of each pixel point; marking the filled image as +.>Light source with various incidence anglesThe coordinates in the gray-scale image under illumination are +.>The light corresponding to the pixel points of (c) affects the similarity distribution map.
5. The method of claim 4, wherein obtaining the spray anomaly characteristic value corresponding to each pixel in the gray image under the irradiation of the light source at each incident angle according to the suspected anomaly pixel and the light influence similarity distribution map, comprises:
marking any light ray influence similarity distribution graph as an image to be analyzed, and marking a region formed by suspected abnormal pixel points in the image to be analyzed as a suspected abnormal region;
Calculating the average value of the light influence similarity indexes corresponding to all pixel points in a suspected abnormal region in an image to be analyzed, and marking the average value as a first similarity index average value; and calculating the product of the number of the pixel points in the suspected abnormal region in the image to be analyzed and the first similar index mean value, and taking the product as a spraying abnormal characteristic value corresponding to the corresponding pixel point.
6. The method for processing an image according to claim 1, wherein the obtaining weights corresponding to the coordinate positions on the PET protection film of the mobile phone under the irradiation of the light source at each incident angle based on the abnormal spraying characteristic values comprises:
according to the spraying abnormal characteristic values corresponding to the pixel points at the same coordinate position in the gray image irradiated by the light source at each incident angle, constructing a characteristic matrix corresponding to each coordinate position on the PET protective film of the mobile phone; based on the feature matrix, the corresponding weight of each coordinate position on the PET protection film of the mobile phone under the irradiation of the light source of each incident angle is obtained.
7. The method according to claim 1, wherein determining the target gray value of each coordinate position on the PET protection film of the mobile phone according to the weight and the gray value of each pixel point in the gray image irradiated by the light source of each incident angle comprises:
For the mobile phone PET protection film, the coordinates are as followsIs defined by the position of:
calculating the coordinates of the gray level image irradiated by the light source at each incident angle asThe product of the gray value of the pixel point and the corresponding weight is taken as the coordinate of +.>The position of the first characteristic index corresponds to the second characteristic index under each incident angle; coordinates on a PET protective film of the mobile phone are +.>The sum of the second characteristic indexes corresponding to the positions of the mobile phone PET protective film at all incidence angles is used as the coordinate of +.>Is a target gray value for the position of (a).
8. The image processing method according to claim 1, wherein the obtaining the target image of the PET protection film of the mobile phone based on the target gray value comprises:
and (3) selecting one gray level image from the gray level images irradiated by the light sources with all incidence angles as an image to be corrected, replacing the gray level value of each pixel point in the image to be corrected with a corresponding target gray level value, and marking the replaced image as a target image of the PET protective film of the mobile phone.
9. The method according to claim 1, wherein the screening the suspected abnormal pixels in the gray-scale image under the irradiation of the light source at each incident angle based on the light ray influence similarity distribution map comprises:
Will be the firstThe coordinates in the gray-scale image under the irradiation of the light source with the respective incidence angles are +.>The light influence similarity distribution diagram corresponding to the pixel points of the image is marked as an image to be analyzed, and coordinates in the image to be analyzed are +.>The pixel point of (2) is taken as a central point, and the coordinate is determined asIf so, selecting the pixel points with the light influence similarity index larger than or equal to the similarity index threshold, taking each selected pixel point as a center point, continuing to select the pixel points in the eight neighborhood until the light influence similarity indexes corresponding to all the pixel points in the eight neighborhood are smaller than the similarity index threshold, and marking the selected pixel points as suspected abnormal pixel points.
10. The quality detection method of the mobile phone PET protection film priming process is characterized by comprising the following steps: a target image of a PET protective film of a mobile phone obtained by the image processing method of any one of claims 1 to 9; judging whether the PET protection film of the mobile phone is uniformly sprayed according to the target image of the PET protection film of the mobile phone.
CN202310713260.2A 2023-06-16 2023-06-16 Image processing method and mobile phone PET (polyethylene terephthalate) protective film priming process quality detection method Active CN116485788B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310713260.2A CN116485788B (en) 2023-06-16 2023-06-16 Image processing method and mobile phone PET (polyethylene terephthalate) protective film priming process quality detection method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310713260.2A CN116485788B (en) 2023-06-16 2023-06-16 Image processing method and mobile phone PET (polyethylene terephthalate) protective film priming process quality detection method

Publications (2)

Publication Number Publication Date
CN116485788A true CN116485788A (en) 2023-07-25
CN116485788B CN116485788B (en) 2023-08-29

Family

ID=87219853

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310713260.2A Active CN116485788B (en) 2023-06-16 2023-06-16 Image processing method and mobile phone PET (polyethylene terephthalate) protective film priming process quality detection method

Country Status (1)

Country Link
CN (1) CN116485788B (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116754566A (en) * 2023-08-17 2023-09-15 绍兴旭源新材料科技有限公司 Flexible folding screen protective film detection method

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
GB0412025D0 (en) * 2004-05-28 2004-06-30 Sony Uk Ltd Image processing
JP2008065651A (en) * 2006-09-08 2008-03-21 Ntt Data Corp Face image authentication method, face image authentication apparatus and program
US20200320296A1 (en) * 2017-12-22 2020-10-08 Hangzhou Ezviz Software Co., Ltd. Target detection method and apparatus
CN113538432A (en) * 2021-09-17 2021-10-22 南通蓝城机械科技有限公司 Part defect detection method and system based on image processing
CN114998333A (en) * 2022-08-02 2022-09-02 山东第一医科大学(山东省医学科学院) Computer vision detection method and system for light source characteristics
CN115170572A (en) * 2022-09-08 2022-10-11 山东瑞峰新材料科技有限公司 BOPP composite film surface gluing quality monitoring method
CN115294113A (en) * 2022-09-30 2022-11-04 南通佳木汇木制品有限公司 Wood veneer quality detection method
CN115908590A (en) * 2022-10-13 2023-04-04 新疆青卫舜源信息科技有限公司 Data intelligent acquisition method and system based on artificial intelligence

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
GB0412025D0 (en) * 2004-05-28 2004-06-30 Sony Uk Ltd Image processing
JP2008065651A (en) * 2006-09-08 2008-03-21 Ntt Data Corp Face image authentication method, face image authentication apparatus and program
US20200320296A1 (en) * 2017-12-22 2020-10-08 Hangzhou Ezviz Software Co., Ltd. Target detection method and apparatus
CN113538432A (en) * 2021-09-17 2021-10-22 南通蓝城机械科技有限公司 Part defect detection method and system based on image processing
CN114998333A (en) * 2022-08-02 2022-09-02 山东第一医科大学(山东省医学科学院) Computer vision detection method and system for light source characteristics
CN115170572A (en) * 2022-09-08 2022-10-11 山东瑞峰新材料科技有限公司 BOPP composite film surface gluing quality monitoring method
CN115294113A (en) * 2022-09-30 2022-11-04 南通佳木汇木制品有限公司 Wood veneer quality detection method
CN115908590A (en) * 2022-10-13 2023-04-04 新疆青卫舜源信息科技有限公司 Data intelligent acquisition method and system based on artificial intelligence

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
吴军;: "基于灰度分布梯度的织物疵点检测算法", 毛纺科技, no. 04, pages 80 - 84 *
曾凡锋;付亚南;李良旭;: "基于区域的光照不均文本图像校正方法", 计算机工程与设计, no. 12, pages 181 - 185 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116754566A (en) * 2023-08-17 2023-09-15 绍兴旭源新材料科技有限公司 Flexible folding screen protective film detection method
CN116754566B (en) * 2023-08-17 2023-10-31 绍兴旭源新材料科技有限公司 Flexible folding screen protective film detection method

Also Published As

Publication number Publication date
CN116485788B (en) 2023-08-29

Similar Documents

Publication Publication Date Title
CN111563889B (en) Liquid crystal screen Mura defect detection method based on computer vision
CN100367293C (en) Method and apparatus for optical inspection of a display
CN113570605B (en) Defect detection method and system based on liquid crystal display panel
Wang et al. Biologically inspired image enhancement based on Retinex
US8320658B2 (en) Unevenness inspection method, method for manufacturing display panel, and unevenness inspection apparatus
CN116030060B (en) Plastic particle quality detection method
CN116485788B (en) Image processing method and mobile phone PET (polyethylene terephthalate) protective film priming process quality detection method
US9582899B2 (en) Real-time digitally enhanced imaging for the prediction, application, and inspection of coatings
KR101640118B1 (en) Display unevenness detection method and device for display device
CN108169236A (en) A kind of cracks of metal surface detection method of view-based access control model
CN107680054A (en) Multisource image anastomosing method under haze environment
CN111474177A (en) Liquid crystal screen backlight foreign matter defect detection method based on computer vision
CN107742291B (en) Defect detection method and device for photovoltaic glass
CN115131354B (en) Laboratory plastic film defect detection method based on optical means
CN113608378B (en) Full-automatic defect detection method and system based on LCD (liquid crystal display) process
CN108898132A (en) A kind of terahertz image dangerous material recognition methods based on Shape context description
CN102938137A (en) Dynamic non-uniformity correction method for linear scanned image based on image sequence analysis
CN113034474A (en) Test method for wafer map of OLED display
CN107833223B (en) Fruit hyperspectral image segmentation method based on spectral information
CN115272256A (en) Sub-pixel level sensing optical fiber path Gaussian extraction method and system
CN108022219B (en) Two-dimensional image gray level correction method
CN116433669A (en) Machine vision-based quality detection method for weld joints of steel frame of anti-seismic structure
CN114092682A (en) Small hardware fitting defect detection algorithm based on machine learning
CN117670886B (en) Display screen defect detection method, device, equipment and storage medium
CN113808104A (en) Block-based metal surface 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