CN108470028B - Picture auditing method and device - Google Patents
Picture auditing method and device Download PDFInfo
- Publication number
- CN108470028B CN108470028B CN201710100578.8A CN201710100578A CN108470028B CN 108470028 B CN108470028 B CN 108470028B CN 201710100578 A CN201710100578 A CN 201710100578A CN 108470028 B CN108470028 B CN 108470028B
- Authority
- CN
- China
- Prior art keywords
- picture
- audited
- auditing
- result
- unique identifier
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
- G06F16/5838—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using colour
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/2163—Partitioning the feature space
-
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/30—Network architectures or network communication protocols for network security for supporting lawful interception, monitoring or retaining of communications or communication related information
- H04L63/302—Network architectures or network communication protocols for network security for supporting lawful interception, monitoring or retaining of communications or communication related information gathering intelligence information for situation awareness or reconnaissance
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Library & Information Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Databases & Information Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computer Hardware Design (AREA)
- Life Sciences & Earth Sciences (AREA)
- Quality & Reliability (AREA)
- Computer Security & Cryptography (AREA)
- Computing Systems (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Technology Law (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Image Analysis (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the invention provides a picture auditing method and device. The method comprises the following steps: dividing a picture to be audited into a plurality of parts; generating a unique identifier of each part obtained by dividing the picture to be audited; according to the plurality of unique identifiers corresponding to the picture to be audited, the audit result of the audited picture, which is the same as the unique identifier exceeding the set proportion with the picture to be audited, is searched; and extracting the audit result of the searched audited picture as the audit result of the picture to be audited. According to the method, the picture to be audited and the audited picture corresponding to the audited result are the same or partially the same, so that the audited result can be used as the audited result of the picture to be audited, the previous audited result can be automatically adopted for the audited of the same or partially the same picture, the workload of re-auditing is reduced, and the picture auditing efficiency is improved.
Description
Technical Field
The invention relates to the technical field of picture auditing, in particular to a picture auditing method and device.
Background
With the development of the internet, a large number of pictures are uploaded every day through a website or a client. In order to prevent the propagation of the riot and pornographic pictures, the background service team needs to perform machine or manual auditing on the pictures, and the auditing process consumes a great amount of manpower and material resources.
Because a lot of repeated pictures are uploaded by a user or a part of uploaded pictures are obtained by altering the original pictures and changing the brightness, the pictures to be audited have many identical or similar pictures. And the pictures are audited, and if the pictures are audited for multiple times, unnecessary audit resources are wasted, and the picture audit efficiency is reduced.
Disclosure of Invention
In view of the above, the present invention is proposed to provide a picture auditing method and apparatus that overcome the above problems or at least partially solve the above problems.
According to an aspect of the present invention, there is provided a picture auditing method, including:
dividing a picture to be audited into a plurality of parts;
generating a unique identifier of each part obtained by dividing the picture to be audited;
according to the plurality of unique identifiers corresponding to the picture to be audited, the audit result of the audited picture, which is the same as the unique identifier exceeding the set proportion with the picture to be audited, is searched;
and extracting the audit result of the searched audited picture as the audit result of the picture to be audited.
In this embodiment of the present invention, preferably, the dividing the picture to be audited into a plurality of parts includes:
the picture to be audited is divided into a set number of parts of the same size.
In this embodiment of the present invention, preferably, the dividing the picture to be audited into a plurality of parts includes:
rotating the original picture to obtain a rotated picture;
and taking the original picture and the rotated picture as pictures to be audited, and respectively dividing the pictures into a plurality of parts.
In the embodiment of the present invention, preferably, the rotated picture is at least one of a rotated picture obtained by clockwise rotating the original picture by 90 degrees, a rotated picture obtained by clockwise rotating the original picture by 180 degrees, and a rotated picture obtained by clockwise rotating the original picture by 270 degrees.
In this embodiment of the present invention, preferably, the generating of the unique identifier of each part obtained by dividing the picture to be audited includes:
acquiring a color value table of the pixel points corresponding to each part according to the positions of the pixel points in each part;
calculating to obtain the difference value between each color value in the color value table and the average value of the color values in the color value table, and forming a color difference table of the pixel points corresponding to each part;
and generating a unique identifier of the color difference table as a unique identifier of each part.
In the embodiment of the present invention, preferably, the unique identifier includes: MD5 value of picture file data, MD5 value of unique feature of picture.
In this embodiment of the present invention, preferably, after the examining result of the examined picture, which has the same unique identifier that exceeds a set ratio as the unique identifier of the picture to be examined, is found according to the plurality of unique identifiers corresponding to the picture to be examined, the method further includes:
auditing the to-be-audited picture which does not have the audit result;
and storing the auditing result obtained by auditing and the unique identifiers of the parts of the picture to be audited.
In this embodiment of the present invention, preferably, after the extracting the audit result of the searched audited picture as the audit result of the picture to be audited, the method further includes:
if the auditing result is that the auditing is passed, the client side is allowed to upload the picture to be audited to a server or store the picture to be audited;
and if the audit result is that the audit is not passed, rejecting the client to upload the picture to be audited to a server or deleting the picture to be audited.
According to another aspect of the present invention, there is provided a picture auditing apparatus, including:
the segmentation module is used for segmenting the picture to be audited into a plurality of parts;
the identification generation module is used for generating a unique identification of each part obtained by dividing the picture to be audited;
the result searching module is used for searching the auditing result of the audited picture which has the same unique identifier exceeding the set proportion with the picture to be audited according to the plurality of unique identifiers corresponding to the picture to be audited;
and the result extraction module is used for extracting the audit result of the searched audited picture as the audit result of the picture to be audited.
In the embodiment of the present invention, preferably, the dividing module is specifically configured to divide the picture to be checked into a plurality of portions with the same size and a set number.
In the embodiment of the present invention, preferably, the dividing module includes:
the rotation sub-module is used for rotating the original picture to obtain a rotated picture;
and the division submodule is used for taking the original picture and the rotated picture as pictures to be checked and dividing the pictures into a plurality of parts respectively.
In the embodiment of the present invention, preferably, the rotated picture is at least one of a rotated picture obtained by clockwise rotating the original picture by 90 degrees, a rotated picture obtained by clockwise rotating the original picture by 180 degrees, and a rotated picture obtained by clockwise rotating the original picture by 270 degrees.
In the embodiment of the present invention, preferably, the identifier generating module includes:
the color value table obtaining submodule is used for obtaining the color value table of the pixel point corresponding to each part according to the position of the pixel point in each part;
the color difference table composition submodule is used for calculating and obtaining the difference between each color value in the color value table and the average value of the color values in the color value table, and forming a color difference table of the pixel point corresponding to each part;
and the identifier generation submodule is used for generating a unique identifier of the color difference table as the unique identifier of each part.
In the embodiment of the present invention, preferably, the unique identifier includes: MD5 value of picture file data, MD5 value of unique feature of picture.
In the embodiment of the present invention, preferably, the apparatus further includes:
the picture auditing module is used for auditing the picture to be audited, of which the auditing result is not found, after the auditing result of the audited picture, which is the same as the unique identifier exceeding the set proportion, of the picture to be audited is found according to the plurality of unique identifiers corresponding to the picture to be audited;
and the result storage module is used for storing the auditing result obtained by auditing and the unique identifiers of the parts of the picture to be audited.
In the embodiment of the present invention, preferably, the apparatus further includes:
the auditing passing module is used for agreeing the client to upload the picture to be audited to the server or store the picture to be audited if the auditing result is that the auditing is passed after the auditing result of the searched audited picture is extracted and used as the auditing result of the picture to be audited;
and the auditing failure module is used for refusing the client to upload the picture to be audited to the server or delete the picture to be audited if the auditing result is that the auditing is not passed.
In summary, according to the embodiments of the present invention, by comparing the unique identifiers of the plurality of portions corresponding to the picture to be audited with the unique identifiers of the plurality of portions corresponding to the picture already audited, the audit result of the picture already audited, which has the same unique identifier exceeding the set ratio as the picture to be audited, is found.
Drawings
FIG. 1 is a flow chart illustrating steps of one embodiment of a picture review method of the present invention;
FIG. 2 is a flow chart illustrating steps of another embodiment of a picture review method of the present invention;
fig. 3 shows a block diagram of an embodiment of the picture auditing apparatus according to the present invention.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.
Referring to fig. 1, a flowchart illustrating steps of an embodiment of a picture auditing method according to the present invention is shown, which may specifically include the following steps:
In the embodiment of the invention, the picture to be audited is cut into a plurality of parts, so that the plurality of parts obtained by cutting can be spliced into a plurality of pictures to be audited, and mutually and directly have no overlapped part. Specifically, the picture may be divided into M × N parts of M rows and N columns, for example, 16 parts of 4 rows and 4 columns, in an average division manner. Or the picture may be divided into portions in a non-equally divided manner. The embodiment of the present invention is not limited to the specific division method, but a uniform division method should be selected for division, or a uniform division method should be set for pictures of various sizes according to different picture sizes. After a picture is divided into a plurality of parts, image data of each part can be obtained, or each part can be saved as a picture file.
In practical applications, a website or a client receives a large number of pictures, such as an avatar picture uploaded by a user. Because many uploaded pictures are repeatedly uploaded, or many uploaded pictures have only partial differences compared with pictures uploaded once, for example, correction or special effect processing is performed on partial positions of the pictures. The picture to be audited and the audited picture can be considered to be the same or similar pictures only by dividing the picture to be audited into a plurality of parts, wherein more than half of the parts are the same as the audited picture.
And 102, generating a unique identifier of each part obtained by dividing the picture to be audited.
In the embodiment of the present invention, the unique identifier refers to identification information for uniquely identifying image data of a picture file or a picture, for example, an MD5 value calculated from the image data of the picture file or the picture (MD5, full Message digest MD5, fifth edition of chinese name Message digest algorithm). Generally, the unique identifications of different pictures will not be the same.
Specifically, after the picture to be checked is divided into a plurality of portions, image data of each portion or a picture file corresponding to each portion may be obtained. Specifically, the corresponding unique identifier may be generated according to the image data of each portion or the picture file corresponding to each portion.
And 103, searching for an audit result of the audited picture, which has the same unique identifier exceeding a set proportion with the picture to be audited, according to the plurality of unique identifiers corresponding to the picture to be audited.
In the embodiment of the present invention, the audit result refers to information for describing whether the picture meets the requirement, for example, information whether the picture meets the specification. And storing a plurality of unique identifiers corresponding to the audited pictures and the audit results of the audited pictures which are generated by the same method. Wherein the auditing result can be obtained by a manual auditing method or an existing machine auditing method.
If the unique identifiers exceeding the set proportion are the same after comparing the unique identifiers corresponding to the picture to be audited with the unique identifiers corresponding to the audited picture, the picture to be audited and the audited picture can be considered to be the same or partially the same. The specific adopted set proportion can be set according to actual needs, and the invention is not limited to this.
Specifically, a plurality of unique identifiers and corresponding audit results of the audited picture generated by the audited picture in the same method can be correspondingly stored in one database for searching.
And 104, extracting the searched auditing result of the audited picture to be used as the auditing result of the picture to be audited.
In the embodiment of the invention, the checked picture which has the same unique identifier with the picture to be checked and exceeds the set proportion is found to have the same audit result, and the picture to be checked and the checked picture are considered to be the same or partially the same because the picture to be checked and the checked picture have the same unique identifier with the picture to be checked and exceeding the set proportion. And extracting the audit result of the searched audited picture as the audit result of the picture to be audited.
In summary, according to the embodiments of the present invention, by comparing the unique identifiers of the plurality of portions corresponding to the picture to be audited with the unique identifiers of the plurality of portions corresponding to the picture already audited, the audit result of the picture already audited, which has the same unique identifier exceeding the set ratio as the picture to be audited, is found.
In the embodiment of the present invention, preferably, one implementation manner of dividing the picture to be checked into a plurality of portions is to divide the picture to be checked into a set number of portions with the same size.
Specifically, the picture may be divided into a plurality of portions having the same size, for example, 16 portions having the same size, in an evenly divided manner. In practical application, the picture may be divided into any number of parts with the same size according to any proportion, and the present invention is not limited to this.
In the embodiment of the present invention, preferably, one implementation manner of dividing the picture to be audited into a plurality of parts is to rotate an original picture to obtain a rotated picture; and taking the original picture and the rotated picture as pictures to be audited, and respectively dividing the pictures into a plurality of parts.
Specifically, the original picture refers to a picture submitted for auditing or a corresponding original picture that is not modified. And rotating the original picture to obtain a rotated picture, and rotating by different angles to obtain different rotated pictures. The specific rotation angle and the number of the required rotation pictures are not limited in the invention, and can be set according to actual needs. And taking the rotary picture and the original picture as pictures to be audited, and respectively segmenting to obtain a plurality of parts corresponding to the rotary picture and a plurality of parts corresponding to the original picture, namely obtaining a plurality of pictures to be audited from the original picture.
For the picture audit, the rotated picture and the picture before the rotation can adopt the same audit result. After the picture is rotated, the picture is compared with the audited picture, if the audit result of the audited picture with the unique identification which exceeds the set proportion and is the same as the unique identification of the rotated picture is found, the found audit result can be used as the audit result of the rotated picture, namely the audit result of the picture before rotation, the workload of secondary audit is reduced, and the picture audit efficiency is improved.
In the embodiment of the present invention, preferably, the rotated picture is at least one of a rotated picture obtained by clockwise rotating the original picture by 90 degrees, a rotated picture obtained by clockwise rotating the original picture by 180 degrees, and a rotated picture obtained by clockwise rotating the original picture by 270 degrees.
Specifically, the rotated picture may be at least one of a rotated picture obtained by rotating the original picture by 90 degrees clockwise, a rotated picture obtained by rotating the original picture by 180 degrees clockwise, and a rotated picture obtained by rotating the original picture by 270 degrees clockwise
In the embodiment of the present invention, preferably, one implementation manner of generating the unique identifier of each part obtained by dividing the picture to be audited is to obtain a color value table of a pixel point corresponding to each part according to a position of a pixel point in each part; calculating to obtain the difference value between each color value in the color value table and the average value of the color values in the color value table, and forming a color difference table of the pixel points corresponding to each part; and generating a unique identifier of the color difference table as a unique identifier of each part.
Specifically, the color value refers to a numerical value representing a color in a computer, such as a color value of RGB standard (red, green, blue standard, a color standard in the industry). And forming a table consisting of color values of the pixels according to the positions of the pixels in each part obtained by segmentation. The average value of the color values in the color value table is obtained through calculation, then the average value is subtracted from each color value in the color value table, and the obtained difference value forms a corresponding difference value table, namely the color difference table of the pixel point corresponding to each part. And generating a unique identifier of the color difference table through a specific Algorithm, for example, calculating a generated MD5 value according to the color difference table (MD5, full name Message Digest Algorithm MD5, fifth edition of Chinese name Message Digest Algorithm).
Because the color difference table corresponding to the new picture and the color difference table corresponding to the original picture obtained after the brightness of one picture is adjusted are the same, if the audit result of the audited picture with the unique identifier which is more than the set proportion and is the same as that of the picture to be audited is found, the found audit result can be used as the audit result of the picture to be audited, the workload of rechecking is reduced, and the efficiency of picture audit is improved.
In the embodiment of the present invention, preferably, the unique identifier includes: MD5 value of picture file data, MD5 value of unique feature of picture.
The MD5 value of the picture file data is an MD5 value obtained by an MD5(MD5, full name MessageDigest Algorithm MD5, fifth version of chinese name message digest Algorithm) Algorithm with the picture file data as an input. The MD5 value of the unique feature of a picture is an MD5 value obtained by an MD5(MD5, full name Message digest MD5, fifth edition of chinese name Message digest algorithm) algorithm with the unique feature capable of identifying a picture as an input. The unique feature of the picture may include a matrix of pixel values corresponding to each pixel point in the picture.
Referring to fig. 2, a flowchart illustrating steps of another embodiment of the image auditing method of the present invention is shown, which may specifically include the following steps:
And 203, searching for an audit result of the audited picture, which has the same unique identifier exceeding a set proportion with the picture to be audited, according to the plurality of unique identifiers corresponding to the picture to be audited.
And step 204, extracting the searched auditing result of the audited picture as the auditing result of the picture to be audited.
And step 205, auditing the picture to be audited, wherein the audit result is not found.
In the embodiment of the invention, if an audit result of an audited picture with the unique identifier which exceeds the set proportion and is the same as that of the picture to be audited is not found, the picture to be audited is audited, and the specific audit mode comprises a manual audit or other machine automatic audit method, which is not limited by the invention.
And step 206, storing the audit result obtained by the audit and the unique identifiers of the parts of the picture to be audited.
In the embodiment of the invention, the auditing result obtained by auditing and the unique identifiers of a plurality of parts of the picture to be audited are correspondingly stored together. Specifically, the audit result and the unique identifiers of the multiple parts of the picture to be audited can be correspondingly stored in the database for later searching when auditing other pictures.
According to the different results of the audit, step 207 or step 208 is executed alternatively.
And step 207, if the audit result is that the audit is passed, the client is allowed to upload the picture to be audited to the server or store the picture to be audited.
In the embodiment of the invention, when the client requests the server to upload the picture, if the found auditing result is that the auditing is passed, the server sends a message of agreeing to upload the picture to the client. And when the client side uploads the picture to the server, if the found auditing result is that the auditing is passed, the picture is saved on the server.
And 208, if the audit result is that the audit is not passed, rejecting the client to upload the picture to be audited to the server or deleting the picture to be audited.
In the embodiment of the invention, when the client requests the server to upload the picture, if the found auditing result is that the auditing is not passed, the server sends a message of refusing to upload the picture to the client. And when the client side uploads the picture to the server, if the found auditing result is that the auditing is not passed, deleting the picture on the server.
In summary, according to the embodiments of the present invention, by comparing the unique identifiers of the plurality of portions corresponding to the picture to be audited with the unique identifiers of the plurality of portions corresponding to the picture already audited, the audit result of the picture already audited, which has the same unique identifier exceeding the set ratio as the picture to be audited, is found.
Furthermore, the picture to be audited, for which the audit result is not found, is audited, and the audit result obtained by auditing and the unique identifiers of the parts of the picture to be audited are stored, so that the audit result is stored after the picture for which the audit result is not found is audited, the audit result can be searched later when other pictures are audited, and the picture audit efficiency is improved.
Further, if the audit result is that the audit is passed, the client is allowed to upload the picture to be audited to the server or store the picture to be audited, or if the audit result is that the audit is not passed, the client is refused to upload the picture to be audited to the server or delete the picture to be audited, so that the function of automatically judging whether part of pictures can be adopted is realized, and the efficiency of uploading or storing the pictures is improved.
It should be noted that, for simplicity of description, the method embodiments are described as a series of acts or combination of acts, but those skilled in the art will recognize that the present invention is not limited by the illustrated order of acts, as some steps may occur in other orders or concurrently in accordance with the embodiments of the present invention. Further, those skilled in the art will appreciate that the embodiments described in the specification are presently preferred and that no particular act is required to implement the invention.
Referring to fig. 3, a block diagram of a structure of an embodiment of the image auditing apparatus according to the present invention is shown, which may specifically include the following modules:
a dividing module 301, configured to divide a picture to be audited into multiple parts;
an identifier generating module 302, configured to generate a unique identifier of each portion obtained by segmenting the picture to be audited;
the result searching module 303 is configured to search, according to the plurality of unique identifiers corresponding to the picture to be audited, an audit result of an audited picture that is the same as the unique identifier exceeding a set ratio with the picture to be audited;
and the result extracting module 304 is configured to extract an audit result of the searched audited picture as an audit result of the picture to be audited.
In the embodiment of the present invention, preferably, the dividing module is specifically configured to divide the picture to be checked into a plurality of portions with the same size and a set number.
In the embodiment of the present invention, preferably, the dividing module includes:
the rotation sub-module is used for rotating the original picture to obtain a rotated picture;
and the division submodule is used for taking the original picture and the rotated picture as pictures to be checked and dividing the pictures into a plurality of parts respectively.
In the embodiment of the present invention, preferably, the rotated picture is at least one of a rotated picture obtained by clockwise rotating the original picture by 90 degrees, a rotated picture obtained by clockwise rotating the original picture by 180 degrees, and a rotated picture obtained by clockwise rotating the original picture by 270 degrees.
In the embodiment of the present invention, preferably, the identifier generating module includes:
the color value table obtaining submodule is used for obtaining the color value table of the pixel point corresponding to each part according to the position of the pixel point in each part;
the color difference table composition submodule is used for calculating and obtaining the difference between each color value in the color value table and the average value of the color values in the color value table, and forming a color difference table of the pixel point corresponding to each part;
and the identifier generation submodule is used for generating a unique identifier of the color difference table as the unique identifier of each part.
In the embodiment of the present invention, preferably, the unique identifier includes: MD5 value of picture file data, MD5 value of unique feature of picture.
In the embodiment of the present invention, preferably, the apparatus further includes:
the picture auditing module is used for auditing the picture to be audited, of which the auditing result is not found, after the auditing result of the audited picture, which is the same as the unique identifier exceeding the set proportion, of the picture to be audited is found according to the plurality of unique identifiers corresponding to the picture to be audited;
and the result storage module is used for storing the auditing result obtained by auditing and the unique identifiers of the parts of the picture to be audited.
In the embodiment of the present invention, preferably, the apparatus further includes:
the auditing passing module is used for agreeing the client to upload the picture to be audited to the server or store the picture to be audited if the auditing result is that the auditing is passed after the auditing result of the searched audited picture is extracted and used as the auditing result of the picture to be audited;
and the auditing failure module is used for refusing the client to upload the picture to be audited to the server or delete the picture to be audited if the auditing result is that the auditing is not passed.
In summary, according to the embodiments of the present invention, by comparing the unique identifiers of the plurality of portions corresponding to the picture to be audited with the unique identifiers of the plurality of portions corresponding to the picture already audited, the audit result of the picture already audited, which has the same unique identifier exceeding the set ratio as the picture to be audited, is found.
For the device embodiment, since it is basically similar to the method embodiment, the description is simple, and for the relevant points, refer to the partial description of the method embodiment.
The embodiments in the present specification are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, apparatus, or computer program product. Accordingly, embodiments of the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
Embodiments of the present invention are described with reference to flowchart illustrations and/or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing terminal to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing terminal to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing terminal to cause a series of operational steps to be performed on the computer or other programmable terminal to produce a computer implemented process such that the instructions which execute on the computer or other programmable terminal provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications of these embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the embodiments of the invention.
Finally, it should also be noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or terminal 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 terminal. 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 terminal that comprises the element.
The method and the device for checking the picture provided by the invention are described in detail, a specific example is applied in the text to explain the principle and the implementation mode of the invention, and the description of the embodiment is only used for helping to understand the method and the core idea of the invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.
Claims (14)
1. A picture auditing method is characterized by comprising the following steps:
dividing a picture to be audited into a plurality of parts;
generating a unique identifier of each part obtained by dividing the picture to be audited;
according to the plurality of unique identifiers corresponding to the picture to be audited, an audit result of the audited picture which has the same unique identifier exceeding a set proportion with the picture to be audited is searched, the audited picture is a picture which is segmented by adopting the same segmentation method as the picture to be audited, and the audit result is used for describing whether the picture meets requirements or not;
extracting the audit result of the searched audited picture as the audit result of the picture to be audited;
wherein, the dividing the picture to be audited into a plurality of parts includes:
rotating the original picture to obtain a rotated picture;
and taking the original picture and the rotated picture as pictures to be audited, and respectively dividing the pictures into a plurality of parts.
2. The method according to claim 1, wherein the dividing the picture to be audited into a plurality of parts comprises:
the picture to be audited is divided into a set number of parts of the same size.
3. The method according to claim 1, wherein the rotated picture is at least one of a rotated picture obtained by rotating the original picture 90 degrees clockwise, a rotated picture obtained by rotating the original picture 180 degrees clockwise, and a rotated picture obtained by rotating the original picture 270 degrees clockwise.
4. The method according to any one of claims 1 to 3, wherein the generating of the unique identifier of each part segmented from the picture to be audited comprises:
acquiring a color value table of the pixel points corresponding to each part according to the positions of the pixel points in each part;
calculating to obtain the difference value between each color value in the color value table and the average value of the color values in the color value table, and forming a color difference table of the pixel points corresponding to each part;
and generating a unique identifier of the color difference table as a unique identifier of each part.
5. The method of claim 1, wherein the unique identification comprises: MD5 value of picture file data, MD5 value of unique feature of picture.
6. The method according to claim 1, wherein after searching for an audit result of an audited picture having a unique identifier that is the same as the unique identifier of the picture to be audited and exceeds a set ratio according to the plurality of unique identifiers corresponding to the picture to be audited, the method further comprises:
auditing the to-be-audited picture which does not have the audit result;
and storing the auditing result obtained by auditing and the unique identifiers of the parts of the picture to be audited.
7. The method according to claim 1, wherein after the extracting the audit result of the searched audited picture as the audit result of the picture to be audited, the method further comprises:
if the auditing result is that the auditing is passed, the client side is allowed to upload the picture to be audited to a server or store the picture to be audited;
and if the audit result is that the audit is not passed, rejecting the client to upload the picture to be audited to a server or deleting the picture to be audited.
8. A picture auditing device, comprising:
the segmentation module is used for segmenting the picture to be audited into a plurality of parts;
the identification generation module is used for generating a unique identification of each part obtained by dividing the picture to be audited;
the result searching module is used for searching an auditing result of the audited picture which has the same unique identifier exceeding a set proportion with the picture to be audited according to the plurality of unique identifiers corresponding to the picture to be audited, wherein the audited picture is a picture which is segmented by adopting the same segmentation method as the picture to be audited, and the auditing result is used for describing whether the picture meets the requirement or not;
the result extraction module is used for extracting the audit result of the searched audited picture as the audit result of the picture to be audited;
the segmentation module includes:
the rotation sub-module is used for rotating the original picture to obtain a rotated picture;
and the division submodule is used for taking the original picture and the rotated picture as pictures to be checked and dividing the pictures into a plurality of parts respectively.
9. The apparatus according to claim 8, wherein the segmentation module is specifically configured to segment the picture to be reviewed into a set number of portions of the same size.
10. The apparatus according to claim 8, wherein the rotated picture is at least one of a rotated picture obtained by rotating the original picture 90 degrees clockwise, a rotated picture obtained by rotating the original picture 180 degrees clockwise, and a rotated picture obtained by rotating the original picture 270 degrees clockwise.
11. The apparatus according to any one of claims 8 to 10, wherein the identification generation module comprises:
the color value table obtaining submodule is used for obtaining the color value table of the pixel point corresponding to each part according to the position of the pixel point in each part;
the color difference table composition submodule is used for calculating and obtaining the difference between each color value in the color value table and the average value of the color values in the color value table, and forming a color difference table of the pixel point corresponding to each part;
and the identifier generation submodule is used for generating a unique identifier of the color difference table as the unique identifier of each part.
12. The apparatus of claim 8, wherein the unique identifier comprises: MD5 value of picture file data, MD5 value of unique feature of picture.
13. The apparatus of claim 8, further comprising:
the picture auditing module is used for auditing the picture to be audited, of which the auditing result is not found, after the auditing result of the audited picture, which is the same as the unique identifier exceeding the set proportion, of the picture to be audited is found according to the plurality of unique identifiers corresponding to the picture to be audited;
and the result storage module is used for storing the auditing result obtained by auditing and the unique identifiers of the parts of the picture to be audited.
14. The apparatus of claim 8, further comprising:
the auditing passing module is used for agreeing the client to upload the picture to be audited to the server or store the picture to be audited if the auditing result is that the auditing is passed after the auditing result of the searched audited picture is extracted and used as the auditing result of the picture to be audited;
and the auditing failure module is used for refusing the client to upload the picture to be audited to the server or delete the picture to be audited if the auditing result is that the auditing is not passed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710100578.8A CN108470028B (en) | 2017-02-23 | 2017-02-23 | Picture auditing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710100578.8A CN108470028B (en) | 2017-02-23 | 2017-02-23 | Picture auditing method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108470028A CN108470028A (en) | 2018-08-31 |
| CN108470028B true CN108470028B (en) | 2020-08-18 |
Family
ID=63266734
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710100578.8A Active CN108470028B (en) | 2017-02-23 | 2017-02-23 | Picture auditing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108470028B (en) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109886437A (en) * | 2019-03-15 | 2019-06-14 | 山东省农业机械科学研究院 | A kind of electronic component atlas management system based on BS+CS framework |
| CN112381408B (en) * | 2020-11-16 | 2022-10-14 | 支付宝(杭州)信息技术有限公司 | Quality inspection method and device and electronic equipment |
| CN112581033A (en) * | 2020-12-29 | 2021-03-30 | 支付宝(杭州)信息技术有限公司 | Investigation evaluation method and device |
| CN112785659A (en) * | 2021-01-28 | 2021-05-11 | 特赞（上海）信息科技有限公司 | Enterprise case material picture detection method, device, equipment and storage medium |
| CN113095647B (en) * | 2021-04-01 | 2023-01-06 | 中国汽车技术研究中心有限公司 | Vehicle inspection system |
| CN114491184B (en) * | 2022-04-02 | 2022-07-12 | 飞狐信息技术（天津）有限公司 | Data processing method and device, storage medium and electronic equipment |
| CN115514494A (en) * | 2022-09-16 | 2022-12-23 | 长城汽车股份有限公司 | Image transmission method and device, electronic equipment and readable storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101303734A (en) * | 2008-06-25 | 2008-11-12 | 腾讯科技（深圳）有限公司 | System and method for detecting picture |
| CN101996180A (en) * | 2009-08-12 | 2011-03-30 | 升东网络科技发展(上海)有限公司 | Picture examination and filter system and method |
| CN102902675A (en) * | 2011-07-26 | 2013-01-30 | 腾讯科技（深圳）有限公司 | Picture content approval method and device |
| CN103020086A (en) * | 2011-09-26 | 2013-04-03 | 北大方正集团有限公司 | Duplicate checking method and device for pictures |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102122389A (en) * | 2010-01-12 | 2011-07-13 | 阿里巴巴集团控股有限公司 | Method and device for judging image similarity |
| US8811745B2 (en) * | 2010-01-20 | 2014-08-19 | Duke University | Segmentation and identification of layered structures in images |
| CN102521838B (en) * | 2011-12-19 | 2013-11-27 | 国家计算机网络与信息安全管理中心 | Image searching/matching method and system for same |
| CN103578105B (en) * | 2013-11-01 | 2016-04-27 | 中北大学 | A kind of multi-source foreign peoples method for registering images based on provincial characteristics |
-
2017
- 2017-02-23 CN CN201710100578.8A patent/CN108470028B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101303734A (en) * | 2008-06-25 | 2008-11-12 | 腾讯科技（深圳）有限公司 | System and method for detecting picture |
| CN101996180A (en) * | 2009-08-12 | 2011-03-30 | 升东网络科技发展(上海)有限公司 | Picture examination and filter system and method |
| CN102902675A (en) * | 2011-07-26 | 2013-01-30 | 腾讯科技（深圳）有限公司 | Picture content approval method and device |
| CN103020086A (en) * | 2011-09-26 | 2013-04-03 | 北大方正集团有限公司 | Duplicate checking method and device for pictures |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108470028A (en) | 2018-08-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108470028B (en) | Picture auditing method and device | |
| CN112333524B (en) | Dynamic video overlay | |
| CA2906199C (en) | Systems and methods for addressing a media database using distance associative hashing | |
| US20150213324A1 (en) | Photo forensics using image signatures | |
| US9055335B2 (en) | Systems and methods for addressing a media database using distance associative hashing | |
| US20190179851A1 (en) | Systems and methods for addressing a media database using distance associative hashing | |
| US20180159928A1 (en) | Network-Based File Cloud Synchronization Method | |
| US9977823B2 (en) | Content control method, content control apparatus, and program | |
| EP3001871B1 (en) | Systems and methods for addressing a media database using distance associative hashing | |
| RU2637876C2 (en) | Method, server device and terminal device for image delivery | |
| JP2020525935A (en) | Method and apparatus for determining duplicate video | |
| US20160196478A1 (en) | Image processing method and device | |
| CN110321675B (en) | Webpage watermark-based generation and tracing method and device | |
| US9602565B2 (en) | Video processing system, video content monitoring method, video processing apparatus, control method of the apparatus, and storage medium storing control program of the apparatus | |
| CN101425082A (en) | Video file content determining method and system | |
| CN110569213A (en) | File access method, device and equipment | |
| US20140037203A1 (en) | Image Recognition System in a Cloud Environment | |
| WO2020001488A1 (en) | File download method and apparatus, client and computer readable storage medium | |
| CN110209714A (en) | Report form generation method, device, computer equipment and computer readable storage medium | |
| CN104778252B (en) | The storage method and device of index | |
| CN111126928A (en) | Method and device for auditing release content | |
| CN113435439A (en) | Document auditing method and device, storage medium and electronic device | |
| CN109710827B (en) | Picture attribute management method and device, picture server and business processing terminal | |
| US20150186751A1 (en) | Image duplication detection | |
| CN108449627B (en) | Video processing method, video source identification method, video processing device, video source identification device and video source identification 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 |