CN113111200B - Method, device, electronic equipment and storage medium for auditing picture files - Google Patents
Method, device, electronic equipment and storage medium for auditing picture files Download PDFInfo
- Publication number
- CN113111200B CN113111200B CN202110385971.2A CN202110385971A CN113111200B CN 113111200 B CN113111200 B CN 113111200B CN 202110385971 A CN202110385971 A CN 202110385971A CN 113111200 B CN113111200 B CN 113111200B
- Authority
- CN
- China
- Prior art keywords
- picture file
- data
- file
- picture
- auditing
- 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
- 238000000034 method Methods 0.000 title claims abstract description 57
- 238000012545 processing Methods 0.000 claims abstract description 84
- 230000002159 abnormal effect Effects 0.000 claims abstract description 69
- 230000006835 compression Effects 0.000 claims abstract description 33
- 238000007906 compression Methods 0.000 claims abstract description 33
- 238000001514 detection method Methods 0.000 claims description 18
- 238000004590 computer program Methods 0.000 claims description 13
- 238000004458 analytical method Methods 0.000 claims description 10
- 238000012550 audit Methods 0.000 claims description 9
- 238000006243 chemical reaction Methods 0.000 claims description 9
- 230000005856 abnormality Effects 0.000 claims description 7
- 230000008569 process Effects 0.000 claims description 5
- 238000013473 artificial intelligence Methods 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 10
- 238000004891 communication Methods 0.000 description 9
- 230000006870 function Effects 0.000 description 7
- 238000004422 calculation algorithm Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000003993 interaction Effects 0.000 description 3
- 238000007726 management method Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000013527 convolutional neural network Methods 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000007635 classification algorithm Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 239000000047 product Substances 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/40—Information retrieval; Database structures therefor; File system structures therefor of multimedia data, e.g. slideshows comprising image and additional audio data
- G06F16/48—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/483—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
- G06F16/40—Information retrieval; Database structures therefor; File system structures therefor of multimedia data, e.g. slideshows comprising image and additional audio data
- G06F16/41—Indexing; Data structures therefor; Storage structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/40—Information retrieval; Database structures therefor; File system structures therefor of multimedia data, e.g. slideshows comprising image and additional audio data
- G06F16/45—Clustering; Classification
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Library & Information Science (AREA)
- Software Systems (AREA)
- Information Transfer Between Computers (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The disclosure provides a method, a device, electronic equipment and a storage medium for auditing a picture file, which are applied to the technical field of computers, particularly to the technical field of artificial intelligence and can be used for multimedia information identification and multimedia information auditing scenes. The specific implementation scheme of the method for auditing the picture file is as follows: acquiring a picture file to be audited; detecting whether the picture file contains streaming data or not under the condition that the picture file is determined to be a lossless compression file; and under the condition that the picture file is detected to contain streaming data, auditing the streaming data by adopting a preset processing model to determine whether the picture file is abnormal.
Description
Technical Field
The present disclosure relates to the field of computer technology, and in particular, to the field of artificial intelligence technology, and more particularly, to a method, an apparatus, an electronic device, and a storage medium for auditing a picture file applicable to multimedia information identification and multimedia information auditing scenarios.
Background
With the development of computer technology, the multimedia data is increasingly diversified in its form of embodiment. If the diversified form is used illegally by some specific users, for example, the user conceals the abnormal data in the multimedia data by using the diversified form to bypass the auditing of each information platform, the abnormal data may be widely spread, and the social air is negatively affected.
Disclosure of Invention
Provided are a method, a device, equipment and a storage medium for auditing picture files, which can improve auditing accuracy.
According to one aspect of the present disclosure, there is provided a method of auditing a picture file, including: acquiring a picture file to be audited; detecting whether the picture file contains streaming data or not under the condition that the picture file is determined to be a lossless compression file; and under the condition that the picture file is detected to contain streaming data, auditing the streaming data by adopting a preset processing model to determine whether the picture file is abnormal.
According to another aspect of the present disclosure, there is provided an apparatus for auditing a picture file, including: the file acquisition module is used for acquiring a picture file to be audited; the data detection module is used for detecting whether the picture file contains streaming data or not under the condition that the picture file is determined to be a lossless compression file; and the data auditing module is used for auditing the streaming data by adopting a preset processing model under the condition that the streaming data is detected to be contained in the picture file so as to determine whether the picture file is abnormal.
According to another aspect of the present disclosure, there is provided an electronic device including: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of auditing a picture file provided by the present disclosure.
According to another aspect of the present disclosure, there is provided a non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform the method of auditing a picture file provided by the present disclosure.
According to another aspect of the present disclosure, there is provided a computer program product comprising a computer program which, when executed by a processor, implements the method of auditing a picture file provided by the present disclosure.
It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the disclosure, nor is it intended to be used to limit the scope of the disclosure. Other features of the present disclosure will become apparent from the following specification.
Drawings
The drawings are for a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:
fig. 1 is an application scenario schematic diagram of a method and apparatus for auditing a picture file according to an embodiment of the present disclosure;
FIG. 2 is a flow chart of a method of auditing a picture file according to an embodiment of the present disclosure;
FIG. 3 is a schematic illustration of a method of auditing a picture file according to an embodiment of the present disclosure;
Fig. 4 is a flowchart illustrating detecting whether a picture file contains streaming data according to an embodiment of the present disclosure;
FIG. 5 is a schematic diagram of auditing of streaming data using a predetermined auditing model, according to an embodiment of the present disclosure;
FIG. 6 is a block diagram of an apparatus for auditing a picture file according to an embodiment of the present disclosure; and
Fig. 7 is a block diagram of an electronic device for implementing a method of auditing picture files in accordance with an embodiment of the present disclosure.
Detailed Description
Exemplary embodiments of the present disclosure are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present disclosure to facilitate understanding, and should be considered as merely exemplary. Accordingly, one of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
The present disclosure provides a method of auditing a picture file, the method including a file acquisition stage, a data detection stage, and a data auditing stage. And in the file acquisition stage, acquiring a picture file to be audited. In the data detection stage, if the picture file is determined to be a lossless compression file, whether the picture file contains streaming data or not is detected. And in the data auditing stage, under the condition that the picture file is detected to contain streaming data, auditing the streaming data by adopting a preset processing model so as to determine whether the picture file is abnormal.
An application scenario of the method and apparatus provided by the present disclosure will be described below with reference to fig. 1.
Fig. 1 is an application scenario schematic diagram of a method and apparatus for auditing a picture file according to an embodiment of the present disclosure.
As shown in fig. 1, the application scenario 100 includes a terminal device 110 and a server 130. Terminal device 110 may be communicatively coupled to server 130 via a network, which may include wired or wireless communication links.
According to embodiments of the present disclosure, terminal device 110 may be, for example, various electronic devices capable of providing a user interaction interface and having processing functionality, including but not limited to smartphones, tablets, laptop and desktop computers, and the like.
By way of example, the terminal device 110 may be installed with various client applications, such as a picture editing class application, a search class application, an instant messaging tool, etc. (just examples). The user may generate the picture file 120, for example, through a picture editing class application, in hopes of providing information available for retrieval to other client applications, such as a search class application. The user may interact with the server 130 over a network, for example, using the terminal device 110 to send the generated picture file 120 to the server 130 for review by the server 130.
According to embodiments of the present disclosure, the server 130 may be, for example, a background management server that provides support for the operation of the other client applications described above, or any server that may communicate with a background management server that provides support for the operation of other client applications. The server may be a cloud server, a server of a distributed system, or a server incorporating a blockchain.
For example, the server 130 may audit the received picture file 120 to confirm whether the picture file 120 is an abnormal file. If the file is a non-abnormal file, the picture file 120 is determined to pass the audit.
Illustratively, as shown in FIG. 1, the application scenario 100 may also include, for example, a database 140. The database 140 maintains a full amount of data provided to other client applications. Upon the server 130 confirming that the picture file 120 passes the audit, the picture file 120 may also be stored in the database 140, for example, to supplement data provided to other client applications.
The electronic device 150 may illustratively access the database 140 to search for user-retrieved data from the full amount of data in the database 140, for example. The electronic device 150 may be a server, a smart phone, a tablet computer, a laptop portable computer, a desktop computer, and the like.
It should be noted that, the method for auditing the picture file provided in the present disclosure may be performed by the server 130. Accordingly, the device for auditing the picture file provided in the present disclosure may be disposed in the server 130. The method of auditing picture files provided by the present disclosure may also be performed by a server or cluster of servers other than server 130 and capable of communicating with server 130. Accordingly, the apparatus for auditing the picture file provided in the present disclosure may also be provided in a server or a server cluster that is different from the server 130 and capable of communicating with the server 130.
It should be understood that the number and types of terminal devices, servers, databases, and electronic devices in fig. 1 are merely illustrative. There may be any number and type of terminal devices, servers, databases, and electronic devices, as desired for implementation.
Fig. 2 is a flow chart of a method of auditing a picture file according to an embodiment of the present disclosure.
As shown in fig. 2, the method 200 of auditing the picture file in this embodiment includes operations S210 to S250.
In operation S210, a picture file to be audited is acquired.
According to an embodiment of the disclosure, the picture file to be audited may be a file in JPEG, TIFF, RAW, BMP, GIF or PNG format, for example. It will be appreciated that the format of the pending picture file is merely exemplary to facilitate understanding of the present disclosure, which is not limited by the present disclosure.
According to an embodiment of the present disclosure, the file to be audited provided by the user may include, for example, a plurality of types of multimedia files, and the operation S210 may select a picture file from the multimedia files as the picture file to be audited. In an embodiment, the picture file to be audited may be sent to the server for auditing by the server, for example, by the user via a user generated content (User Generated Content, UGC) platform.
In operation S220, it is determined whether the picture file is a lossless compression file.
According to embodiments of the present disclosure, whether a picture file is a lossless compression file may be determined according to a format of the picture file. The lossless compression means that the compressed data is used for reconstruction, and the data obtained after reconstruction is identical to the original data. The format of the picture file may be determined according to the suffix name of the picture file.
Illustratively, if the picture file is in PNG format, the picture file is determined to be a lossless compression file. This is because PNG is a bitmap format employing a lossless compression algorithm. It is understood that PNG format is only one storage format for lossless compressed files, and this list is only used for the understanding of the present disclosure. The format of the stored picture obtained by adopting the lossless compression algorithm can be used as the basis for judging whether the picture file is a lossless compression file or not.
In case it is determined that the picture file is not a lossless compression file, operation S230 is performed. In case that it is determined that the picture file is a lossless compression file, operation S240 is performed.
In operation S230, the picture in the picture file is audited by using the picture audit model.
According to an embodiment of the present disclosure, the picture audit model may be, for example, an object detection model for detecting whether a picture in a picture file contains an abnormal object. If the abnormal object is contained, determining that the picture file does not pass the verification, and if the abnormal object is not contained, determining that the picture file passes the verification. The object detection model may be a deep neural network model, and the disclosure is not limited thereto.
In operation S240, it is detected whether streaming data is included in the picture file. According to an embodiment of the present disclosure, whether streaming data is contained in a picture file may be determined by decoding the picture file. The streaming data may comprise, for example, audio data and/or video data, etc.
For example, whether a file is hidden in a picture file may be detected according to a storage capacity of the picture file and a picture size. For example, if the picture size in the picture file is 400 pixels by 400 pixels, each pixel occupies 4 bytes (where the R channel, G channel, B channel, and alpha transparent channel each occupy one byte), it can be determined that the maximum storage capacity required for storing the pictures in the picture file is 400 by 400 x 4/1024=625 KB when not compressed. If the storage capacity of the picture file is greater than the maximum storage capacity, it may be determined that the picture file contains streaming data.
If it is detected that the picture file does not contain streaming data, the operation S230 is executed back; in case that it is detected that the streaming data is included in the picture file, operation S250 is performed.
In operation S250, the streaming data is audited using a predetermined processing model to determine whether the picture file is abnormal.
According to the embodiment of the disclosure, when the streaming data is included in the picture file, the picture file may be parsed, and the streaming data may be extracted from the picture file. Features of the streaming data are then extracted using a predetermined processing model and the streaming data is classified according to the extracted features. The classification result may indicate whether the stream data is abnormal data, and if so, it may be determined that the picture file is abnormal. If the classification result indicates that the streaming data is normal data, it can be determined that abnormal data is not hidden in the picture file, and when the picture in the picture file is checked and determined that the picture is abnormal, the picture file can be shared and transmitted through each Internet platform. The predetermined processing model may be a model such as a convolutional neural network model that can be used for object detection to detect an abnormal object from the streaming data. In the case where the abnormal target is included in the streaming data, the streaming data is outputted as a classification result of the abnormal data. It will be appreciated that the predetermined process model described above is merely exemplary to facilitate an understanding of the present disclosure, and the present disclosure is not limited thereto.
According to the embodiment of the disclosure, when the streaming data is detected to be contained in the picture file, a mplayer player or the like can be used for playing the picture file, and the streaming data hidden by the picture file can be heard and seen through the mplayer player. Therefore, whether the hidden stream data has abnormal content or not is determined according to the playing result, and if the hidden stream data has abnormal content, the picture file is determined to be abnormal. It will be appreciated that the above-described player is merely exemplary to facilitate an understanding of the present disclosure, and that any player having a decoding function and a playing function may be employed by the present disclosure to play a picture file.
According to the embodiment of the disclosure, after the picture file is obtained, the integrity of the picture file with the hidden streaming data can be checked by detecting whether the streaming data is contained in the picture file and checking the streaming data when the streaming data is contained. Compared with the technical scheme that only the pictures in the picture files are audited in the prior art, the picture files of the non-abnormal pictures hiding the abnormal data can be effectively prevented from bypassing the auditing platform, so that the abnormal data are transmitted in the network, auditing accuracy and management effectiveness of the transmitted data can be improved, safety and health transmission of network information can be facilitated, and network environment can be purified.
In accordance with embodiments of the present disclosure, a firmware analysis tool may be employed to analyze a picture file in detecting whether the picture file contains streaming data. The embodiment can obtain the data type contained in the picture file through analysis of the firmware analysis tool. After the data type is obtained, whether the picture file contains streaming data or not is determined according to the data type. In this way, the accuracy of detecting streaming data is improved.
For example, if the analyzed data type includes a streaming data type, it may be determined that streaming data is included in the picture file. The firmware analysis tool may include Binwalk or the like tools for searching a given binary image file to obtain an embedded file and embedded code, which is designed to identify files and code within the embedded firmware image.
For example, if the picture file contains only picture data, the Description information (Description) analyzed by the firmware analysis tool generally includes only one line of Description information describing the size of the picture, etc. If the picture file contains streaming data, the description information analyzed by the firmware analysis tool also includes description information of the data stream (STREAM DATA). Therefore, if the data type analyzed by the firmware analysis tool further includes a data stream, it may be determined that the picture file includes streaming data.
Fig. 3 is a schematic diagram of a method of auditing a picture file according to an embodiment of the present disclosure.
According to embodiments of the present disclosure, it may be determined whether a picture file is a lossless compressed file by analyzing a binary stream of the picture file. Typically the data at the first 4 byte positions of the binary stream represents the storage format of the picture file, and therefore it can be determined whether the picture file is a lossless compressed file by comparing the data at the first 4 byte positions with a binary representation of a predetermined lossless compressed format.
Illustratively, as shown in fig. 3, after the image file to be checked is obtained, the method 300 for checking the image file in this embodiment may convert the image file 310 to obtain a binary file 320, that is, the binary stream is used to represent the image file 310. For example, base64 may be used to implement conversion between a picture file and a binary file. In one example, the binary stream converted from the picture file may be "10001001 01010000.
After the binary file is obtained, it may be first determined whether the data located at the predetermined byte position in the binary file describes the data in the lossless compression format. This embodiment may maintain a list of lossless compression formats with binary data representations. If the data at the predetermined byte position is data belonging to the lossless compression format list, it is determined that the data at the predetermined byte position describes a lossless compression format, and thus the picture file is determined to be a lossless compression file. Wherein the predetermined byte position may be the first 4 bytes of the binary file. It is understood that the binary code at the predetermined byte position represents the storage format of the data picture file, and the predetermined byte position may be set according to the actual situation, which is not limited in the present disclosure.
In one embodiment, after the binary file is obtained, the binary file may also be converted to hexadecimal file 330, as shown in FIG. 3. Accordingly, the lossless compression format list may be represented by hexadecimal. After obtaining the hexadecimal file, the hexadecimal data at the predetermined byte position can be compared with the lossless compression format list to determine whether the picture file is a lossless compression file. In one example, if the data at the first 4 bytes of the hexadecimal file is "89 50 4E 47 0D 0A 1A 0A", then the storage format of the picture file 310 may be determined to be the PNG format, and thus the picture file is determined to be the lossless compression file 340.
Fig. 4 is a flowchart illustrating a process of detecting whether a picture file contains streaming data according to an embodiment of the present disclosure.
In carrying out the present disclosure, the inventors have found that when streaming data is contained in a picture file, there is typically a specific identifier in a binary stream of the picture file, the specific identifier being used to indicate a decoder, and when the indicated decoder is used to decode the picture file, the streaming data can be decoded. The embodiment may use the specific identifier in the binary stream as a basis for determining whether the picture file contains streaming data.
For example, as shown in fig. 4, in this embodiment, the operation of detecting whether streaming data is included in the picture file may include operations S441 to S442.
In operation S441, the picture file is converted into a binary file. The implementation manner of this operation is similar to the method for implementing conversion between a picture file and a binary file based on Base64 or the like described above, and will not be described here again.
In operation S442, it is determined whether an identifier is included in the binary file. The identifier may be an identifier corresponding to the audio decoder and/or the audio decoder.
Illustratively, this embodiment may maintain a list of identifiers of the audio decoder and identifiers of the video decoder as the list of identifiers. After the binary file is obtained through conversion, the binary code in the binary file can be compared with each identifier in the identifier list, and if the binary file contains a certain identifier in the identifier list, the binary file is determined to contain the identifier corresponding to the audio decoder and/or the video decoder.
The list of identifiers may, for example, comprise identifiers in hexadecimal representation, for example. After the binary file is obtained, the binary file can be converted into a hexadecimal file, and then the hexadecimal code in the hexadecimal file is compared with each identifier in the identifier list. In an example, if the converted hexadecimal file includes hexadecimal code "46 46 6D 70 65 67" indicating FFmpeg, since FFmpeg is an open source computer program for recording, converting digital audio and video, and converting it into a stream (i.e. open source software for audio and video processing), it can be determined that the hexadecimal code "46 46 6D 70 65 67" indicates an audio and video decoder. So that it can be determined that the picture file contains streaming data. In this case, the identifier may be a binary representation of hexadecimal code "46 46 6D 70 65 67". It is to be understood that the above-described identifiers, audio decoder, and video decoder are merely examples to facilitate understanding of the present disclosure, which is not limited thereto.
If it is determined that the identifier is included in the binary file through operation S442, operation S443 may be performed to determine that the picture file contains streaming data.
If it is determined that the identifier is not included in the binary file through operation S442, it may be determined that the streaming data is not included in the picture file.
In accordance with embodiments of the present disclosure, in the event that it is determined that no identifier is included in the binary file, for example, the storage capacity of the picture file may also be audited to determine whether the picture file contains streaming data. Therefore, the condition of low detection accuracy of the streaming data caused by incomplete identifiers maintained in the identifier list is avoided, and the detection accuracy is further improved.
For example, as shown in fig. 4, if it is determined that the identifier is not included in the binary file through operation S442, the operation of detecting whether the picture file contains streaming data in this embodiment may further include operations S444 to S447.
In operation S444, the size of the picture in the picture file and the storage capacity required to store the picture file are determined. This embodiment can acquire the size of the picture and the storage capacity of the picture file using a JavaScript statement or the like written in advance. It will be appreciated that the above-described method of obtaining size and storage capacity is merely by way of example to facilitate an understanding of the present disclosure, which is not limited thereto.
In operation S445, a maximum storage capacity required to store the picture is determined based on the size of the picture. This operation may be similar to the method of calculating the maximum storage capacity required to store the pictures in the picture file described above, and will not be described again.
In operation S446, it is determined whether the storage capacity is greater than the maximum storage capacity.
If the storage capacity is greater than the maximum storage capacity, operation S443 is performed to determine that the picture file contains streaming data. If the storage capacity is not greater than the maximum storage capacity, operation S447 is performed to determine that the picture file does not contain streaming data.
It can be appreciated that when it is determined that the picture file does not include streaming data, the picture file may also be cached to a predetermined storage space for an auditor to perform manual audit.
Fig. 5 is a schematic diagram of auditing streaming data using a predetermined auditing model, according to an embodiment of the present disclosure.
According to the embodiment of the disclosure, when the streaming data comprises a plurality of types of data, different processing models can be adopted to respectively process the different types of data, so that the auditing precision is improved.
For example, as shown in fig. 5, when auditing streaming data, the embodiment 500 may first decode the picture file 510 to obtain various types of streaming data contained in the picture file. Any tool such as the FFmpeg decoder described above that can decode various types of streaming data can be used for decoding. Through decoding, different types of streaming data in the picture file can be separated, and at least one streaming data with the same number as the types of the streaming data in the picture file is obtained.
In one embodiment, as shown in fig. 5, audio data 511 and video data 512 may be obtained by decoding. After the at least one stream data is obtained by decoding, a matched processing model can be selected according to the type of the stream data, and whether the picture file is abnormal or not can be determined according to the processing result. For example, the audio data 511 is processed using the audio processing model 520, resulting in a first processing result 530. The video data 512 is processed using the video processing model 540 to obtain a second processing result 550. Finally, the first processing result 530 and the second processing result 550 are used as a judgment basis to judge whether the picture file 510 is abnormal. For example, if at least one of the audio data and the video data is abnormal, it may be determined that the picture file is abnormal.
According to an embodiment of the present disclosure, the audio processing model 520 may be, for example, a recurrent neural network model, and the first processing result 530 may indicate whether the audio data is abnormal. For example, the audio processing model 520 may have a function of converting audio data into text information, then performing semantic understanding on the text information, determining whether abnormal audio is included in the audio data according to the semantic understanding result, and outputting a processing result of whether the audio data is abnormal according to the determination result. The output layer of the audio processing model 520 may be constructed based on a classification algorithm, for example, to output a classification result of abnormal audio data or normal audio data.
Illustratively, the audio processing model 520 may identify not only whether the audio data contains abnormal audio but also an abnormal category of the abnormal audio when processing the audio data. The abnormal category is one of a plurality of categories set in advance. Accordingly, the first processing result may also indicate an abnormal category of the audio data, for example. For example, the first processing result includes first data indicating abnormality and second data indicating abnormality category of the audio data. By the method, the abnormal categories can be obtained through the processing model, so that abnormal picture files can be conveniently classified and stored later, or more abundant information can be provided for subsequent manual auditing work of auditors.
According to an embodiment of the present disclosure, the video processing model 540 may be, for example, a convolutional neural network model, and the second processing result 550 may indicate whether the video data is abnormal. For example, the video processing model 540 may have a function of extracting features from a video frame and recognizing an object based on the extracted features, and output a processing result of whether video data is abnormal according to whether the recognized object includes an abnormal object. If the abnormal object is included, the output second processing result indicates that the video data is abnormal, otherwise, the output second processing result indicates that the video data is normal.
Illustratively, the video processing model 540 may identify not only whether the video data contains an abnormal object, but also an abnormal category of the abnormal object when processing the video data. The abnormal category is one of a plurality of categories set in advance. Accordingly, the second processing result may also indicate, for example, an abnormal category of the video data (i.e., an abnormal category of the abnormal object). For example, the second processing result includes first data indicating an abnormality and second data indicating an abnormality category of the video data. By the method, the abnormal categories can be obtained through the processing model, so that abnormal picture files can be conveniently classified and stored later, or more abundant information can be provided for subsequent manual auditing work of auditors.
Based on the method for auditing the picture file, the disclosure further provides a device for auditing the picture file, which will be described in detail below with reference to fig. 6.
Fig. 6 is a block diagram of an apparatus for auditing a picture file according to an embodiment of the present disclosure.
As shown in fig. 6, the apparatus 600 for auditing a picture file according to this embodiment includes a file acquisition module 610, a data detection module 630, and a data auditing module 650.
The file obtaining module 610 is configured to obtain a picture file to be audited. In an embodiment, the file obtaining module 610 may be configured to perform the operation S210 described above, which is not described herein.
The data detection module 630 is configured to detect whether the picture file contains streaming data if it is determined that the picture file is a lossless compression file. In an embodiment, the data detection module 630 may be used to perform the operation S240 described above, which is not described herein.
The data auditing module 650 is configured to audit the streaming data by using a predetermined processing model to determine whether the picture file is abnormal, if it is detected that the streaming data is included in the picture file. In an embodiment, the data auditing module 650 may be configured to perform the operation S250 described above, and will not be described herein.
The apparatus 600 for auditing a picture file may further include a file conversion module and a file determination module, for example. The file conversion module is used for converting the picture file into a binary file. The file determining module is used for determining that the picture file is a lossless compression file in the case that the data located at the predetermined byte position in the binary file is determined to be the data used for representing the lossless compression format.
In an embodiment, the data detection module 630 may include a file conversion sub-module and a first data determination sub-module, where the file conversion sub-module is used to convert a picture file into a binary file. The first data determination sub-module is used for determining that the picture file contains streaming data in the case that the binary file contains identifiers corresponding to the audio decoder and/or the video decoder.
In an embodiment, the data detection module 630 may further include a first capacity determination sub-module and a second capacity determination sub-module. The first capacity determination submodule is used for determining the size of the picture in the picture file and the storage capacity required for storing the picture file in the case that the identifier is not included in the binary file. The second capacity determination submodule is used for determining the maximum storage capacity required for storing the picture based on the size of the picture. The above-mentioned first data determining submodule may be further configured to determine that the picture file contains streaming data in a case where the storage capacity is greater than the maximum storage capacity.
In another embodiment, the data detection module 630 may include a data type acquisition sub-module and a second data determination sub-module. The data type acquisition submodule is used for analyzing the picture file by adopting a firmware analysis tool to obtain the data type contained in the picture file. The second data determining sub-module is used for determining that the picture file contains streaming data in the case that the data type comprises the streaming data type.
The data auditing module 650 described above may include a file decoding sub-module, a first processing sub-module, a second processing sub-module, and an anomaly determination sub-module, according to embodiments of the present disclosure. The file decoding submodule is used for decoding the picture file to obtain audio data and video data contained in the picture file. The first processing sub-module is used for processing the audio data by adopting the audio processing model to obtain a first processing result, and the first processing result indicates whether the audio data is abnormal or not. The second processing sub-module is used for processing the video data by adopting the video processing model to obtain a second processing result, and the second processing result indicates whether the video data is abnormal or not. The abnormality determination sub-module is used for determining that the picture file is abnormal in the case that at least one of the audio data and the video data is abnormal.
According to an embodiment of the present disclosure, the first processing result also indicates an abnormality category of the audio data. The second processing result also indicates an anomaly class of the video data.
It should be noted that, in the technical solution of the present disclosure, the acquisition, storage, application, etc. of the related personal information of the user all conform to the rules of the related laws and regulations, and do not violate the popular regulations of the public order.
According to embodiments of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.
Fig. 7 is a block diagram of an electronic device 700 for implementing a method of auditing picture files in accordance with an embodiment of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the disclosure described and/or claimed herein.
As shown in fig. 7, the apparatus 700 includes a computing unit 701 that can perform various appropriate actions and processes according to a computer program stored in a Read Only Memory (ROM) 702 or a computer program loaded from a storage unit 708 into a Random Access Memory (RAM) 703. In the RAM 703, various programs and data required for the operation of the device 700 may also be stored. The computing unit 701, the ROM 702, and the RAM 703 are connected to each other through a bus 704. An input/output (I/O) interface 705 is also connected to bus 704.
Various components in device 700 are connected to I/O interface 705, including: an input unit 706 such as a keyboard, a mouse, etc.; an output unit 707 such as various types of displays, speakers, and the like; a storage unit 708 such as a magnetic disk, an optical disk, or the like; and a communication unit 709 such as a network card, modem, wireless communication transceiver, etc. The communication unit 709 allows the device 700 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.
The computing unit 701 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of computing unit 701 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 701 performs the respective methods and processes described above, for example, a method of auditing a picture file. For example, in some embodiments, the method of auditing a picture file may be implemented as a computer software program tangibly embodied on a machine-readable medium, such as storage unit 708. In some embodiments, part or all of the computer program may be loaded and/or installed onto device 700 via ROM702 and/or communication unit 709. When the computer program is loaded into RAM703 and executed by computing unit 701, one or more steps of the method of auditing a picture file described above may be performed. Alternatively, in other embodiments, the computing unit 701 may be configured to perform the method of auditing the picture file by any other suitable means (e.g., by means of firmware).
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.
Program code for carrying out methods of the present disclosure may be written in any combination of one or more programming languages. These program code may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus such that the program code, when executed by the processor or controller, causes the functions/operations specified in the flowchart and/or block diagram to be implemented. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. The machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and pointing device (e.g., a mouse or trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), and the internet.
The computer system may include a client and a server. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other.
It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps recited in the present disclosure may be performed in parallel or sequentially or in a different order, provided that the desired results of the technical solutions of the present disclosure are achieved, and are not limited herein.
The above detailed description should not be taken as limiting the scope of the present disclosure. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present disclosure are intended to be included within the scope of the present disclosure.
Claims (17)
1. A method of auditing a picture file, comprising:
Acquiring a picture file to be audited;
detecting whether the picture file contains streaming data or not under the condition that the picture file is determined to be a lossless compression file; and
Under the condition that the picture file contains the streaming data, auditing the streaming data by adopting a preset processing model to determine whether the picture file is abnormal;
Wherein the method further comprises: and under the condition that the picture file is not a lossless compression file or the streaming data contained in the picture file is not detected, adopting a picture auditing model to audit the pictures in the picture file.
2. The method of claim 1, further comprising:
Converting the picture file into a binary file; and
In a case where it is determined that the data located at the predetermined byte position in the binary file is data representing a lossless compression format, it is determined that the picture file is a lossless compression file.
3. The method of claim 1 or 2, wherein detecting whether streaming data is contained in the picture file comprises:
Converting the picture file into a binary file; and
In the case that the binary file is determined to include an identifier corresponding to an audio decoder and/or a video decoder, it is determined that streaming data is included in the picture file.
4. The method of claim 3, wherein detecting whether streaming data is contained in the picture file further comprises:
determining a size of a picture in the picture file and a storage capacity required to store the picture file, if the identifier is not included in the binary file;
Determining a maximum storage capacity required for storing the picture based on the size of the picture; and
And determining that the picture file contains streaming data under the condition that the storage capacity is larger than the maximum storage capacity.
5. The method of claim 1 or 2, wherein detecting whether streaming data is contained in the picture file comprises:
Analyzing the picture file by adopting a firmware analysis tool to obtain the data type contained in the picture file; and
In the case that the data type includes a streaming data type, it is determined that streaming data is included in the picture file.
6. The method of any of claims 1-5, wherein auditing the streaming data with a predetermined process model comprises:
Decoding the picture file to obtain audio data and video data contained in the picture file;
processing the audio data by adopting an audio processing model to obtain a first processing result, wherein the first processing result indicates whether the audio data is abnormal or not;
processing the video data by adopting a video processing model to obtain a second processing result, wherein the second processing result indicates whether the video data is abnormal or not; and
In the case that at least one of the audio data and the video data is abnormal, determining that the picture file is abnormal.
7. The method of claim 6, wherein,
The first processing result also indicates an anomaly class of the audio data;
the second processing result also indicates an anomaly class of the video data.
8. An apparatus for auditing a picture file, comprising:
the file acquisition module is used for acquiring a picture file to be audited;
The data detection module is used for detecting whether the picture file contains streaming data or not under the condition that the picture file is determined to be a lossless compression file; and
The data auditing module is used for auditing the streaming data by adopting a preset processing model under the condition that the streaming data is contained in the picture file, so as to determine whether the picture file is abnormal;
Wherein, the data auditing module is further used for: and under the condition that the picture file is not a lossless compression file or the streaming data contained in the picture file is not detected, adopting a picture auditing model to audit the pictures in the picture file.
9. The apparatus of claim 8, further comprising:
the file conversion module is used for converting the picture file into a binary file; and
And the file determining module is used for determining the picture file to be a lossless compression file under the condition that the data positioned at the preset byte position in the binary file is determined to be the data used for representing the lossless compression format.
10. The apparatus of claim 8 or 9, wherein the data detection module comprises:
The file conversion sub-module is used for converting the picture file into a binary file; and
A first data determining sub-module for determining that the picture file contains streaming data in case that it is determined that an identifier corresponding to an audio decoder and/or a video decoder is included in the binary file.
11. The apparatus of claim 10, wherein the data detection module further comprises:
A first capacity determination submodule, configured to determine a size of a picture in the picture file and a storage capacity required for storing the picture file, in a case where it is determined that the identifier is not included in the binary file; and
A second capacity determination sub-module for determining a maximum storage capacity required for storing the picture based on a size of the picture,
The first data determining submodule is further used for determining that streaming data is contained in the picture file under the condition that the storage capacity is larger than the maximum storage capacity.
12. The apparatus of claim 8 or 9, wherein the data detection module comprises:
The data type acquisition sub-module is used for analyzing the picture file by adopting a firmware analysis tool to obtain the data type contained in the picture file; and
And the second data determining submodule is used for determining that streaming data is contained in the picture file when the data type comprises the streaming data type.
13. The apparatus of any of claims 8-12, wherein the data auditing module comprises:
the file decoding submodule is used for decoding the picture file to obtain audio data and video data contained in the picture file;
the first processing sub-module is used for processing the audio data by adopting an audio processing model to obtain a first processing result, and the first processing result indicates whether the audio data is abnormal or not;
The second processing sub-module is used for processing the video data by adopting a video processing model to obtain a second processing result, and the second processing result indicates whether the video data is abnormal or not; and
An abnormality determination sub-module for determining that the picture file is abnormal in the case that at least one of the audio data and the video data is abnormal.
14. The apparatus of claim 13, wherein,
The first processing result also indicates an anomaly class of the audio data;
the second processing result also indicates an anomaly class of the video data.
15. An electronic device, comprising:
at least one processor; and
A memory communicatively coupled to the at least one processor; wherein,
The memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1 to 7.
16. A non-transitory computer readable storage medium storing computer instructions for causing the computer to perform the method of any one of claims 1-7.
17. A computer program product comprising a computer program which, when executed by a processor, implements the method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110385971.2A CN113111200B (en) | 2021-04-09 | 2021-04-09 | Method, device, electronic equipment and storage medium for auditing picture files |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110385971.2A CN113111200B (en) | 2021-04-09 | 2021-04-09 | Method, device, electronic equipment and storage medium for auditing picture files |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113111200A CN113111200A (en) | 2021-07-13 |
| CN113111200B true CN113111200B (en) | 2024-05-24 |
Family
ID=76716059
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110385971.2A Active CN113111200B (en) | 2021-04-09 | 2021-04-09 | Method, device, electronic equipment and storage medium for auditing picture files |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113111200B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113674246B (en) * | 2021-08-20 | 2023-09-01 | 百度在线网络技术（北京）有限公司 | Method, device, electronic equipment and storage medium for auditing picture files |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101184241A (en) * | 2007-12-03 | 2008-05-21 | 中兴通讯股份有限公司 | Image automatic detection method and apparatus |
| WO2009015422A1 (en) * | 2007-07-30 | 2009-02-05 | Michael Kefaloukos | A computer-implemented security method and system |
| CN101882296A (en) * | 2010-05-07 | 2010-11-10 | 邹阿金 | Method for hiding Chebyshev neural network chaotic digital watermark information |
| CN106101713A (en) * | 2016-07-06 | 2016-11-09 | 武汉大学 | A kind of video steganalysis method based on the calibration of window optimum |
| CN106845242A (en) * | 2016-08-26 | 2017-06-13 | 中国科学院信息工程研究所 | A kind of steganographic detection and extracting method based on IS4 software features |
| WO2018120946A1 (en) * | 2016-12-30 | 2018-07-05 | 广州虎牙信息科技有限公司 | Method and apparatus for determining video image abnormality, and terminal device |
| CN108509775A (en) * | 2018-02-08 | 2018-09-07 | 暨南大学 | A kind of malice PNG image-recognizing methods based on machine learning |
| CN109348211A (en) * | 2018-08-06 | 2019-02-15 | 中国科学院声学研究所 | The general information of interframe encode hides detection method in a kind of video frame |
| CN109785848A (en) * | 2019-01-28 | 2019-05-21 | 宁波大学 | The bis- compression audio-frequency detections of AAC based on scale factor coefficient differentials |
| CN109817233A (en) * | 2019-01-25 | 2019-05-28 | 清华大学 | Voice flow steganalysis method and system based on level attention network model |
| CN110909630A (en) * | 2019-11-06 | 2020-03-24 | 腾讯科技（深圳）有限公司 | Abnormal game video detection method and device |
| WO2020078165A1 (en) * | 2018-10-15 | 2020-04-23 | Oppo广东移动通信有限公司 | Video processing method and apparatus, electronic device, and computer-readable medium |
| CN111309632A (en) * | 2020-03-20 | 2020-06-19 | 北京达佳互联信息技术有限公司 | Application program testing method and device, computer equipment and storage medium |
| CN111783644A (en) * | 2020-06-30 | 2020-10-16 | 百度在线网络技术（北京）有限公司 | Detection method, device, equipment and computer storage medium |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9818136B1 (en) * | 2003-02-05 | 2017-11-14 | Steven M. Hoffberg | System and method for determining contingent relevance |
| WO2007049282A2 (en) * | 2005-10-26 | 2007-05-03 | Cortica Ltd. | A computing device, a system and a method for parallel processing of data streams |
| US20120262545A1 (en) * | 2011-04-18 | 2012-10-18 | Paul Kerbiriou | Method for coding and decoding a 3d video signal and corresponding devices |
| US11341235B2 (en) * | 2019-02-21 | 2022-05-24 | Raytheon Company | Anomaly detection with adaptive auto grouping |
| US20210051122A1 (en) * | 2019-08-15 | 2021-02-18 | Rovi Guides, Inc. | Systems and methods for pushing content |
-
2021
- 2021-04-09 CN CN202110385971.2A patent/CN113111200B/en active Active
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2009015422A1 (en) * | 2007-07-30 | 2009-02-05 | Michael Kefaloukos | A computer-implemented security method and system |
| CN101184241A (en) * | 2007-12-03 | 2008-05-21 | 中兴通讯股份有限公司 | Image automatic detection method and apparatus |
| CN101882296A (en) * | 2010-05-07 | 2010-11-10 | 邹阿金 | Method for hiding Chebyshev neural network chaotic digital watermark information |
| CN106101713A (en) * | 2016-07-06 | 2016-11-09 | 武汉大学 | A kind of video steganalysis method based on the calibration of window optimum |
| CN106845242A (en) * | 2016-08-26 | 2017-06-13 | 中国科学院信息工程研究所 | A kind of steganographic detection and extracting method based on IS4 software features |
| WO2018120946A1 (en) * | 2016-12-30 | 2018-07-05 | 广州虎牙信息科技有限公司 | Method and apparatus for determining video image abnormality, and terminal device |
| CN108509775A (en) * | 2018-02-08 | 2018-09-07 | 暨南大学 | A kind of malice PNG image-recognizing methods based on machine learning |
| CN109348211A (en) * | 2018-08-06 | 2019-02-15 | 中国科学院声学研究所 | The general information of interframe encode hides detection method in a kind of video frame |
| WO2020078165A1 (en) * | 2018-10-15 | 2020-04-23 | Oppo广东移动通信有限公司 | Video processing method and apparatus, electronic device, and computer-readable medium |
| CN109817233A (en) * | 2019-01-25 | 2019-05-28 | 清华大学 | Voice flow steganalysis method and system based on level attention network model |
| CN109785848A (en) * | 2019-01-28 | 2019-05-21 | 宁波大学 | The bis- compression audio-frequency detections of AAC based on scale factor coefficient differentials |
| CN110909630A (en) * | 2019-11-06 | 2020-03-24 | 腾讯科技（深圳）有限公司 | Abnormal game video detection method and device |
| CN111309632A (en) * | 2020-03-20 | 2020-06-19 | 北京达佳互联信息技术有限公司 | Application program testing method and device, computer equipment and storage medium |
| CN111783644A (en) * | 2020-06-30 | 2020-10-16 | 百度在线网络技术（北京）有限公司 | Detection method, device, equipment and computer storage medium |
Non-Patent Citations (3)
| Title |
|---|
| 图像信息隐藏检测及其在互联网监管中的应用;曹蓁;李建华;;微型电脑应用;20070320(第03期);全文 * |
| 应用二值图像信息隐藏技术实现彩色图像中的安全隐写;刘春庆;梁光岚;王朔中;张新鹏;;应用科学学报;20070715(第04期);全文 * |
| 数字图像重压缩检测研究综述;王志锋;朱琳;曾春艳;闵秋莎;夏丹;;计算机科学;20180915(第09期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113111200A (en) | 2021-07-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112559800B (en) | Method, apparatus, electronic device, medium and product for processing video | |
| KR102002024B1 (en) | Method for processing labeling of object and object management server | |
| CN112861885A (en) | Image recognition method and device, electronic equipment and storage medium | |
| CN111241496B (en) | Method and device for determining small program feature vector and electronic equipment | |
| CN113111200B (en) | Method, device, electronic equipment and storage medium for auditing picture files | |
| US20130322686A1 (en) | Profiling Activity Through Video Surveillance | |
| CN110888791A (en) | Log processing method, device, equipment and storage medium | |
| CN112214770B (en) | Malicious sample identification method, device, computing equipment and medium | |
| CN110414625B (en) | Method and device for determining similar data, electronic equipment and storage medium | |
| CN111261157A (en) | Control method, device and equipment for short video and storage medium | |
| CN113590447B (en) | Buried point processing method and device | |
| CN113852835A (en) | Live broadcast audio processing method and device, electronic equipment and storage medium | |
| CN115730104A (en) | Live broadcast room processing method, device, equipment and medium | |
| CN108009233B (en) | Image restoration method and device, computer equipment and storage medium | |
| CN113674246B (en) | Method, device, electronic equipment and storage medium for auditing picture files | |
| CN110909798A (en) | Multi-algorithm intelligent studying and judging method, system and server | |
| CN114584616B (en) | Message pushing method and device, electronic equipment and storage medium | |
| CN113408530B (en) | Image identification method, device, equipment and storage medium | |
| CN111967273B (en) | Dialog management system, method and rule engine device | |
| CN113722496B (en) | Triple extraction method and device, readable storage medium and electronic equipment | |
| CN114363627B (en) | Image processing method and device and electronic equipment | |
| CN114821378B (en) | Image auditing method, device, electronic equipment and storage medium | |
| CN111428544B (en) | Scene recognition method and device, electronic equipment and storage medium | |
| CN110674839B (en) | Abnormal user identification method and device, storage medium and electronic equipment | |
| CN113641885A (en) | Document detection 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 |