CN111325717B - Mobile phone defect position identification method and equipment - Google Patents
Mobile phone defect position identification method and equipment Download PDFInfo
- Publication number
- CN111325717B CN111325717B CN202010074696.8A CN202010074696A CN111325717B CN 111325717 B CN111325717 B CN 111325717B CN 202010074696 A CN202010074696 A CN 202010074696A CN 111325717 B CN111325717 B CN 111325717B
- Authority
- CN
- China
- Prior art keywords
- screen
- picture
- pixel
- photo
- taking
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Abstract
The invention aims to provide a mobile phone defect position identification method and equipment.
Description
Technical Field
The present invention relates to the field of computers, and in particular, to a method and apparatus for identifying a defect location of a mobile phone.
Background
In the process of mobile phone recovery, whether defects exist on a mobile phone screen or not needs to be detected. However, the existing detection scheme has the problem of inaccurate detection of screen defects.
Disclosure of Invention
The invention aims to provide a mobile phone defect position identification method and equipment.
According to one aspect of the present invention, there is provided a method for identifying a defective location of a mobile phone, the method comprising:
taking a screen photo of a mobile phone to be detected, and identifying a screen defect of the mobile phone to be detected from the screen photo;
Determining the plane pixel coordinates of the screen defect;
converting the plane pixel coordinates of the screen defects into three-dimensional coordinates based on a preset space conversion formula;
wherein, based on a preset space conversion formula, before converting the plane pixel coordinates of the screen defect into three-dimensional coordinates, the method further comprises:
the method comprises the steps of controlling an axis of a detection device to respectively click a plurality of non-linear points on a screen of a mobile phone to be detected, and correspondingly recording three-dimensional coordinates of clicking positions of each point and corresponding plane pixel coordinates sensed by the screen;
and obtaining the preset space conversion formula based on the axis coordinate of the clicking position of each point and the corresponding plane pixel coordinate.
Further, in the above method, taking a screen photo of the mobile phone to be detected, and identifying a screen defect of the mobile phone to be detected from the screen photo includes:
displaying the bright screen as a white background picture;
taking a screen picture comprising the white background picture;
identifying the boundary of the white background picture from the screen photo, and taking the boundary as the outline of the screen;
displaying the bright screen as a full-screen yellow picture, and controlling a light source to illuminate a screen area displayed as the full-screen yellow picture;
Taking a first photograph containing a screen area displayed as a full screen yellow picture;
displaying the screen as a full-screen white picture, and controlling the light source to illuminate a screen area displayed as the full-screen white picture;
taking a second photograph containing a screen area displayed as a full-screen white picture;
detecting whether a crack or a scratch exists in a range enclosed by the outline of the screen in the first photo or the second photo, and if so, judging that the crack or the scratch exists in the screen.
Further, in the above method, identifying a boundary of the white background picture from the screen photo, taking the boundary as an outline of the screen includes:
converting the screen photo into a gray picture;
designating a preset pixel threshold value T1 to divide the gray-scale picture, wherein the pixel value of a pixel point exceeding the preset pixel threshold value T1 in the picture is set to 255, and the pixel value of a pixel point not exceeding the preset pixel threshold value T1 in the picture is set to 0;
acquiring a continuous region of each pixel point with a pixel value of 255 in the gray level picture;
calculating the number of the pixels in the continuous area of each pixel, and screening the continuous area of each pixel, wherein the continuous area of the pixels with the number of the pixels smaller than a preset number threshold T2 is abandoned, and the continuous area of the pixels with the number of the pixels larger than or equal to the preset number threshold T2 is reserved;
Calculating the area of the minimum circumscribing rotation rectangle of each reserved pixel point continuous area, and calculating the fullness s of the minimum circumscribing rotation rectangle of each reserved pixel point continuous area, wherein the fullness s=the number of pixel points in a certain reserved pixel point continuous area/the area of the minimum circumscribing rotation rectangle of the reserved pixel point continuous area;
and taking a reserved continuous pixel point area with the fullness s larger than a preset fullness threshold T3 as a boundary of the white background picture, and taking the boundary as the outline of the screen.
Further, in the above method, detecting whether a crack or a scratch exists in a range enclosed by the outline of the screen in the first photo or the second photo, and if so, determining that the crack or the scratch exists in the screen includes:
detecting whether cracks or scratches exist in a range enclosed by the outline of the screen in the first photo or the second photo, if so, calculating the length of each crack or scratch, and if the number of the cracks or scratches with the length exceeding a preset length threshold exceeds a preset number threshold, judging that the cracks or scratches exist in the screen.
According to another aspect of the present invention, there is also provided a mobile phone defect location identifying apparatus, wherein the apparatus includes:
The mobile phone detection device comprises a first device, a second device and a third device, wherein the first device is used for shooting a screen photo of a mobile phone to be detected, and identifying screen defects of the mobile phone to be detected from the screen photo;
second means for determining planar pixel coordinates of the screen defect;
the third device is used for converting the plane pixel coordinates of the screen defects into three-dimensional coordinates based on a preset space conversion formula; the third device is further used for controlling the shaft of the detection equipment to respectively click a plurality of non-linear points on the screen of the mobile phone to be detected, and correspondingly recording the three-dimensional coordinates of the clicking position of each point and the corresponding plane pixel coordinates sensed by the screen; and obtaining the preset space conversion formula based on the axis coordinate of the clicking position of each point and the corresponding plane pixel coordinate.
Further, in the above device, the first means is configured to display a screen bright as a white background picture; taking a screen picture comprising the white background picture; identifying the boundary of the white background picture from the screen photo, and taking the boundary as the outline of the screen; displaying the bright screen as a full-screen yellow picture, and controlling a light source to illuminate a screen area displayed as the full-screen yellow picture; taking a first photograph containing a screen area displayed as a full screen yellow picture; displaying the screen as a full-screen white picture, and controlling the light source to illuminate a screen area displayed as the full-screen white picture; taking a second photograph containing a screen area displayed as a full-screen white picture; detecting whether a crack or a scratch exists in a range enclosed by the outline of the screen in the first photo or the second photo, and if so, judging that the crack or the scratch exists in the screen.
Further, in the above apparatus, the first means is configured to convert the screen photo into a grayscale picture; designating a preset pixel threshold value T1 to divide the gray-scale picture, wherein the pixel value of a pixel point exceeding the preset pixel threshold value T1 in the picture is set to 255, and the pixel value of a pixel point not exceeding the preset pixel threshold value T1 in the picture is set to 0; acquiring a continuous region of each pixel point with a pixel value of 255 in the gray level picture; calculating the number of the pixels in the continuous area of each pixel, and screening the continuous area of each pixel, wherein the continuous area of the pixels with the number of the pixels smaller than a preset number threshold T2 is abandoned, and the continuous area of the pixels with the number of the pixels larger than or equal to the preset number threshold T2 is reserved; calculating the area of the minimum circumscribing rotation rectangle of each reserved pixel point continuous area, and calculating the fullness s of the minimum circumscribing rotation rectangle of each reserved pixel point continuous area, wherein the fullness s=the number of pixel points in a certain reserved pixel point continuous area/the area of the minimum circumscribing rotation rectangle of the reserved pixel point continuous area; and taking a reserved continuous pixel point area with the fullness s larger than a preset fullness threshold T3 as a boundary of the white background picture, and taking the boundary as the outline of the screen.
Further, in the above device, the first means is configured to detect whether a crack or a scratch exists in a range enclosed by an outline of the screen in the first photograph or the second photograph, calculate a length of each crack or scratch if the crack or the scratch exists, and determine that the crack or the scratch exists on the screen if a number of cracks or scratches whose length exceeds a preset length threshold exceeds a preset number threshold.
According to another aspect of the present invention, there is also provided a computing-based apparatus, including:
a processor; and
a memory arranged to store computer executable instructions that, when executed, cause the processor to:
taking a screen photo of a mobile phone to be detected, and identifying a screen defect of the mobile phone to be detected from the screen photo;
determining the plane pixel coordinates of the screen defect;
converting the plane pixel coordinates of the screen defects into three-dimensional coordinates based on a preset space conversion formula;
wherein, based on a preset space conversion formula, before converting the plane pixel coordinates of the screen defect into three-dimensional coordinates, the method further comprises:
the method comprises the steps of controlling an axis of a detection device to respectively click a plurality of non-linear points on a screen of a mobile phone to be detected, and correspondingly recording three-dimensional coordinates of clicking positions of each point and corresponding plane pixel coordinates sensed by the screen;
And obtaining the preset space conversion formula based on the axis coordinate of the clicking position of each point and the corresponding plane pixel coordinate.
According to another aspect of the present invention, there is also provided a computer-readable storage medium having stored thereon computer-executable instructions, wherein the computer-executable instructions, when executed by a processor, cause the processor to:
taking a screen photo of a mobile phone to be detected, and identifying a screen defect of the mobile phone to be detected from the screen photo;
determining the plane pixel coordinates of the screen defect;
converting the plane pixel coordinates of the screen defects into three-dimensional coordinates based on a preset space conversion formula;
wherein, based on a preset space conversion formula, before converting the plane pixel coordinates of the screen defect into three-dimensional coordinates, the method further comprises:
the method comprises the steps of controlling an axis of a detection device to respectively click a plurality of non-linear points on a screen of a mobile phone to be detected, and correspondingly recording three-dimensional coordinates of clicking positions of each point and corresponding plane pixel coordinates sensed by the screen;
and obtaining the preset space conversion formula based on the axis coordinate of the clicking position of each point and the corresponding plane pixel coordinate.
Compared with the prior art, the method and the device have the advantages that the screen defects of the mobile phone to be detected are identified from the screen photos by taking the screen photos of the mobile phone to be detected, then the plane pixel coordinates of the screen defects are determined, and then the plane pixel coordinates of the screen defects are converted into three-dimensional coordinates based on the preset space conversion formula, so that the three-dimensional coordinate positions of the screen defects can be accurately and efficiently located.
Drawings
Other features, objects and advantages of the present application will become more apparent upon reading of the detailed description of non-limiting embodiments, made with reference to the accompanying drawings in which:
fig. 1 is a flowchart of a method for identifying a defect location of a mobile phone according to an embodiment of the application.
The same or similar reference numbers in the drawings refer to the same or similar parts.
Detailed Description
The application is described in further detail below with reference to the accompanying drawings.
In one exemplary configuration of the application, the terminal, the device of the service network, and the trusted party each include one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of computer-readable media.
Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer readable media, as defined herein, does not include non-transitory computer readable media (transmission media), such as modulated data signals and carrier waves.
As shown in fig. 1, the present invention provides a method for identifying a defect location of a mobile phone, where the method includes:
step S1, taking a screen photo of a mobile phone to be detected, and identifying a screen defect of the mobile phone to be detected from the screen photo;
step S2, determining the plane pixel coordinates of the screen defect;
and step S3, converting the plane pixel coordinates of the screen defect into three-dimensional coordinates based on a preset space conversion formula.
The method and the device can accurately and efficiently locate the three-dimensional coordinate position of the screen defect by taking the screen picture of the mobile phone to be detected, identifying the screen defect of the mobile phone to be detected from the screen picture, determining the plane pixel coordinate of the screen defect, and converting the plane pixel coordinate of the screen defect into the three-dimensional coordinate based on a preset space conversion formula.
In an embodiment of the present invention, step S3, before converting the plane pixel coordinates of the screen defect into three-dimensional coordinates based on a preset space conversion formula, further includes:
step S31, controlling the axis of the detection device to respectively click a plurality of points which are not straight lines on the screen of the mobile phone to be detected,
step S32, correspondingly recording the three-dimensional coordinates of the clicking position of each point and the corresponding plane pixel coordinates sensed by the screen;
Step S33, obtaining the preset space conversion formula based on the axis coordinates of the click position of each point and the corresponding plane pixel coordinates.
The predetermined spatial conversion formula may be, for example, a spatial conversion matrix.
The three-dimensional coordinates of the clicking positions of the points and the corresponding plane pixel coordinates sensed by the screen are correspondingly recorded by controlling the shaft of the detection equipment to respectively click a plurality of non-linear points on the screen of the mobile phone to be detected, and the preset space conversion formula can be accurately and reliably obtained subsequently based on the three-dimensional coordinates of the clicking positions of the points and the corresponding plane pixel coordinates sensed by the screen.
In an embodiment of the mobile phone defect position identification method of the present invention, step S1, taking a screen photo of a mobile phone to be detected, identifying a screen defect of the mobile phone to be detected from the screen photo, includes:
step S111, displaying a bright screen as a white background picture;
step S112, taking a screen photo comprising the white background picture;
when shooting the mobile phone screen, simultaneously shooting irrelevant areas outside the screen area, and subsequently identifying the screen area;
step S113, identifying the boundary of the white background picture from the screen photo, and taking the boundary as the outline of the screen;
Step S114, displaying the bright screen as a full-screen yellow picture, and controlling the light source to illuminate a screen area displayed as the full-screen yellow picture;
step S115, taking a first picture containing a screen area displayed as a full-screen yellow picture;
here, in order to ensure the definition of the subsequent photographed picture, the screen area displayed as the full-screen yellow picture may be illuminated by controlling the light source to supplement the light to the screen area displayed as the full-screen yellow picture;
step S116, displaying the bright screen as a full-screen white picture, and controlling the light source to illuminate a screen area displayed as the full-screen white picture;
here, in order to ensure the definition of the subsequent photographed picture, the screen area displayed as the full-screen white picture may be illuminated by controlling the light source to supplement the light to the screen area displayed as the full-screen white picture;
step S117, taking a second picture including a screen area displayed as a full-screen white picture;
step S118, detecting whether a crack or a scratch exists in a range enclosed by the outline of the screen in the first photo or the second photo, and if so, determining that the crack or the scratch exists in the screen.
Here, the display definition of the different types of cracks or scratches may be different in the screen area of the full-screen white screen or the screen area of the full-screen yellow screen, and thus, the first photograph including the screen area displayed as the full-screen yellow screen and the second photograph including the screen area displayed as the full-screen white screen may be photographed separately to ensure the definition of the different types of screen cracks or scratches photographed later.
If a crack or a scratch is detected in one of the first photograph or the second photograph, it may be determined that the crack or the scratch exists in the screen.
According to the invention, the screen is displayed as the white background picture, and the screen position of the equipment can be simply and accurately positioned based on the boundary of the white background picture. In addition, the invention facilitates the subsequent reliable identification of different kinds of screen cracks or scratches within the range enclosed by the outline of the screen in the first photo or the second photo by respectively taking a first photo containing the screen area displayed as a full-screen yellow picture and a second photo containing the screen area displayed as a full-screen white picture.
In an embodiment of the mobile phone defect location recognition method of the present invention, step S113, which recognizes a boundary of the white background picture from the screen photo, uses the boundary as an outline of the screen, includes:
step S1131, converting the screen photo into a gray picture;
step S1132, designating a preset pixel threshold T1 to segment the gray-scale picture, wherein the pixel value of the pixel point in the picture exceeding the preset pixel threshold T1 is set to 255, and the pixel value of the pixel point in the picture not exceeding the preset pixel threshold T1 is set to 0;
Step S1133, obtaining a continuous region of each pixel point with a pixel value of 255 in the gray scale picture;
here, a certain pixel point is within 8 adjacent to another pixel point, and can be considered to be continuous, and 2 or more continuous pixel points can form a continuous pixel point region;
a pixel point with a pixel value of 0 being black, wherein a pixel point with a pixel value of 255 represents a white pixel point, and a connection area of the pixel point with the pixel value of 0 is not needed to be considered, and is regarded as a background outside a screen area;
step S1134, calculating the number of the pixel points in the continuous area of each pixel point, and screening the continuous area of each pixel point, wherein the continuous area of the pixel points, the number of which is smaller than the preset number threshold T2, is discarded, and the continuous area of the pixel points, the number of which is larger than or equal to the preset number threshold T2, is reserved;
step S1135, calculating the area of the minimum circumscribing rectangle of the continuous area of each reserved pixel point, and calculating the fullness S of the minimum circumscribing rectangle of the continuous area of each reserved pixel point, wherein the fullness s=the number of pixel points in the continuous area of a certain reserved pixel point/the area of the minimum circumscribing rectangle of the continuous area of the reserved pixel point;
Step S1136, using the region with the saturation S greater than the preset saturation threshold T3, where the reserved pixels are continuous, as the boundary of the white background picture, and using the boundary as the contour of the screen.
The continuous area of each reserved pixel point can be traversed, the number of the pixel points of the continuous area of each reserved pixel point is divided by the area of the minimum circumscribed rotation rectangle to obtain the plumpness s of the area, if the plumpness s of the continuous area of a certain reserved pixel point is larger than the preset plumpness threshold value T3, the continuous area is a screen area, and if the continuous area of the certain reserved pixel point is smaller than the preset plumpness threshold value T3, the continuous area is a non-screen area.
In the implementation, the gray picture gray is segmented by designating a preset pixel threshold T1; calculating the number of the pixel points in the continuous area of each pixel point, and screening the continuous area of each pixel point; calculating the area of the minimum circumscribed rotation rectangle of each reserved pixel point continuous area, and calculating the fullness s of the minimum circumscribed rotation rectangle of each reserved pixel point continuous area; and taking a reserved continuous pixel point area with the fullness s larger than a preset fullness threshold T3 as a boundary of the white background picture and taking the boundary as the outline of the screen, so that the screen positions of various terminals can be accurately and reliably identified.
In an embodiment of the method for identifying a location of a mobile phone defect, step S118 of detecting whether a crack or a scratch exists in a range enclosed by an outline of the screen in the first photo or the second photo, and if so, determining that the crack or the scratch exists in the screen includes:
detecting whether cracks or scratches exist in a range enclosed by the outline of the screen in the first photo or the second photo, if so, calculating the length of each crack or scratch, and if the number of the cracks or scratches with the length exceeding a preset length threshold exceeds a preset number threshold, judging that the cracks or scratches exist in the screen.
Here, by calculating the length of each crack or scratch and calculating whether the number of cracks or scratches with the length exceeding the preset length threshold exceeds the preset number threshold, cracks or scratches meeting the requirements can be reliably screened, and the screen can be more accurately judged to have cracks or scratches.
In an embodiment of the mobile phone defect position identification method of the present invention, step S1, taking a screen photo of a mobile phone to be detected, identifying a screen defect of the mobile phone to be detected from the screen photo, includes:
step S121, determining the outline position of a screen of a mobile phone to be detected;
Step S122, controlling the screen to display a full-screen yellow image lower than a preset exposure value, and shooting a yellow screen image based on the outline position of the screen;
step S123, controlling the screen to display a full-screen black image higher than a preset exposure value, and shooting a black screen image based on the outline position of the screen;
here, the purpose of taking the high and low exposure value pictures is: the high exposure value picture is favorable for shooting the surface texture of the dark screen, but the overexposure problem is easy to occur for the surface texture of the bright screen, so that the low exposure value picture is needed to be used for auxiliary detection;
the purpose of shooting black and yellow pictures is as follows: experiments show that different types of lines have different definition under different background color pictures, so that black and yellow pictures with good experimental effects are selected as the backgrounds;
step S124, inputting the yellow screen image into a convolutional neural network, and extracting image features corresponding to the yellow screen image; inputting the black screen image into a convolutional neural network, and extracting image features corresponding to the black screen image;
here, the convolutional neural network may be a resnext101 convolutional neural network to extract accurate image features;
And step S125, obtaining target candidate frames with the target categories of scratch categories and crack categories in the yellow screen image and the black screen image respectively based on the image characteristics corresponding to the yellow screen image and the black screen image.
According to the invention, the target candidate frames with the target categories of scratch categories and broken cracks in the yellow screen image and the black screen image are obtained based on the image characteristics corresponding to the yellow screen image and the black screen image respectively, so that the scratch or broken cracks on the screen of the equipment such as the mobile phone can be accurately identified, and the efficiency of valuation and recovery of intelligent equipment such as the mobile phone can be improved.
In an embodiment of the method for identifying a defect position of a mobile phone, step S125, obtaining target candidate frames with target categories of scratch categories and crack categories in the yellow screen image and the black screen image based on image features corresponding to the yellow screen image and the black screen image, respectively, includes:
step S1251, based on the image features corresponding to the yellow screen image, obtaining multiple feature layers with different scales corresponding to the yellow screen image by a FPN (feature pyramid networks) method; based on the image features corresponding to the black screen image and the image features corresponding to the black screen image, obtaining corresponding multi-layer feature layers with different scales corresponding to the black screen image through an FPN method;
Step S1252, extracting target candidate frames in the yellow screen image through a RPN (Region Proposal Network) network at multi-layer feature layers with different scales corresponding to the yellow screen image, and presetting probability values of scratch and crack existence of each target candidate frame in the yellow screen image; extracting target candidate frames in the black screen image through an RPN network on multi-layer characteristic layers with different scales corresponding to the black screen image, and presetting probability values of scratch lines and broken cracks of each target candidate frame in the black screen image;
step S1253, selecting a pre-set number of target candidate frames in the yellow screen image with a larger probability value; selecting a preset number of target candidate frames in the black screen image with a larger probability value;
here, the first 1000 target candidate boxes in the yellow screen image with a larger probability value may be selected; selecting the first 1000 target candidate frames in the black screen image with larger probability value;
step S1254, inputting the previous preset number of target candidate boxes in the yellow screen image into a classification neural network, and obtaining probability values of each target candidate box in the previous preset number of target candidate boxes in the yellow screen image, which belong to a background category, a scratch category and a crack category, respectively; inputting the target candidate frames with the preset number in the black screen image into a classification neural network, and acquiring probability values of each target candidate frame belonging to a background category, a scratch category and a crack category respectively;
Here, the classification neural network may be a full-connection layer classification neural network to obtain reliable class alike;
step S1255, determining the corresponding category with a larger probability value of each target candidate frame as the initial category of the target candidate frame;
here, for example, if the neural network outputs that the probability value of the background class of a certain target candidate frame a is 0.2, the probability value of the scratch class is 0.3, and the probability value of the crack class is 0.5, then the initial class of the target candidate frame a is the crack class;
for another example, the neural network outputs that the probability value of the background category of a certain target candidate frame b is 0.1, the probability value of the scratch category is 0.2, and the probability value of the crack category is 0.7, so that the initial category of the target candidate frame b is the crack category;
step S1256, if it is determined that the probability value of the initial class of the target candidate frame of the initial class is greater than the preset probability threshold, determining the initial class as the target class of the target candidate frame;
here, for example, the preset probability threshold is 0.6,
the neural network outputs that the initial category of a certain target candidate frame a is a crushed crack category, the probability value of the crushed crack category is 0.5, and the initial category of the crushed crack category of the target candidate frame a cannot be used as the target category because the preset probability threshold value of the crushed crack category is not exceeded 0.6;
For another example, the neural network outputs that the initial category of a certain target candidate frame b is a crushed crack category, the probability value of the crushed crack category is 0.7, and the initial category of the crushed crack category of the target candidate frame b can be used as the target category because the probability value exceeds a preset probability threshold value of 0.6;
step S1257, output the target candidate frame for which the target category is determined as the scratch category and the crack category.
In this embodiment, by determining the initial category of the target candidate frame and then screening the target candidate frame of the determined target category from the target candidate frames of the determined initial category, the scratch or the crack on the screen of the device such as the mobile phone can be further reliably and accurately identified.
In one embodiment of the mobile phone defect location recognition method of the present invention, step S1257, outputting a target candidate frame with the determined target category being a scratch category and a crack category, includes:
step S12571, performing descending order on the target candidate frames with the overlapping positions of the determined target categories in the yellow screen image based on the probability values to obtain a first ordering queue, taking the target candidate frame with the highest probability value in the first ordering queue as a first reference candidate frame, and deleting the target candidate frame and the target category corresponding to the target candidate frame if the overlapping area of each target candidate frame in the subsequent queues in the first ordering queue and the first reference candidate frame is a threshold value of the area of the first reference candidate frame exceeding a preset proportion;
Step S12572, arranging the target candidate frames with overlapping positions of the determined target categories in the black screen image in a descending order based on the probability values to obtain a second sorting queue, taking the target candidate frame with the highest probability value in the second sorting queue as a second reference candidate frame, and deleting the target candidate frame and the corresponding target category if the overlapping area of each subsequent target candidate frame in the second sorting queue and the second reference candidate frame exceeds the threshold value of the area of the second reference candidate frame with the preset proportion;
step S12573, outputting a target candidate frame in which the target category is determined to be the scratch category and the crack category.
Here, the preset ratio threshold may be 0.7, and when the overlapping area of each target candidate frame in the subsequent queues in the sorting queue and the reference candidate frame exceeds the area of the reference candidate frame by 0.7, deleting the target candidate frame and the target class corresponding to the target candidate frame;
according to the embodiment, each subsequent target candidate frame with the overlapping area exceeding the area threshold value of the standard candidate frame with the preset proportion is subjected to further filtering and deleting, so that the output target candidate frames with the target categories of scratch and broken crack can be reliably determined.
In an embodiment of the mobile phone defect location identifying method of the present invention, step S121, determining a contour location of a screen of a mobile phone to be detected includes:
step S1211, displaying the screen bright as a white background screen;
step S1212, taking a picture of a screen comprising the white background picture;
when the screen is shot, irrelevant areas outside the screen area are shot at the same time, and the screen area needs to be identified later;
step S1213, identifying the boundary of the white background picture from the photograph, and taking the boundary as the position of the outline of the screen.
Here, the present invention can simply and accurately locate the screen position of the device based on the boundary of the white background picture by displaying the screen as the white background picture.
In one embodiment of the mobile phone defect location identifying method of the present invention, step S1213, identifying a boundary of the white background picture from the photograph, and taking the boundary as a location of an outline of the screen includes:
step S12131, converting the photo into a gray-scale picture;
step S12132, designating a preset pixel threshold T1 to divide the gray-scale picture, wherein the pixel value of the pixel point in the picture exceeding the preset pixel threshold T1 is set to 255, and the pixel value of the pixel point in the picture not exceeding the preset pixel threshold T1 is set to 0;
Step S12133, obtaining a continuous area of each pixel point with a pixel value of 255 in the gray scale picture;
here, a certain pixel point is within 8 adjacent to another pixel point, and can be considered to be continuous, and 2 or more continuous pixel points can form a continuous pixel point region;
a pixel point with a pixel value of 0 being black, wherein a pixel point with a pixel value of 255 represents a white pixel point, and a connection area of the pixel point with the pixel value of 0 is not needed to be considered, and is regarded as a background outside a screen area;
step S12134, calculating the number of the pixels in the continuous area of each pixel, and screening the continuous area of each pixel, wherein the continuous area of the pixels with the number of the pixels smaller than the preset number threshold T2 is discarded, and the continuous area of the pixels with the number of the pixels larger than or equal to the preset number threshold T2 is reserved;
step S12135, calculating the area of the minimum circumscribing rectangle of each reserved pixel point continuous area, and calculating the fullness S of the minimum circumscribing rectangle of each reserved pixel point continuous area, wherein the fullness s=the number of pixels in a certain reserved pixel point continuous area/the area of the minimum circumscribing rectangle of the reserved pixel point continuous area;
Step S12136, taking the area with continuous reserved pixels with the fullness S greater than the preset fullness threshold T3 as the boundary of the white background picture, and taking the boundary as the position of the outline of the screen.
The continuous area of each reserved pixel point can be traversed, the number of the pixel points of the continuous area of each reserved pixel point is divided by the area of the minimum circumscribed rotation rectangle to obtain the plumpness s of the area, if the plumpness s of the continuous area of a certain reserved pixel point is larger than the preset plumpness threshold value T3, the continuous area is a screen area, and if the continuous area of the certain reserved pixel point is smaller than the preset plumpness threshold value T3, the continuous area is a non-screen area.
In the implementation, the gray picture gray is segmented by designating a preset pixel threshold T1; calculating the number of the pixel points in the continuous area of each pixel point, and screening the continuous area of each pixel point; calculating the area of the minimum circumscribed rotation rectangle of each reserved pixel point continuous area, and calculating the fullness s of the minimum circumscribed rotation rectangle of each reserved pixel point continuous area; and taking a reserved continuous pixel point area with the fullness s larger than a preset fullness threshold T3 as a boundary of the white background picture and taking the boundary as the position of the outline of the screen, so that the screen positions of various terminals can be accurately and reliably identified.
According to another aspect of the present invention, there is also provided a mobile phone defect position identifying apparatus, wherein the apparatus includes:
the mobile phone detection device comprises a first device, a second device and a third device, wherein the first device is used for shooting a screen photo of a mobile phone to be detected, and identifying screen defects of the mobile phone to be detected from the screen photo;
second means for determining planar pixel coordinates of the screen defect;
the third device is used for converting the plane pixel coordinates of the screen defects into three-dimensional coordinates based on a preset space conversion formula, and is also used for controlling the shaft of the detection equipment to respectively click a plurality of non-linear points on the screen of the mobile phone to be detected, and correspondingly recording the three-dimensional coordinates of the clicking position of each point and the corresponding plane pixel coordinates sensed by the screen; and obtaining the preset space conversion formula based on the axis coordinate of the clicking position of each point and the corresponding plane pixel coordinate.
According to another aspect of the present invention, there is also provided a computing-based apparatus, including:
a processor; and
a memory arranged to store computer executable instructions that, when executed, cause the processor to:
taking a screen photo of a mobile phone to be detected, and identifying a screen defect of the mobile phone to be detected from the screen photo;
Determining the plane pixel coordinates of the screen defect;
converting the plane pixel coordinates of the screen defects into three-dimensional coordinates based on a preset space conversion formula;
wherein, based on a preset space conversion formula, before converting the plane pixel coordinates of the screen defect into three-dimensional coordinates, the method further comprises:
the method comprises the steps of controlling an axis of a detection device to respectively click a plurality of non-linear points on a screen of a mobile phone to be detected, and correspondingly recording three-dimensional coordinates of clicking positions of each point and corresponding plane pixel coordinates sensed by the screen;
and obtaining the preset space conversion formula based on the axis coordinate of the clicking position of each point and the corresponding plane pixel coordinate.
According to another aspect of the present invention, there is also provided a computer-readable storage medium having stored thereon computer-executable instructions, wherein the computer-executable instructions, when executed by a processor, cause the processor to:
taking a screen photo of a mobile phone to be detected, and identifying a screen defect of the mobile phone to be detected from the screen photo;
determining the plane pixel coordinates of the screen defect;
converting the plane pixel coordinates of the screen defects into three-dimensional coordinates based on a preset space conversion formula;
wherein, based on a preset space conversion formula, before converting the plane pixel coordinates of the screen defect into three-dimensional coordinates, the method further comprises:
The method comprises the steps of controlling an axis of a detection device to respectively click a plurality of non-linear points on a screen of a mobile phone to be detected, and correspondingly recording three-dimensional coordinates of clicking positions of each point and corresponding plane pixel coordinates sensed by the screen;
and obtaining the preset space conversion formula based on the axis coordinate of the clicking position of each point and the corresponding plane pixel coordinate.
Details of each device and storage medium embodiment of the present application may refer to corresponding parts of each method embodiment, and are not described herein.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present application without departing from the spirit or scope of the application. Thus, it is intended that the present application also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.
It should be noted that the present application may be implemented in software and/or a combination of software and hardware, e.g., using Application Specific Integrated Circuits (ASIC), a general purpose computer or any other similar hardware device. In one embodiment, the software program of the present application may be executed by a processor to perform the steps or functions described above. Likewise, the software programs of the present application (including associated data structures) may be stored on a computer readable recording medium, such as RAM memory, magnetic or optical drive or diskette and the like. In addition, some steps or functions of the present application may be implemented in hardware, for example, as circuitry that cooperates with the processor to perform various steps or functions.
Furthermore, portions of the present invention may be implemented as a computer program product, such as computer program instructions, which when executed by a computer, may invoke or provide methods and/or techniques in accordance with the present invention by way of operation of the computer. Program instructions for invoking the inventive methods may be stored in fixed or removable recording media and/or transmitted via a data stream in a broadcast or other signal bearing medium and/or stored within a working memory of a computer device operating according to the program instructions. An embodiment according to the invention comprises an apparatus comprising a memory for storing computer program instructions and a processor for executing the program instructions, wherein the computer program instructions, when executed by the processor, trigger the apparatus to operate a method and/or a solution according to the embodiments of the invention as described above.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential characteristics thereof. The present embodiments are, therefore, to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned. Furthermore, it is evident that the word "comprising" does not exclude other elements or steps, and that the singular does not exclude a plurality. A plurality of units or means recited in the apparatus claims can also be implemented by means of one unit or means in software or hardware. The terms first, second, etc. are used to denote a name, but not any particular order.
Claims (8)
1. A mobile phone defect position identification method includes:
taking a screen photo of a mobile phone to be detected, and identifying a screen defect of the mobile phone to be detected from the screen photo;
determining the plane pixel coordinates of the screen defect;
converting the plane pixel coordinates of the screen defects into three-dimensional coordinates based on a preset space conversion formula;
wherein, based on a preset space conversion formula, before converting the plane pixel coordinates of the screen defect into three-dimensional coordinates, the method further comprises:
the method comprises the steps of controlling an axis of a detection device to respectively click a plurality of non-linear points on a screen of a mobile phone to be detected, and correspondingly recording three-dimensional coordinates of clicking positions of each point and corresponding plane pixel coordinates sensed by the screen;
obtaining the preset space conversion formula based on the axis coordinate of the clicking position of each point and the corresponding plane pixel coordinate, wherein the preset space conversion formula is a space conversion matrix;
taking a screen photo of a mobile phone to be detected, identifying a screen defect of the mobile phone to be detected from the screen photo, and comprising the following steps:
displaying the bright screen as a white background picture;
taking a screen picture comprising the white background picture;
identifying the boundary of the white background picture from the screen photo, and taking the boundary as the outline of the screen;
Displaying the bright screen as a full-screen yellow picture, and controlling a light source to illuminate a screen area displayed as the full-screen yellow picture;
taking a first photograph containing a screen area displayed as a full screen yellow picture;
displaying the screen as a full-screen white picture, and controlling the light source to illuminate a screen area displayed as the full-screen white picture;
taking a second photograph containing a screen area displayed as a full-screen white picture;
detecting whether a crack or a scratch exists in a range enclosed by the outline of the screen in the first photo or the second photo, and if so, judging that the crack or the scratch exists in the screen.
2. The method of claim 1, wherein identifying the boundary of the white background picture from the screen photograph, the boundary being an outline of the screen, comprises:
converting the screen photo into a gray picture;
designating a preset pixel threshold value T1 to divide the gray-scale picture, wherein the pixel value of a pixel point exceeding the preset pixel threshold value T1 in the picture is set to 255, and the pixel value of a pixel point not exceeding the preset pixel threshold value T1 in the picture is set to 0;
acquiring a continuous region of each pixel point with a pixel value of 255 in the gray level picture;
Calculating the number of the pixels in the continuous area of each pixel, and screening the continuous area of each pixel, wherein the continuous area of the pixels with the number of the pixels smaller than a preset number threshold T2 is abandoned, and the continuous area of the pixels with the number of the pixels larger than or equal to the preset number threshold T2 is reserved;
calculating the area of the minimum circumscribing rotation rectangle of each reserved pixel point continuous area, and calculating the fullness s of the minimum circumscribing rotation rectangle of each reserved pixel point continuous area, wherein the fullness s=the number of pixel points in a certain reserved pixel point continuous area/the area of the minimum circumscribing rotation rectangle of the reserved pixel point continuous area;
and taking a reserved continuous pixel point area with the fullness s larger than a preset fullness threshold T3 as a boundary of the white background picture, and taking the boundary as the outline of the screen.
3. The method of claim 1, wherein detecting whether a crack or a scratch exists within a range enclosed by the outline of the screen in the first photograph or the second photograph, and if so, determining that the crack or the scratch exists on the screen comprises:
detecting whether cracks or scratches exist in a range enclosed by the outline of the screen in the first photo or the second photo, if so, calculating the length of each crack or scratch, and if the number of the cracks or scratches with the length exceeding a preset length threshold exceeds a preset number threshold, judging that the cracks or scratches exist in the screen.
4. A mobile phone defect location identification device, wherein the device comprises:
the mobile phone detection device comprises a first device, a second device and a third device, wherein the first device is used for shooting a screen photo of a mobile phone to be detected, and identifying screen defects of the mobile phone to be detected from the screen photo;
second means for determining planar pixel coordinates of the screen defect;
the third device is used for converting the plane pixel coordinates of the screen defects into three-dimensional coordinates based on a preset space conversion formula; the third device is further used for controlling the shaft of the detection equipment to respectively click a plurality of non-linear points on the screen of the mobile phone to be detected, and correspondingly recording the three-dimensional coordinates of the clicking position of each point and the corresponding plane pixel coordinates sensed by the screen; obtaining the preset space conversion formula based on the axis coordinate of the clicking position of each point and the corresponding plane pixel coordinate, wherein the preset space conversion formula is a space conversion matrix;
the first device is used for displaying a screen as a white background picture; taking a screen picture comprising the white background picture; identifying the boundary of the white background picture from the screen photo, and taking the boundary as the outline of the screen; displaying the bright screen as a full-screen yellow picture, and controlling a light source to illuminate a screen area displayed as the full-screen yellow picture; taking a first photograph containing a screen area displayed as a full screen yellow picture; displaying the screen as a full-screen white picture, and controlling the light source to illuminate a screen area displayed as the full-screen white picture; taking a second photograph containing a screen area displayed as a full-screen white picture; detecting whether a crack or a scratch exists in a range enclosed by the outline of the screen in the first photo or the second photo, and if so, judging that the crack or the scratch exists in the screen.
5. The apparatus of claim 4, wherein the first means for converting the screen photograph to a grayscale picture; designating a preset pixel threshold value T1 to divide the gray-scale picture, wherein the pixel value of a pixel point exceeding the preset pixel threshold value T1 in the picture is set to 255, and the pixel value of a pixel point not exceeding the preset pixel threshold value T1 in the picture is set to 0; acquiring a continuous region of each pixel point with a pixel value of 255 in the gray level picture; calculating the number of the pixels in the continuous area of each pixel, and screening the continuous area of each pixel, wherein the continuous area of the pixels with the number of the pixels smaller than a preset number threshold T2 is abandoned, and the continuous area of the pixels with the number of the pixels larger than or equal to the preset number threshold T2 is reserved; calculating the area of the minimum circumscribing rotation rectangle of each reserved pixel point continuous area, and calculating the fullness s of the minimum circumscribing rotation rectangle of each reserved pixel point continuous area, wherein the fullness s=the number of pixel points in a certain reserved pixel point continuous area/the area of the minimum circumscribing rotation rectangle of the reserved pixel point continuous area; and taking a reserved continuous pixel point area with the fullness s larger than a preset fullness threshold T3 as a boundary of the white background picture, and taking the boundary as the outline of the screen.
6. The apparatus according to claim 4, wherein the first means is configured to detect whether a crack or a scratch exists within a range enclosed by an outline of the screen in the first photograph or the second photograph, calculate a length of each crack or scratch if the crack or the scratch exists, and determine that the crack or the scratch exists on the screen if a number of cracks or scratches whose length exceeds a preset length threshold exceeds a preset number threshold.
7. A computing-based device, comprising:
a processor; and
a memory arranged to store computer executable instructions that, when executed, cause the processor to:
taking a screen photo of a mobile phone to be detected, and identifying a screen defect of the mobile phone to be detected from the screen photo;
determining the plane pixel coordinates of the screen defect;
converting the plane pixel coordinates of the screen defects into three-dimensional coordinates based on a preset space conversion formula;
wherein, based on a preset space conversion formula, before converting the plane pixel coordinates of the screen defect into three-dimensional coordinates, the method further comprises:
the method comprises the steps of controlling an axis of a detection device to respectively click a plurality of non-linear points on a screen of a mobile phone to be detected, and correspondingly recording three-dimensional coordinates of clicking positions of each point and corresponding plane pixel coordinates sensed by the screen;
Obtaining the preset space conversion formula based on the axis coordinate of the clicking position of each point and the corresponding plane pixel coordinate, wherein the preset space conversion formula is a space conversion matrix;
taking a screen photo of a mobile phone to be detected, identifying a screen defect of the mobile phone to be detected from the screen photo, and comprising the following steps:
displaying the bright screen as a white background picture;
taking a screen picture comprising the white background picture;
identifying the boundary of the white background picture from the screen photo, and taking the boundary as the outline of the screen;
displaying the bright screen as a full-screen yellow picture, and controlling a light source to illuminate a screen area displayed as the full-screen yellow picture;
taking a first photograph containing a screen area displayed as a full screen yellow picture;
displaying the screen as a full-screen white picture, and controlling the light source to illuminate a screen area displayed as the full-screen white picture;
taking a second photograph containing a screen area displayed as a full-screen white picture;
detecting whether a crack or a scratch exists in a range enclosed by the outline of the screen in the first photo or the second photo, and if so, judging that the crack or the scratch exists in the screen.
8. A computer-readable storage medium having stored thereon computer-executable instructions, wherein the computer-executable instructions, when executed by a processor, cause the processor to:
taking a screen photo of a mobile phone to be detected, and identifying a screen defect of the mobile phone to be detected from the screen photo;
determining the plane pixel coordinates of the screen defect;
converting the plane pixel coordinates of the screen defects into three-dimensional coordinates based on a preset space conversion formula;
wherein, based on a preset space conversion formula, before converting the plane pixel coordinates of the screen defect into three-dimensional coordinates, the method further comprises:
the method comprises the steps of controlling an axis of a detection device to respectively click a plurality of non-linear points on a screen of a mobile phone to be detected, and correspondingly recording three-dimensional coordinates of clicking positions of each point and corresponding plane pixel coordinates sensed by the screen;
obtaining the preset space conversion formula based on the axis coordinate of the clicking position of each point and the corresponding plane pixel coordinate, wherein the preset space conversion formula is a space conversion matrix;
taking a screen photo of a mobile phone to be detected, identifying a screen defect of the mobile phone to be detected from the screen photo, and comprising the following steps:
displaying the bright screen as a white background picture;
Taking a screen picture comprising the white background picture;
identifying the boundary of the white background picture from the screen photo, and taking the boundary as the outline of the screen;
displaying the bright screen as a full-screen yellow picture, and controlling a light source to illuminate a screen area displayed as the full-screen yellow picture;
taking a first photograph containing a screen area displayed as a full screen yellow picture;
displaying the screen as a full-screen white picture, and controlling the light source to illuminate a screen area displayed as the full-screen white picture;
taking a second photograph containing a screen area displayed as a full-screen white picture;
detecting whether a crack or a scratch exists in a range enclosed by the outline of the screen in the first photo or the second photo, and if so, judging that the crack or the scratch exists in the screen.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010074696.8A CN111325717B (en) | 2020-01-21 | 2020-01-21 | Mobile phone defect position identification method and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010074696.8A CN111325717B (en) | 2020-01-21 | 2020-01-21 | Mobile phone defect position identification method and equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111325717A CN111325717A (en) | 2020-06-23 |
| CN111325717B true CN111325717B (en) | 2023-08-29 |
Family
ID=71166186
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010074696.8A Active CN111325717B (en) | 2020-01-21 | 2020-01-21 | Mobile phone defect position identification method and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111325717B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020167849A1 (en) | 2019-02-12 | 2020-08-20 | Ecoatm, Llc | Connector carrier for electronic device kiosk |
| JP2021530793A (en) | 2019-02-18 | 2021-11-11 | エコエーティーエム， エルエルシー | Neural networks based on physical state assessment of electronic devices, and associated systems and methods |
| US11922467B2 (en) | 2020-08-17 | 2024-03-05 | ecoATM, Inc. | Evaluating an electronic device using optical character recognition |
| DE102020213828B4 (en) * | 2020-11-03 | 2022-12-01 | Volkswagen Aktiengesellschaft | Inspection device and method for checking an object manufactured by means of a sintering process for possible defects |
| CN113610774B (en) * | 2021-07-16 | 2024-01-09 | 广州大学 | Glass scratch defect detection method, system, device and storage medium |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107749268A (en) * | 2017-10-27 | 2018-03-02 | 歌尔科技有限公司 | Screen detection method and equipment |
| CN108280822A (en) * | 2017-12-20 | 2018-07-13 | 歌尔科技有限公司 | The detection method and device of screen cut |
| CN108460757A (en) * | 2018-02-11 | 2018-08-28 | 深圳市鑫信腾科技有限公司 | A kind of mobile phone TFT-LCD screens Mura defects online automatic detection method |
| CN109211207A (en) * | 2018-06-29 | 2019-01-15 | 南京邮电大学 | A kind of screw identification and positioning device based on machine vision |
| CN109765245A (en) * | 2019-02-25 | 2019-05-17 | 武汉精立电子技术有限公司 | Large scale display screen defects detection localization method |
| CN110084801A (en) * | 2019-04-28 | 2019-08-02 | 深圳回收宝科技有限公司 | A kind of detection method of terminal screen, device, portable terminal and storage medium |
| CN110506252A (en) * | 2017-11-27 | 2019-11-26 | 华为技术有限公司 | Based on the transformational relation positioning terminal screen for indicating graphical dots coordinate in pattern |
| CN110570411A (en) * | 2019-09-05 | 2019-12-13 | 中国科学院长春光学精密机械与物理研究所 | mura detection method and device based on coefficient of variation |
| CN110609037A (en) * | 2019-07-12 | 2019-12-24 | 北京旷视科技有限公司 | Product defect detection system and method |
| CN110675399A (en) * | 2019-10-28 | 2020-01-10 | 上海悦易网络信息技术有限公司 | Screen appearance flaw detection method and equipment |
| CN110672617A (en) * | 2019-09-14 | 2020-01-10 | 华南理工大学 | Method for detecting defects of silk-screen area of glass cover plate of smart phone based on machine vision |
-
2020
- 2020-01-21 CN CN202010074696.8A patent/CN111325717B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107749268A (en) * | 2017-10-27 | 2018-03-02 | 歌尔科技有限公司 | Screen detection method and equipment |
| CN110506252A (en) * | 2017-11-27 | 2019-11-26 | 华为技术有限公司 | Based on the transformational relation positioning terminal screen for indicating graphical dots coordinate in pattern |
| CN108280822A (en) * | 2017-12-20 | 2018-07-13 | 歌尔科技有限公司 | The detection method and device of screen cut |
| CN108460757A (en) * | 2018-02-11 | 2018-08-28 | 深圳市鑫信腾科技有限公司 | A kind of mobile phone TFT-LCD screens Mura defects online automatic detection method |
| CN109211207A (en) * | 2018-06-29 | 2019-01-15 | 南京邮电大学 | A kind of screw identification and positioning device based on machine vision |
| CN109765245A (en) * | 2019-02-25 | 2019-05-17 | 武汉精立电子技术有限公司 | Large scale display screen defects detection localization method |
| CN110084801A (en) * | 2019-04-28 | 2019-08-02 | 深圳回收宝科技有限公司 | A kind of detection method of terminal screen, device, portable terminal and storage medium |
| CN110609037A (en) * | 2019-07-12 | 2019-12-24 | 北京旷视科技有限公司 | Product defect detection system and method |
| CN110570411A (en) * | 2019-09-05 | 2019-12-13 | 中国科学院长春光学精密机械与物理研究所 | mura detection method and device based on coefficient of variation |
| CN110672617A (en) * | 2019-09-14 | 2020-01-10 | 华南理工大学 | Method for detecting defects of silk-screen area of glass cover plate of smart phone based on machine vision |
| CN110675399A (en) * | 2019-10-28 | 2020-01-10 | 上海悦易网络信息技术有限公司 | Screen appearance flaw detection method and equipment |
Non-Patent Citations (1)
| Title |
|---|
| 张弘等.《图像处理与分析》.2019,第135页. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111325717A (en) | 2020-06-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111325717B (en) | Mobile phone defect position identification method and equipment | |
| CN111325716B (en) | Screen scratch and fragmentation detection method and equipment | |
| CN110060237B (en) | Fault detection method, device, equipment and system | |
| CN111311556B (en) | Mobile phone defect position identification method and equipment | |
| US9740967B2 (en) | Method and apparatus of determining air quality | |
| CN107749268B (en) | Screen detection method and equipment | |
| CN111292302B (en) | Screen detection method and device | |
| CN109977191B (en) | Problem map detection method, device, electronic equipment and medium | |
| CN111627009A (en) | Screen detection method and device and head-mounted display equipment | |
| WO2021147386A1 (en) | Screen scratch and crack detection method and device | |
| JP5779089B2 (en) | Edge detection apparatus, edge detection program, and edge detection method | |
| CN110288612B (en) | Nameplate positioning and correcting method and device | |
| CN111126393A (en) | Vehicle appearance refitting judgment method and device, computer equipment and storage medium | |
| CN111626295A (en) | Training method and device for license plate detection model | |
| CN112634201A (en) | Target detection method and device and electronic equipment | |
| CN113781396B (en) | Screen defect detection method, device, equipment and storage medium | |
| CN114821274A (en) | Method and device for identifying state of split and combined indicator | |
| CN113920434A (en) | Image reproduction detection method, device and medium based on target | |
| CN112287905A (en) | Vehicle damage identification method, device, equipment and storage medium | |
| CN115345895B (en) | Image segmentation method and device for visual detection, computer equipment and medium | |
| CN116681677A (en) | Lithium battery defect detection method, device and system | |
| CN117218633A (en) | Article detection method, device, equipment and storage medium | |
| CN115222653B (en) | Test method and device | |
| US20220335650A1 (en) | Methods and Systems for Training a Machine Learning Method for Determining Pre-Determined Points in an Image | |
| CN115760854A (en) | Deep learning-based power equipment defect detection method and device and electronic equipment |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: Room 1101-1103, No. 433, Songhu Road, Yangpu District, Shanghai Applicant after: Shanghai wanwansheng Environmental Protection Technology Group Co.,Ltd. Address before: Room 1101-1103, No. 433, Songhu Road, Yangpu District, Shanghai Applicant before: SHANGHAI YUEYI NETWORK INFORMATION TECHNOLOGY Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |