CN111178147A - Screen crushing and grading method, device, equipment and computer readable storage medium - Google Patents
Screen crushing and grading method, device, equipment and computer readable storage medium Download PDFInfo
- Publication number
- CN111178147A CN111178147A CN201911244445.3A CN201911244445A CN111178147A CN 111178147 A CN111178147 A CN 111178147A CN 201911244445 A CN201911244445 A CN 201911244445A CN 111178147 A CN111178147 A CN 111178147A
- Authority
- CN
- China
- Prior art keywords
- screen
- crushing
- photo
- breaking
- area
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 54
- 238000012795 verification Methods 0.000 claims abstract description 42
- 238000001514 detection method Methods 0.000 claims abstract description 36
- 238000003062 neural network model Methods 0.000 claims description 18
- 238000004590 computer program Methods 0.000 claims description 16
- 238000013467 fragmentation Methods 0.000 claims description 15
- 238000006062 fragmentation reaction Methods 0.000 claims description 15
- 238000013507 mapping Methods 0.000 claims description 13
- 238000012549 training Methods 0.000 claims description 10
- 238000010586 diagram Methods 0.000 description 10
- 230000008569 process Effects 0.000 description 8
- 238000013528 artificial neural network Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 238000013527 convolutional neural network Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 241001156002 Anthonomus pomorum Species 0.000 description 1
- 206010024796 Logorrhoea Diseases 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 229910052704 radon Inorganic materials 0.000 description 1
- SYUHGPGVQRZVTB-UHFFFAOYSA-N radon atom Chemical compound [Rn] SYUHGPGVQRZVTB-UHFFFAOYSA-N 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/20—Scenes; Scene-specific elements in augmented reality scenes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/08—Insurance
Abstract
The application provides a screen crushing and grading method, a screen crushing and grading device, screen crushing and grading equipment and a computer readable storage medium, wherein the method comprises the following steps: acquiring a screen breaking claim photo, and performing authenticity verification on the screen breaking claim photo; when the photo of the claims on the screen breaking passes the authenticity check, acquiring a screen breaking area in the photo of the claims on the screen breaking through a preset screen breaking detection model; and determining the screen crushing grade of the screen crushing claim photo according to a preset screen crushing degree grading model and the screen crushing area. The application relates to image detection, and the authenticity check is carried out on the broken screen claim settlement photo, so that the check photo can be accurately and quickly checked, the screen breaking degree can be automatically evaluated, and the cheating insurance risk is reduced.
Description
Technical Field
The present application relates to the field of image detection technologies, and in particular, to a screen breaking and grading method, device, and apparatus, and a computer-readable storage medium.
Background
With the popularization and application of electronic devices, such as smart phones, tablet computers, electronic learning machines and electronic readers, problems of depreciation and screen breakage of the electronic devices also arise, especially the problem of screen breakage, screens of the electronic devices are generally expensive, and a certain amount of money needs to be spent for replacing the broken screens, which brings loss to users. At present, the money loss after screen breaking can be reduced by applying insurance screen breaking risk, and when the screen breaking occurs to the electronic equipment applied by the user, the settlement claim can be initiated to the insurance company, and the insurance company checks and guarantees the damage.
The traditional check and guarantee damage is that the check and guarantee personnel check whether the electronic equipment of claim is the electronic equipment of user insurance by comparing the screen breaking photo of claim and the screen photo of electronic equipment of insurance manually, and after the check is passed, the screen breaking degree is evaluated according to experience. Therefore, how to accurately and rapidly check the photos and evaluate the screen breakage degree is a problem to be solved urgently at present.
Disclosure of Invention
The present application is directed to a screen breaking and grading method, device, and apparatus, and a computer readable storage medium, for checking photos and evaluating screen breaking degree accurately and rapidly.
In a first aspect, the present application provides a screen crushing and grading method, including the steps of:
acquiring a screen breaking claim photo, and performing authenticity verification on the screen breaking claim photo;
when the photo of the claims on the screen breaking passes the authenticity check, acquiring a screen breaking area in the photo of the claims on the screen breaking through a preset screen breaking detection model;
and determining the screen crushing grade of the screen crushing claim photo according to a preset screen crushing degree grading model and the screen crushing area.
In a second aspect, the present application further provides a screen crushing grading device, comprising:
the verification module is used for acquiring the crushed-screen claim settlement photo and verifying the authenticity of the crushed-screen claim settlement photo;
the screen crushing detection module is used for acquiring a screen crushing area in the screen crushing claim photo through a preset screen crushing detection model when the screen crushing claim photo passes authenticity verification;
and the crushing grade determining module is used for determining the screen crushing grade of the crushed screen claim settlement photo according to a preset crushed screen degree grading model and the screen crushing area.
In a third aspect, the present application further provides a computer device comprising a processor, a memory, and a computer program stored on the memory and executable by the processor, wherein the computer program, when executed by the processor, implements the steps of the screen crushing and grading method as described above.
In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the screen crushing grading method as described above.
The application provides a broken hierarchical method of screen, device, equipment and computer readable storage medium, this application is through carrying out the authenticity check to the broken screen claim photo, and after the broken screen claim photo passes through the authenticity check, again according to the broken screen region in the broken screen claim photo of quick acquisition of broken screen detection model, can be based on broken screen degree hierarchical model at last, the broken level of screen in the broken region of screen of quick accurate definite screen, whole process need not artifical the processing, can accurate quick check the photo and appraise the broken degree of screen, reduce the risk of cheating the insurance.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a schematic flowchart of a screen crushing and grading method provided in an embodiment of the present application;
FIG. 2 is a schematic diagram of a scene for implementing the screen breaking classification method provided in this embodiment;
FIG. 3 is a schematic flow chart of another screen crushing and grading method provided in the embodiments of the present application;
FIG. 4 is a flow diagram illustrating sub-steps of the screen-breaking grading method of FIG. 3;
FIG. 5 is a schematic block diagram of a screen crushing and grading device provided in an embodiment of the present application;
FIG. 6 is a schematic block diagram of another screen crushing grading device provided by the embodiment of the application;
fig. 7 is a block diagram schematically illustrating a structure of a computer device according to an embodiment of the present application.
The implementation, functional features and advantages of the objectives of the present application will be further explained with reference to the accompanying drawings.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some, but not all, embodiments of the present application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The flow diagrams depicted in the figures are merely illustrative and do not necessarily include all of the elements and operations/steps, nor do they necessarily have to be performed in the order depicted. For example, some operations/steps may be decomposed, combined or partially combined, so that the actual execution sequence may be changed according to the actual situation.
The embodiment of the application provides a screen crushing and grading method, device and equipment and a computer readable storage medium. The screen crushing and grading method can be applied to a server, and the server can be a single server or a server cluster consisting of a plurality of servers.
Some embodiments of the present application will be described in detail below with reference to the accompanying drawings. The embodiments described below and the features of the embodiments can be combined with each other without conflict.
Referring to fig. 1, fig. 1 is a schematic flowchart illustrating a screen breaking and grading method according to an embodiment of the present disclosure.
As shown in fig. 1, the screen crushing and grading method includes steps S101 to S103.
And S101, acquiring the screen breaking claim photo, and verifying the authenticity of the screen breaking claim photo.
The method includes the steps that an applicant can initiate a screen-breaking claim request through terminal equipment, namely when a screen-breaking claim instruction is received, the terminal equipment displays a screen-breaking claim page, the applicant can upload a screen-breaking claim photo from the local or shoot the screen-breaking claim photo through the screen-breaking claim page, the terminal equipment receives the screen-breaking claim photo uploaded on the basis of the screen-breaking claim page and generates a screen-breaking claim request carrying the screen-breaking claim photo, the screen-breaking claim request is sent to a server, the server receives the screen-breaking claim request and obtains the screen-breaking claim photo in the screen-breaking claim request, the screen-breaking claim photo can be determined in real time on the basis of the screen-breaking claim photo, the screen-breaking claim photo can be stored firstly, the screen-breaking claim photo is obtained by the server at a follow-up timing, and the screen-breaking claim photo is determined on the basis of the obtained screen-breaking claim photo. It should be noted that the terminal device may be a screen-breaking terminal, or may be other terminal devices used for shooting a screen-breaking terminal, and this application is not limited in this respect.
In an embodiment, when the server receives a screen-crushing claim request, validity verification can be performed on a screen-crushing claim photo in the screen-crushing claim request, when the screen-crushing claim photo passes the validity verification, the screen-crushing grade can be determined in real time or at regular time based on the screen-crushing claim photo, and when the screen-crushing claim photo does not pass the validity verification, reminding information is sent to the terminal device to remind a user to upload or shoot the screen-crushing claim photo again. Through carrying out validity check on the screen fragmentation claim photo, the screen fragmentation claim photo with higher definition can be obtained, and the accuracy of determining the screen fragmentation grade based on the screen fragmentation claim photo can be improved.
It can be understood that, when the terminal device uploads or shoots the screen-crushing claim photo, the terminal device performs validity check on the screen-crushing claim photo, when the screen-crushing claim photo passes the validity check, a screen-crushing claim request carrying the screen-crushing claim photo is generated and sent to the server, and when the screen-crushing claim photo fails the validity check, the user is reminded to upload or shoot the screen-crushing claim photo again.
Wherein, the mode of carrying out validity check to this garrulous screen claim photo specifically is: and the terminal equipment or the server operates a pre-stored definition detection program to determine the image definition of the screen breaking claim photo, and judges whether the image definition is greater than or equal to a preset threshold value or not, if the image definition is greater than or equal to the preset threshold value, the screen breaking claim photo is determined to pass validity check, and if the image definition is less than the preset threshold value, the screen breaking claim photo is determined not to pass validity check. The image definition is used for representing the definition of the image.
It should be noted that the preset threshold may be set based on actual conditions, and the sharpness detection procedure may be implemented based on Brenner gradient function, Tenengrad gradient function, Laplacian gradient function, SMD (grayscale variance) function, energy gradient function, and the like, which is not specifically limited in this application.
The server acquires the screen-breaking claim photo in real time or at regular time and performs authenticity verification on the screen-breaking claim photo, wherein authenticity means that the screen-breaking claim photo uploaded by the user is not an authentic and error-free screen-breaking photo, the risk of cheating the screen-breaking claim photo with higher authenticity is lower, and the risk of cheating the screen-breaking claim photo with lower authenticity is higher.
Specifically, the authenticity check method specifically includes: extracting character check codes from the broken-screen claim photo, and determining whether the character check codes are the same as preset character check codes or not; if the character check code is the same as the preset character check code, determining that the broken-screen claim photo passes authenticity check; and if the character check code is different from the preset character check code, determining that the screen-crushing claim photo does not pass the authenticity check. It should be noted that the character check code may be set based on actual situations, and this is not specifically limited in this application.
In an embodiment, the character check code is an International Mobile Equipment Identity (IMEI) of the terminal device, when a user uploads a broken-screen claim photo through the terminal device, the user displays input reminding information of the IMEI of the broken-screen terminal to remind the user to input the IMEI of the broken-screen terminal, the user shoots a local information page of the broken-screen terminal through the terminal device, the local information page displays IMEI to obtain the broken-screen claim photo containing IMEI, the user selects IMEI in the broken-screen claim photo to obtain the broken-screen claim photo with an IMEI area, when the server processes the broken-screen claim photo, the IMEI area is intercepted from the broken-screen claim photo to obtain a screenshot of the IMEI area, the text screenshot recognition is performed on the IMEI area to obtain a text recognition result, then the text recognition result is obtained from a text recognition result according to a regular expression, and whether the obtained IMEI is the same as a preset IMEI or not is determined, if the obtained IMEI is the same as the preset IMEI, the photo of the claim broken screen is determined to pass authenticity verification, and if the obtained IMEI is different from the preset IMEI, the photo of the claim broken screen is determined not to pass authenticity verification.
In an embodiment, the authenticity check may also be performed by: the method comprises the steps that a user inputs an IMEI (international mobile equipment) of a screen-crushing terminal while uploading a screen-crushing claim photo, so that terminal equipment generates a screen-crushing claim request carrying the IMEI and the screen-crushing claim photo, then a server obtains the IMEI and the screen-crushing claim photo from the screen-crushing claim request when receiving the screen-crushing claim request, and conducts authenticity verification on the screen-crushing claim photo according to the IMEI, namely, a pre-stored IMEI corresponding to the screen-crushing claim photo is obtained, whether the obtained IMEI is the same as a preset IMEI or not is determined, if the obtained IMEI is the same as the preset IMEI is determined, the screen-crushing claim photo is determined to pass authenticity verification, and if the obtained IMEI is different from the preset IMEI, the screen-crushing claim photo is determined not to pass authenticity verification.
And S102, when the screen breaking claim photo passes the authenticity verification, acquiring a screen breaking area in the screen breaking claim photo through a preset screen breaking detection model.
When the broken-screen claim photo passes through authenticity verification, a screen crushing region in the broken-screen claim photo is obtained through a preset broken-screen detection model, namely, the breaking probability of each pixel point in the broken-screen claim photo is determined through the broken-screen detection model, the pixel point of which the breaking probability is larger than or equal to a set probability threshold value is obtained, then the region formed by the obtained pixel points is used as the screen crushing region to be output, and therefore the screen crushing region in the broken-screen claim photo is obtained. It should be noted that, the probability threshold is determined when the broken screen detection model is trained, the breaking probability of the pixel is the probability that the pixel is a broken point, the higher the breaking probability of the pixel is, the higher the probability that the pixel is a broken point is, and the lower the breaking probability of the pixel is, the lower the probability that the pixel is a broken point is.
In one embodiment, a neural network model and a sample data set are obtained, wherein the sample data set is a picture set marked with a screen crushing area; and performing iterative training on the neural network model according to the sample data set until the neural network model converges, and obtaining and storing a preset screen fragmentation detection model. Wherein, the neural network model is implemented by a deep neural network, and the deep neural network comprises but is not limited to a convolutional neural network and a cyclic neural network. Through the trained screen fragmentation detection model, the screen fragmentation region in the screen fragmentation claim photo can be rapidly and accurately acquired, and the accuracy of the screen fragmentation grade is effectively improved.
Optionally, the deep neural network is Mask R-CNN, screen crushing pictures are collected, screen crushing areas are marked, a large amount of marked sample data are obtained, and a sample data set is formed; inputting the sample data set into Mask R-CNN for training until the Mask R-CNN converges, and obtaining a screen fragmentation detection model; when the screen crushing area is predicted, inputting the screen crushing claim photo into the screen crushing detection model, and obtaining the screen crushing area.
In one embodiment, the server determines a screen area in the screen-broken claim photo; and acquiring a screen crushing area from the screen area through a preset screen crushing detection model. The screen area is extracted from the screen breaking claim photo, then the screen breaking area is obtained from the screen area through the screen breaking detection model, the screen breaking area can be rapidly and accurately obtained, and the accuracy of the screen breaking grade is effectively improved.
The determination mode of the screen area specifically comprises the following steps: detecting straight lines and angles of all straight lines in the screen breaking claim photo through Hough transformation to obtain a first candidate straight line set, and detecting straight lines and angles of all straight lines in the screen breaking claim photo through Radon transformation to obtain a second candidate straight line set; and comparing the candidate straight lines in the first candidate straight line set and the second candidate straight line set, taking the candidate straight lines with the angle errors in the preset angle range and the pixel errors in the preset pixel range as target straight lines, so as to obtain the outline of the screen frame in the screen breaking claim photo, and cutting out the screen area from the screen breaking claim photo based on the outline of the screen frame, so as to determine the screen area. It should be noted that the preset angle range and the preset pixel range may be set based on actual situations, and the present application is not limited to this.
And S103, determining the screen crushing grade of the crushed screen claim photo according to a preset crushed screen degree grading model and the screen crushing area.
After the screen crushing area is determined, the screen crushing level of the crushed screen claim photo can be determined according to a preset crushed screen degree grading model and the screen crushing area, namely, the screen crushing area is input into the crushed screen degree grading model, the crushed screen degree grading model outputs the screen crushing level corresponding to the screen crushing area, and the output screen crushing level is used as the screen crushing level of the crushed screen claim photo.
In one embodiment, a neural network model and a sample data set are obtained, wherein the sample data set is a data set comprising a screen fragmentation area and a marked screen fragmentation level; and performing iterative training on the neural network model according to the sample data set until the neural network model converges to obtain a preset screen crushing degree grading model and storing the preset screen crushing degree grading model. Wherein the neural network model is implemented based on a deep neural network. Iterative training is carried out on the neural network model through the labeled sample data, and a screen fragmentation degree grading model with high accuracy can be obtained.
Optionally, training a screen breaking degree classification model by adopting a 50-layer deep Residual Network (ResNet), collecting screen breaking regions, and marking corresponding screen breaking levels based on different service requirements, so as to obtain marked sample data in different service scenes to form a sample data set; and inputting the sample data set into the depth residual error network of 50 layers for model training until the depth residual error network of 50 layers is converged, thereby obtaining the screen crushing degree grading model.
In an embodiment, the determining manner of the screen breaking level may specifically be: according to the screen crushing area, crushing parameter information is determined, and a screen crushing level is determined according to the crushing parameter information, wherein the crushing parameter information comprises at least one of crushing area, number of crushing marks and crushing position.
Specifically, calculating the area of a screen crushing area, and recording as a crushing area; and/or counting the number of the broken marks in the broken area of the screen, and recording the number as the number of the broken marks; and/or determining the position of the screen crushing area in the screen area, and recording the position as a crushing position; and determining the screen crushing grade according to the crushing area, the number of crushing marks and/or the crushing position. The crushing position includes, but is not limited to, an upper screen position, a lower screen position, a middle screen position, and an edge screen position.
The determination mode of the crushing degree index of the screen crushing area specifically comprises the following steps: acquiring a specific numerical value of each crushing parameter from the crushing parameter information, and determining a crushing degree index corresponding to each crushing parameter based on the specific numerical value of each crushing parameter; determining the crushing degree index of the screen crushing area according to the respective crushing degree index corresponding to each crushing parameter, namely acquiring the respective preset weight coefficient corresponding to each crushing parameter, calculating the sum of the respective crushing degree index corresponding to each crushing parameter and the corresponding preset weight coefficient to obtain the respective crushing degree weight index corresponding to each crushing parameter, and then accumulating the respective crushing degree weight index corresponding to each crushing parameter to obtain the crushing degree index of the screen crushing area. It should be noted that the preset weighting factor may be set based on actual situations, and the present application is not limited to this.
The determination mode of the respective corresponding crushing degree index of each crushing parameter is as follows: acquiring a mapping relation table between the pre-stored specific numerical values of the crushing parameters and the crushing degree indexes; and inquiring the mapping relation table to obtain the crushing degree index corresponding to the specific numerical value of the crushing parameter. It should be noted that, the crushing degree indexes corresponding to the specific numerical values of each crushing parameter may be stored in one mapping table, or one mapping table may store the crushing degree indexes corresponding to the specific numerical values of one crushing parameter, so as to obtain a plurality of mapping tables.
Referring to fig. 2, fig. 2 is a schematic view of a scene for implementing the screen breaking and grading method provided in this embodiment, as shown in fig. 2, a user initiates a request for screen breaking claim to a server through a terminal device, and the server receives the request for screen breaking claim and determines a screen breaking grade based on a photo of the screen breaking claim in the request for screen breaking claim.
The screen crushing and grading method provided by the embodiment carries out authenticity verification on the screen crushing claim photo, and after the screen crushing claim photo passes through authenticity verification, the screen crushing region in the screen crushing claim photo is rapidly obtained according to the screen crushing detection model, and finally the screen crushing grade of the screen crushing region can be rapidly and accurately determined based on the screen crushing degree grading model.
Referring to fig. 3, fig. 3 is a schematic flow chart of another screen breaking and grading method according to an embodiment of the present application.
As shown in fig. 3, the screen crushing and grading method includes steps S201 to 206.
Step S201, acquiring the screen breaking claim photo, and performing authenticity verification on the screen breaking claim photo.
The method includes the steps that an applicant can initiate a screen-breaking claim request through terminal equipment, namely when a screen-breaking claim instruction is received, the terminal equipment displays a screen-breaking claim page, the applicant can upload a screen-breaking claim photo from the local or shoot the screen-breaking claim photo through the screen-breaking claim page, the terminal equipment receives the screen-breaking claim photo uploaded on the basis of the screen-breaking claim page and generates a screen-breaking claim request carrying the screen-breaking claim photo, the screen-breaking claim request is sent to a server, the server receives the screen-breaking claim request and obtains the screen-breaking claim photo in the screen-breaking claim request, the screen-breaking claim photo can be determined in real time on the basis of the screen-breaking claim photo, the screen-breaking claim photo can be stored firstly, the screen-breaking claim photo is obtained by the server at a follow-up timing, and the screen-breaking claim photo is determined on the basis of the obtained screen-breaking claim photo.
Step S202, when the screen breaking claim photo passes the authenticity verification, acquiring a screen breaking area in the screen breaking claim photo through a preset screen breaking detection model.
When the broken-screen claim photo passes through authenticity verification, a screen crushing region in the broken-screen claim photo is obtained through a preset broken-screen detection model, namely, the breaking probability of each pixel point in the broken-screen claim photo is determined through the broken-screen detection model, the pixel point of which the breaking probability is larger than or equal to a set probability threshold value is obtained, then the region formed by the obtained pixel points is used as the screen crushing region to be output, and therefore the screen crushing region in the broken-screen claim photo is obtained.
And S203, determining the screen crushing grade of the crushed screen claim photo according to a preset crushed screen degree grading model and the screen crushing area.
After the screen crushing area is determined, the screen crushing level of the crushed screen claim photo can be determined according to a preset crushed screen degree grading model and a preset screen crushing area, namely, the screen crushing area is input into the crushed screen degree grading model, the crushed screen degree grading model outputs the screen crushing level corresponding to the screen crushing area, and the output screen crushing level is used as the screen crushing level of the crushed screen claim photo.
Step S204, determining crushing parameter information according to the screen crushing area, wherein the crushing parameter information comprises at least one of crushing area, number of crushing marks and crushing position.
Specifically, according to the screen crushing area, crushing parameter information is determined, wherein the crushing parameter information comprises at least one of crushing area, number of crushing marks and crushing position. Specifically, calculating the area of a screen crushing area, and recording as a crushing area; and/or counting the number of the broken marks in the broken area of the screen, and recording the number as the number of the broken marks; and/or determining the position of the screen crushing area in the screen area, and recording the position as the crushing position. The crushing position includes, but is not limited to, an upper screen position, a lower screen position, a middle screen position, and an edge screen position.
And S205, verifying the screen crushing grade according to the crushing parameter information, and storing the screen crushing grade when the screen crushing grade passes the verification.
The server may verify the screen crushing level according to the crushing parameter information, and store the screen crushing level when the screen crushing level passes the verification, and may re-determine the screen crushing level when the screen crushing level does not pass the verification. By checking the screen crushing level, the accuracy of the screen crushing level can be further improved.
In one embodiment, referring to fig. 4, step S205 includes: substeps S2051 to substep S2053.
And a substep S2051, determining a first crushing degree index of the screen crushing area according to the crushing parameter information.
Specifically, the server determines a crushing degree index corresponding to at least one crushing parameter according to a numerical value of at least one crushing parameter in the crushing parameter information, namely, obtains a pre-stored mapping relation table between the numerical value of the at least one crushing parameter and the crushing degree index, and queries the mapping relation table to obtain the crushing degree index corresponding to the numerical value of the at least one crushing parameter; according to the crushing degree index corresponding to at least one crushing parameter, determining a first crushing degree index of the screen crushing region, namely according to the crushing degree index corresponding to numerical values of the crushing area, the number of crushing marks and/or the crushing position, determining the first crushing degree index of the screen crushing region.
In one embodiment, a preset weight coefficient corresponding to at least one crushing parameter is obtained; determining a crushing degree weight index corresponding to at least one crushing parameter according to the crushing degree index corresponding to at least one crushing parameter and the preset weight coefficient; and determining a first crushing degree index of the screen crushing area according to the crushing degree weight index corresponding to at least one crushing parameter. It should be noted that, the sum of the preset weight coefficients corresponding to each crushing parameter in the at least one crushing parameter is 1, and the preset weight coefficient is greater than or equal to 0 and less than 1, and the preset weight coefficient corresponding to each crushing parameter may be set based on actual conditions, which is not specifically limited in this application.
The determination process of the first crushing degree index will be explained by taking the crushing parameters as the crushing area, the number of crushing marks and the crushing position as examples. Specifically, preset weight coefficients corresponding to the crushing area, the number of the crushing marks and the crushing position are obtained, the sum of the crushing degree indexes corresponding to the crushing area, the number of the crushing marks and the crushing position and the corresponding preset weight coefficients is calculated to obtain the crushing degree weight indexes corresponding to the crushing area, the number of the crushing marks and the crushing position, and then the crushing degree weight indexes corresponding to the crushing area, the number of the crushing marks and the crushing position are accumulated to obtain a first crushing degree index of the screen crushing area. The sum of the predetermined weight coefficients of the crushing area, the number of crushing marks, and the crushing position is 1.
And a substep S2052 of obtaining a second crushing degree index corresponding to the screen crushing grade of the screen crushing claim photo according to a mapping relation table between pre-stored crushing degree indexes and screen crushing grades.
Specifically, the server acquires a second crushing degree index corresponding to the screen crushing degree of the screen crushing claim photo according to a mapping relation table between pre-stored crushing degree indexes and screen crushing degrees, namely, the mapping relation table is inquired, the crushing degree index corresponding to the screen crushing degree is acquired, and the acquired crushing degree index is used as the second crushing degree index.
And a substep S2053 of verifying the screen crushing grade according to the first crushing degree index and the second crushing degree index.
Specifically, the screen crushing level is verified according to the first crushing degree index and the second crushing degree index, namely, the absolute value of the difference value between the first crushing degree index and the second crushing degree index is calculated, whether the absolute value of the difference value is smaller than or equal to a set numerical value is determined, if the absolute value of the difference value is smaller than or equal to the set numerical value, the screen crushing level is determined to pass the verification, and if the absolute value of the difference value is larger than the set numerical value, the screen crushing level is determined not to pass the verification.
According to the screen crushing grading method provided by the embodiment, the accuracy of the screen crushing grade can be further improved by verifying the screen crushing grade.
Referring to fig. 5, fig. 5 is a schematic block diagram of a screen breaking and grading device according to an embodiment of the present disclosure.
As shown in fig. 5, the screen crushing and grading device 300 includes: a verification module 301, a screen crash detection module 302, and a crash level determination module 303.
The verification module 301 is configured to obtain a screen-breaking claim photo, and perform authenticity verification on the screen-breaking claim photo.
The screen crushing detection module 302 is configured to, when the screen crushing claim photo passes the authenticity verification, obtain a screen crushing area in the screen crushing claim photo through a preset screen crushing detection model.
And the crushing grade determining module 303 is configured to determine a screen crushing grade of the crushed screen claim settlement photo according to a preset crushed screen degree grading model and the screen crushing area.
Further, the verification module 301 is further configured to extract a character verification code from the photo of the claims broken by screen, and determine whether the character verification code is the same as a preset character verification code; if the character check code is the same as a preset character check code, determining that the broken-screen claim photo passes authenticity check; and if the character check code is different from the preset character check code, determining that the screen-crushing claim photo does not pass authenticity check.
Further, the screen crushing and grading device further comprises:
the acquisition module is used for acquiring a neural network model and a sample data set, wherein the sample data set is a picture set marked with a screen crushing area;
and the training module is used for carrying out iterative training on the neural network model according to the sample data set until the neural network model converges, and obtaining and storing the preset broken screen detection model.
Referring to fig. 6, fig. 6 is a schematic block diagram of another screen crushing and grading device provided in the embodiments of the present application.
As shown in fig. 6, the screen crushing and grading device 400 includes: a first check module 401, a screen crash detection module 402, a crash level determination module 403, a parameter information determination module 404, and a second check module 405.
The first verification module 401 is configured to obtain a screen-crushing claim photo, and perform authenticity verification on the screen-crushing claim photo.
And the screen crushing detection module 402 is used for acquiring the screen crushing area in the screen crushing claim photo through a preset screen crushing detection model when the screen crushing claim photo passes the authenticity check.
And a crushing level determining module 403, configured to determine a screen crushing level of the crushed screen claim settlement photo according to a preset crushed screen degree grading model and the screen crushing area.
A parameter information determining module 404, configured to determine crushing parameter information according to the screen crushing region, where the crushing parameter information includes at least one of a crushing area, a number of crushing marks, and a crushing position.
And the second checking module 405 is configured to check the screen crushing level according to the crushing parameter information, and store the screen crushing level when the screen crushing level passes the check.
Further, the second checking module 405 is further configured to determine a first crushing degree index of the screen crushing area according to the crushing parameter information; acquiring a second crushing degree index corresponding to the screen crushing grade of the screen crushing claim photo according to a mapping relation table between pre-stored crushing degree indexes and screen crushing grades; and verifying the screen crushing grade according to the first crushing degree index and the second crushing degree index.
Further, the second checking module 405 is further configured to determine, according to a numerical value of at least one crushing parameter in the crushing parameter information, a crushing degree index corresponding to the at least one crushing parameter; and determining a first crushing degree index of the screen crushing area according to the crushing degree index corresponding to at least one crushing parameter.
Further, the second checking module 405 is further configured to obtain a preset weight coefficient corresponding to at least one crushing parameter; determining a crushing degree weight index corresponding to at least one crushing parameter according to the crushing degree index corresponding to at least one crushing parameter and the preset weight coefficient; and determining a first crushing degree index of the screen crushing area according to the crushing degree weight index corresponding to at least one crushing parameter.
It should be noted that, as will be clear to those skilled in the art, for convenience and brevity of description, the specific working processes of the apparatus and each module and unit described above may refer to the corresponding processes in the foregoing screen breaking and grading method embodiment, and are not described herein again.
The apparatus provided by the above embodiments may be implemented in the form of a computer program that can be run on a computer device as shown in fig. 7.
Referring to fig. 7, fig. 7 is a schematic block diagram illustrating a structure of a computer device according to an embodiment of the present disclosure. The computer device may be a server.
As shown in fig. 7, the computer device includes a processor, a memory, and a network interface connected by a system bus, wherein the memory may include a nonvolatile storage medium and an internal memory.
The non-volatile storage medium may store an operating system and a computer program. The computer program includes program instructions that, when executed, cause a processor to perform any one of the screen reduction ranking methods.
The processor is used for providing calculation and control capability and supporting the operation of the whole computer equipment.
The internal memory provides an environment for the execution of a computer program on a non-volatile storage medium, which when executed by the processor, causes the processor to perform any of the screen reduction ranking methods.
The network interface is used for network communication, such as sending assigned tasks and the like. Those skilled in the art will appreciate that the architecture shown in fig. 7 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
It should be understood that the Processor may be a Central Processing Unit (CPU), and the Processor may be other general purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Wherein a general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
Wherein, in one embodiment, the processor is configured to execute a computer program stored in the memory to implement the steps of:
acquiring a screen breaking claim photo, and performing authenticity verification on the screen breaking claim photo;
when the photo of the claims on the screen breaking passes the authenticity check, acquiring a screen breaking area in the photo of the claims on the screen breaking through a preset screen breaking detection model;
and determining the screen crushing grade of the screen crushing claim photo according to a preset screen crushing degree grading model and the screen crushing area.
In one embodiment, before implementing obtaining the screenful claim photo and performing the authenticity check on the screenful claim photo, the processor is further configured to implement:
acquiring a neural network model and a sample data set, wherein the sample data set is a picture set marked with a screen crushing area;
and performing iterative training on the neural network model according to the sample data set until the neural network model converges, and obtaining and storing the preset screen fragmentation detection model.
In one embodiment, the processor, when performing the authenticity check on the screen-broken claim photo, is configured to perform:
extracting character check codes from the broken-screen claim photo, and determining whether the character check codes are the same as preset character check codes;
if the character check code is the same as a preset character check code, determining that the broken-screen claim photo passes authenticity check;
and if the character check code is different from the preset character check code, determining that the screen-crushing claim photo does not pass authenticity check.
Wherein in another embodiment the processor is adapted to run a computer program stored in the memory to implement the steps of:
acquiring a screen breaking claim photo, and performing authenticity verification on the screen breaking claim photo;
when the photo of the claims on the screen breaking passes the authenticity check, acquiring a screen breaking area in the photo of the claims on the screen breaking through a preset screen breaking detection model;
determining the screen crushing grade of the screen crushing claim photo according to a preset screen crushing degree grading model and the screen crushing area;
determining crushing parameter information according to the screen crushing area, wherein the crushing parameter information comprises at least one of crushing area, number of crushing marks and crushing position;
and verifying the screen crushing grade according to the crushing parameter information, and storing the screen crushing grade when the screen crushing grade passes the verification.
In one embodiment, when the processor is implemented to check the screen crushing level according to the crushing parameter information, the processor is configured to implement:
determining a first crushing degree index of the screen crushing area according to the crushing parameter information;
acquiring a second crushing degree index corresponding to the screen crushing grade of the screen crushing claim photo according to a mapping relation table between pre-stored crushing degree indexes and screen crushing grades;
and verifying the screen crushing grade according to the first crushing degree index and the second crushing degree index.
In one embodiment, the processor, in effecting determining a first breakage degree index of the screen breakage region from the breakage parameter information, is configured to effect:
determining a crushing degree index corresponding to at least one crushing parameter according to the numerical value of the at least one crushing parameter in the crushing parameter information;
and determining a first crushing degree index of the screen crushing area according to the crushing degree index corresponding to at least one crushing parameter.
In one embodiment, the processor, when determining the first crushing degree index of the screen crushing area according to the crushing degree index corresponding to at least one crushing parameter, is configured to:
acquiring a preset weight coefficient corresponding to at least one crushing parameter;
determining a crushing degree weight index corresponding to at least one crushing parameter according to the crushing degree index corresponding to at least one crushing parameter and the preset weight coefficient;
and determining a first crushing degree index of the screen crushing area according to the crushing degree weight index corresponding to at least one crushing parameter.
Embodiments of the present application also provide a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, where the computer program includes program instructions, and when the program instructions are executed, the method implemented by the program instructions may refer to various embodiments of the screen crushing and grading method of the present application.
The computer-readable storage medium may be an internal storage unit of the computer device described in the foregoing embodiment, for example, a hard disk or a memory of the computer device. The computer readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like provided on the computer device.
It is to be understood that the terminology used in the description of the present application herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in the specification of the present application and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
It should also be understood that the term "and/or" as used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items. It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The above-mentioned serial numbers of the embodiments of the present application are merely for description and do not represent the merits of the embodiments. While the invention has been described with reference to specific embodiments, the scope of the invention is not limited thereto, and those skilled in the art can easily conceive various equivalent modifications or substitutions within the technical scope of the invention. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (10)
1. A screen crushing and grading method, comprising:
acquiring a screen breaking claim photo, and performing authenticity verification on the screen breaking claim photo;
when the photo of the claims on the screen breaking passes the authenticity check, acquiring a screen breaking area in the photo of the claims on the screen breaking through a preset screen breaking detection model;
and determining the screen crushing grade of the screen crushing claim photo according to a preset screen crushing degree grading model and the screen crushing area.
2. The screen crushing grading method according to claim 1, wherein before the acquiring the photo of the crushed-screen claim and performing the authenticity check on the photo of the crushed-screen claim, further comprising:
acquiring a neural network model and a sample data set, wherein the sample data set is a picture set marked with a screen crushing area;
and performing iterative training on the neural network model according to the sample data set until the neural network model converges, and obtaining and storing the preset screen fragmentation detection model.
3. The screen crushing grading method according to claim 1 or 2, wherein after determining the screen crushing grade of the crushed-screen claim photo according to a preset crushed-screen degree grading model and the screen crushing area, the method further comprises:
determining crushing parameter information according to the screen crushing area, wherein the crushing parameter information comprises at least one of crushing area, number of crushing marks and crushing position;
and verifying the screen crushing grade according to the crushing parameter information, and storing the screen crushing grade when the screen crushing grade passes the verification.
4. The screen crushing grading method according to claim 3, wherein the verifying the screen crushing grade according to the crushing parameter information comprises:
determining a first crushing degree index of the screen crushing area according to the crushing parameter information;
acquiring a second crushing degree index corresponding to the screen crushing grade of the screen crushing claim photo according to a mapping relation table between pre-stored crushing degree indexes and screen crushing grades;
and verifying the screen crushing grade according to the first crushing degree index and the second crushing degree index.
5. The screen crushing grading method according to claim 4, wherein the determining a first crushing degree index of the screen crushing area according to the crushing parameter information comprises:
determining a crushing degree index corresponding to at least one crushing parameter according to the numerical value of the at least one crushing parameter in the crushing parameter information;
and determining a first crushing degree index of the screen crushing area according to the crushing degree index corresponding to at least one crushing parameter.
6. The screen crushing grading method according to claim 5, wherein the determining a first crushing degree index of the screen crushing area according to the crushing degree index corresponding to at least one crushing parameter comprises:
acquiring a preset weight coefficient corresponding to at least one crushing parameter;
determining a crushing degree weight index corresponding to at least one crushing parameter according to the crushing degree index corresponding to at least one crushing parameter and the preset weight coefficient;
and determining a first crushing degree index of the screen crushing area according to the crushing degree weight index corresponding to at least one crushing parameter.
7. The screen-breaking grading method according to claim 1 or 2, characterized in that said checking authenticity of said screen-breaking claim photo comprises:
extracting character check codes from the broken-screen claim photo, and determining whether the character check codes are the same as preset character check codes;
if the character check code is the same as a preset character check code, determining that the broken-screen claim photo passes authenticity check;
and if the character check code is different from the preset character check code, determining that the screen-crushing claim photo does not pass authenticity check.
8. A screen crushing grading device, characterized in that the screen crushing grading device comprises:
the verification module is used for acquiring the crushed-screen claim settlement photo and verifying the authenticity of the crushed-screen claim settlement photo;
the screen crushing detection module is used for acquiring a screen crushing area in the screen crushing claim photo through a preset screen crushing detection model when the screen crushing claim photo passes authenticity verification;
and the crushing grade determining module is used for determining the screen crushing grade of the crushed screen claim settlement photo according to a preset crushed screen degree grading model and the screen crushing area.
9. A computer device, characterized in that the computer device comprises a processor, a memory, and a computer program stored on the memory and executable by the processor, wherein the computer program, when executed by the processor, implements the steps of the screen crushing grading method according to any of claims 1 to 7.
10. A computer-readable storage medium, characterized in that a computer program is stored on the computer-readable storage medium, wherein the computer program, when being executed by a processor, carries out the steps of the screen crushing grading method according to any of the claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911244445.3A CN111178147B (en) | 2019-12-06 | 2019-12-06 | Screen crushing and grading method, device, equipment and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911244445.3A CN111178147B (en) | 2019-12-06 | 2019-12-06 | Screen crushing and grading method, device, equipment and computer readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111178147A true CN111178147A (en) | 2020-05-19 |
| CN111178147B CN111178147B (en) | 2023-11-28 |
Family
ID=70652020
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911244445.3A Active CN111178147B (en) | 2019-12-06 | 2019-12-06 | Screen crushing and grading method, device, equipment and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111178147B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111882447A (en) * | 2020-07-28 | 2020-11-03 | 深圳市鑫迅维科技有限公司 | Screen-breaking protection service anti-cheating protection method |
| CN112268912A (en) * | 2020-10-09 | 2021-01-26 | 支付宝(杭州)信息技术有限公司 | Screen damage verification method and device based on mirror shooting |
| CN113537218A (en) * | 2021-07-27 | 2021-10-22 | 京东数科海益信息科技有限公司 | Image recognition method and device |
| CN114663418A (en) * | 2022-04-06 | 2022-06-24 | 京东安联财产保险有限公司 | Image processing method and device, storage medium and electronic equipment |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105894036A (en) * | 2016-04-19 | 2016-08-24 | 武汉大学 | Image feature template matching method being applied to detection of mobile phone screen defects |
| US20170372465A1 (en) * | 2016-06-28 | 2017-12-28 | ecoATM, Inc. | Methods and systems for detecting cracks in illuminated electronic device screens |
| CN108171190A (en) * | 2018-01-05 | 2018-06-15 | 深圳市金立通信设备有限公司 | A kind of optical finger print recognition methods, terminal and computer readable storage medium |
| JP6462080B1 (en) * | 2017-09-20 | 2019-01-30 | アシュリオンジャパン・ホールディングス合同会社 | Inspection device, inspection system, inspection method, and inspection program |
| CN110084957A (en) * | 2019-04-28 | 2019-08-02 | 深圳回收宝科技有限公司 | A kind of method, apparatus, portable terminal and the storage medium of terminal detection |
-
2019
- 2019-12-06 CN CN201911244445.3A patent/CN111178147B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105894036A (en) * | 2016-04-19 | 2016-08-24 | 武汉大学 | Image feature template matching method being applied to detection of mobile phone screen defects |
| US20170372465A1 (en) * | 2016-06-28 | 2017-12-28 | ecoATM, Inc. | Methods and systems for detecting cracks in illuminated electronic device screens |
| JP6462080B1 (en) * | 2017-09-20 | 2019-01-30 | アシュリオンジャパン・ホールディングス合同会社 | Inspection device, inspection system, inspection method, and inspection program |
| CN108171190A (en) * | 2018-01-05 | 2018-06-15 | 深圳市金立通信设备有限公司 | A kind of optical finger print recognition methods, terminal and computer readable storage medium |
| CN110084957A (en) * | 2019-04-28 | 2019-08-02 | 深圳回收宝科技有限公司 | A kind of method, apparatus, portable terminal and the storage medium of terminal detection |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111882447A (en) * | 2020-07-28 | 2020-11-03 | 深圳市鑫迅维科技有限公司 | Screen-breaking protection service anti-cheating protection method |
| CN112268912A (en) * | 2020-10-09 | 2021-01-26 | 支付宝(杭州)信息技术有限公司 | Screen damage verification method and device based on mirror shooting |
| CN113537218A (en) * | 2021-07-27 | 2021-10-22 | 京东数科海益信息科技有限公司 | Image recognition method and device |
| CN113537218B (en) * | 2021-07-27 | 2024-02-06 | 京东科技信息技术有限公司 | Image recognition method and device |
| CN114663418A (en) * | 2022-04-06 | 2022-06-24 | 京东安联财产保险有限公司 | Image processing method and device, storage medium and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111178147B (en) | 2023-11-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111178147B (en) | Screen crushing and grading method, device, equipment and computer readable storage medium | |
| CN106446816B (en) | Face recognition method and device | |
| WO2018166116A1 (en) | Car damage recognition method, electronic apparatus and computer-readable storage medium | |
| CN110555372A (en) | Data entry method, device, equipment and storage medium | |
| CN108171203B (en) | Method and device for identifying vehicle | |
| CN109816200B (en) | Task pushing method, device, computer equipment and storage medium | |
| CN111767228B (en) | Interface testing method, device, equipment and medium based on artificial intelligence | |
| CN112183296B (en) | Simulated bill image generation and bill image recognition method and device | |
| CN112966583A (en) | Image processing method, image processing device, computer equipment and storage medium | |
| CN111275102A (en) | Multi-certificate type synchronous detection method and device, computer equipment and storage medium | |
| CN111046879A (en) | Certificate image classification method and device, computer equipment and readable storage medium | |
| CN111666932B (en) | Document auditing method, device, computer equipment and storage medium | |
| CN112036488A (en) | Event identification method, device and equipment based on image identification and storage medium | |
| CN114386013A (en) | Automatic student status authentication method and device, computer equipment and storage medium | |
| JP6146209B2 (en) | Information processing apparatus, character recognition method, and program | |
| CN110956149A (en) | Pet identity verification method, device and equipment and computer readable storage medium | |
| CN111104542B (en) | Part identification management method and device | |
| CN113723467A (en) | Sample collection method, device and equipment for defect detection | |
| CN111027345A (en) | Font identification method and apparatus | |
| CN111178347B (en) | Ambiguity detection method, ambiguity detection device, ambiguity detection equipment and ambiguity detection storage medium for certificate image | |
| CN113076961A (en) | Image feature library updating method, image detection method and device | |
| CN112668640A (en) | Text image quality evaluation method, device, equipment and medium | |
| CN111783561A (en) | Picture examination result correction method, electronic equipment and related products | |
| CN113807256A (en) | Bill data processing method and device, electronic equipment and storage medium | |
| CN111681116A (en) | Claims data verification method, device, equipment and storage medium |
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 |