CN111064977B - Method, system and readable storage medium for online monitoring of network integrated art program record - Google Patents
Method, system and readable storage medium for online monitoring of network integrated art program record Download PDFInfo
- Publication number
- CN111064977B CN111064977B CN201911236486.8A CN201911236486A CN111064977B CN 111064977 B CN111064977 B CN 111064977B CN 201911236486 A CN201911236486 A CN 201911236486A CN 111064977 B CN111064977 B CN 111064977B
- Authority
- CN
- China
- Prior art keywords
- binarization
- verification
- character recognition
- module
- character
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
- H04N21/234—Processing of video elementary streams, e.g. splicing of video streams, manipulating MPEG-4 scene graphs
- H04N21/23418—Processing of video elementary streams, e.g. splicing of video streams, manipulating MPEG-4 scene graphs involving operations for analysing video streams, e.g. detecting features or characteristics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
- G06V20/635—Overlay text, e.g. embedded captions in a TV program
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
- H04N21/235—Processing of additional data, e.g. scrambling of additional data or processing content descriptors
Abstract
The invention discloses a method, a system and a readable storage medium for online monitoring of network integrated art program record, wherein the method comprises the following steps: a frame extraction step: performing frame extraction processing on the video; character cutting: cutting each frame picture to obtain a character part; character recognition: performing character recognition on the picture; a checking step: checking the recognized characters to obtain a checking result; further preferably, the method further comprises: before the character recognition step is executed, a binarization step is executed; or, when the verification step determines that the verification result is that the verification is not passed, the binarization step is started, and then the character recognition step and the verification step are executed again, so that the video resource can be monitored on the line, and the scheme of the invention can be deployed on a client server, so that the data protection is better; moreover, a dictionary base is not required to be maintained, and the storage capacity is small.
Description
Technical Field
The invention relates to the field of network video supervision, in particular to a method and a system for online monitoring of network comprehensive art program filing and a readable storage medium.
Background
With the increasing popularity of networking, people browse more and more videos and video producers more and more everyday. However, the quality of massive videos is uneven, and especially for various large and short video network platforms, a large number of videos and users appear in order to seek benefits and attract traffic. Therefore, in order to prevent the poor video transmission, a video filing system is introduced in the state at present, but some videos which are not filed are still transmitted in a network, and how to effectively solve the problems of video supervision and the like of a video network platform is a technical problem which needs to be solved urgently by technical personnel in the field at present.
Disclosure of Invention
The technical problem to be solved by the present invention is to provide a method, a system and a readable storage medium for online monitoring of network integrated process program records, aiming at the above-mentioned defects of the prior art.
The technical scheme adopted by the invention for solving the technical problems is as follows:
in one aspect, a method for online monitoring of network integrated art program filing is constructed, the method comprising:
a frame extraction step: performing frame extraction processing on the video;
character cutting: cutting each frame picture to obtain a character part;
character recognition: performing character recognition on the picture;
a checking step: and checking the recognized characters to obtain a checking result.
Preferably, the method further comprises: before the character recognition step is executed, a binarization step is executed; or, starting the binarization step when the verification result is determined to be not passed through the verification in the verification step, and then executing the character recognition step and the verification step again;
the binarization step comprises the following steps: and carrying out binarization processing on the cut character parts.
Preferably, the binarization processing includes: performing parallel processing on the cut character part by adopting two binarization modes to obtain two binarization pictures;
the character recognition step is used for parallelly carrying out character recognition on the two binary images;
in the verification step, the identification characters of the two binary images are verified in parallel, and if the two verifications are passed, the identification characters of the two binary images are returned as record numbers; if both the two verifications fail, returning the result that the verification fails; and if one check passes and the other check does not pass, returning the identification characters of the binary image passing the check as a record number.
Preferably, the first binarization processing method of the two binarization methods is: changing the picture into a grey-scale image; calculating the sum totalSum of the pixel values of all the pixel points; finding a pixel value thread, wherein the sum of all pixel values smaller than thread is smaller than totalSum, wherein b represents a preset threshold value; then, the found thread is used as a threshold value of binaryzation to carry out binaryzation on the gray level picture;
preferably, the second binarization processing method of the two binarization methods is: and forming a circular area by taking the common pixels in the record number as the circle center and the preset pixel distance as the radius, wherein the pixels fall in the circular area to serve as one part, and the pixels fall out of the circular area to serve as the other part, so that all the pixels of the whole picture are divided into two parts.
Preferably, the checking the recognized text includes: counting the number of the recognized characters, and if the counted number of the characters does not meet the requirement of the number of the characters, judging that the verification is not passed; if the requirement of the number of the numbers is met, the correctness of the recognized characters is judged according to the record number rule, if the recognized characters are correct, the verification is judged to be passed, the recognized characters are used as record numbers, and if the recognized characters are incorrect, the verification is judged not to be passed.
In another aspect, a system for online monitoring of network integrated art program records is constructed, the system comprising:
the frame extracting module is used for carrying out frame extracting processing on the video;
the character cutting module is used for cutting each frame of picture to obtain a character part;
the character recognition module is used for carrying out character recognition on the picture;
and the checking module is used for checking the recognized characters to obtain a checking result.
Preferably, the system further comprises a binarization module, configured to perform binarization processing on the cut text portions;
the picture cut by the character cutting module is sent to a binarization module for binarization processing, and then sent to a character recognition module for character recognition; or starting the binarization module when the verification module determines that the verification result is that the verification is not passed, and then starting the character recognition module and the verification module again.
In three aspects, a system for online monitoring of network art program filing is constructed, comprising a processor and a memory, the memory storing a computer program which, when executed by the processor, performs the steps of the method as claimed in any one of the preceding claims.
In a fourth aspect, a computer-readable storage medium is provided, in which a computer program is stored, which computer program, when being executed by a processor, carries out the steps of the method according to any of the preceding claims.
The method, the system and the readable storage medium for online monitoring of the network comprehensive art program record have the following advantages that: the invention obtains the check result by performing frame extraction processing, character cutting, character recognition and check on the video, can realize online monitoring of video resources, and the scheme of the invention can be deployed on a client server, and has better data protection; moreover, a dictionary base is not required to be maintained, and the storage capacity is small.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts:
FIG. 1 is a flow chart of a method for online monitoring of network integrated process program records according to the present invention;
FIG. 2 is a flowchart of an embodiment of a method for online monitoring of network integrated process program records according to the present invention;
FIG. 3 is a block diagram of the online monitoring system for network integrated art program recording of the present invention.
Detailed Description
To facilitate an understanding of the invention, the invention will now be described more fully with reference to the accompanying drawings. Exemplary embodiments of the invention are shown in the drawings. This invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items.
Referring to fig. 1, the general idea of the present invention is: constructing a method, a system and a readable storage medium for online monitoring of network integrated art program records, taking the method as an example, firstly executing a frame extraction step S101 to perform frame extraction processing on a video; then, executing a character cutting step, cutting each frame of picture to obtain a character part; and then, executing a character recognition step to perform character recognition on the picture, and finally executing a verification step to verify the recognized characters to obtain a verification result.
Preferably, a binarization step may be performed before the text recognition step is performed. The binarization step comprises the following steps: and carrying out binarization processing on the cut character parts.
Preferably, the binarization step can be started when the verification step determines that the verification result is not passed, and then the character recognition step and the verification step are executed again. Similarly, the binarization step comprises the following steps: and carrying out binarization processing on the cut character parts.
In order to better understand the technical solutions, the technical solutions will be described in detail below with reference to the drawings and the specific embodiments of the specification, and it should be understood that the embodiments and specific features of the embodiments of the present invention are detailed descriptions of the technical solutions of the present application, and are not limited to the technical solutions of the present application, and the technical features of the embodiments and examples of the present invention may be combined with each other without conflict.
Example one
Referring to fig. 2, the method for online monitoring of network integrated process program filing of the present embodiment may be implemented on a server side, and the specific implementation code may run on a centros or an ubuntu. In the embodiment, the whole process is carried out in two stages, the first stage carries out direct detection on the route 1 after the character picture is obtained, the problem that some foreground and background are clear is solved, and if the corresponding record number cannot be detected through direct detection, the route 2 is carried out, namely, detection is carried out after binarization. Of course, it is understood that in other embodiments, only route 1 or route 2 may exist, which is a simple variation of this embodiment and is within the scope of the present invention.
Specifically, the method of the embodiment includes:
a frame extraction step S201: performing frame extraction processing on the video;
the original picture obtained by frame extraction is an RGB picture, and general record numbers have specific positions, so that an interested area (the interested area can be defined according to the common record number positions in advance) can be cut out as the input of the next step according to the requirement.
Character clipping step S202: cutting each frame picture to obtain a character part;
specifically, text detection can be performed on the obtained region of interest by using an EAST model to determine a text region, then the input picture is cut according to the detected text region, and the picture only containing text is reserved, that is, only the text region is reserved.
Character recognition step S203: performing character recognition on the picture;
for example, the corresponding Chinese and English packet of tesseract may be called to detect the text, and a white list is set during the calling, and is formulated according to the record number rule. For example, according to the current record number rule for network video in china, the record number generally includes the year, some of which is headed by V or V, and some of which is not. Therefore, the white list can be set as numbers or V, v, etc., so that only characters containing the numbers and the assigned letters are detected, and the rest characters cannot be detected, thereby facilitating the subsequent verification.
A verification step S204: and checking the recognized characters to obtain a checking result.
Specifically, the checking the recognized text includes: counting the number of the recognized characters, and if the counted number of the characters does not meet the requirement of the number of the characters (for example, the number of the characters is more than 5, so that the misjudgment of the year is avoided), judging that the verification is not passed; if the requirement of the number of the digits is met, judging the correctness of the recognized characters according to the record number rule (for example, if the recognized characters start with V or V, the recognized characters must meet 17 bits, if the recognized characters do not start with V or V, the recognized characters must be between 15 bits and 16 bits), if the recognized characters are correct, judging that the verification is passed, using the recognized characters as the record number, and if the recognized characters are incorrect, judging that the verification is not passed.
Executing the above S201-S204 corresponds to the completion of the execution of the route 1, and if it is determined in S204 that the verification does not pass, the present embodiment starts the route 2, and executes the binarization step S205: and carrying out binarization processing on the cut character parts. After S205 is completed, S203 and S204 are executed again.
Specifically, the binarization processing of step S205 of the present embodiment includes: and (4) performing parallel processing on the cut character part by adopting two binarization modes to obtain two binarization pictures. Accordingly, the character recognition step S203 needs to perform character recognition on the two binarized pictures in parallel. Correspondingly, in the verification step, in step S205, the identification characters of the two binary images need to be verified in parallel, and if both the two verifications fail, a result that the verification fails is returned; if one check passes and the other check does not pass, returning the identification characters of the binary image passing the check as a record number; if the two verifications are passed, the identification characters of the two binary images are returned as record numbers, if the identification characters of the two binary images are completely consistent, the identification characters of the two binary images are returned to any one of the two binary images, and if the identification characters of the two binary images are not consistent, the two identification characters are returned for reference.
Specifically, the first binarization processing method of the two binarization methods of this embodiment is: changing the picture into a grey-scale image; calculating the sum totalSum of the pixel values of all the pixel points; finding a pixel value thread, wherein the sum of all pixel values smaller than thread is smaller than totalSum, where b represents a preset threshold, for example, b may be set to 60% -70%; and then carrying out binarization on the gray level picture by taking the found thread as a binarization threshold value.
Specifically, the second binarization processing method of the two binarization methods of this embodiment is: the method includes the steps that common pixels in record numbers (for example, most record numbers of the Emblem, mango and Tencent video screen are in white characters, so that the common pixels can be selected as white pixels) serve as circle centers, a circular area is formed by taking a preset pixel distance as a radius, the pixels fall in the circular area to serve as one part, and the pixels fall outside the circular area to serve as the other part, so that all pixels of the whole picture are divided into two parts.
It will be appreciated that code implementing the above method may be deployed on a client server. It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above.
Therefore, the embodiment obtains the verification result by performing frame extraction processing, character cutting, character recognition and verification on the video, can realize online monitoring on video resources, and can be deployed on a client server to achieve better data protection; moreover, a dictionary base is not required to be maintained, and the storage capacity is small.
Example two
Based on the same inventive concept, referring to fig. 3, the present embodiment discloses a system for online monitoring of network integrated process program filing, which includes:
a frame extracting module 301, configured to perform frame extracting processing on a video;
a character clipping module 302, configured to clip each frame of picture to obtain a character portion;
the character recognition module 303 is used for performing character recognition on the picture;
and the checking module 304 is configured to check the identified characters to obtain a checking result.
Preferably, the system further comprises a binarization module 305 for performing binarization processing on the cut-out text part. Specifically, there are two ways the text cropping module 302 is enabled.
The first starting mode is as follows: the character clipping module 302 is triggered to start, that is, the clipped picture is sent to the binarization module 305 for binarization processing, and then sent to the character recognition module 303 for character recognition, which is equivalent to that the whole system starts the frame extracting module 301, the character clipping module 302, the binarization module 305, the character recognition module 303, and the verification module 304 in sequence.
The second starting mode is as follows: if the check module 304 determines that the check result is that the check result does not pass, the binarization module 304 is started, and then the character recognition module 303 and the check module 305 are started again, that is, the whole system firstly starts the frame extraction module 301, the character clipping module 302, the character recognition module 303 and the check module 304 in sequence, which corresponds to the path 1 in the method embodiment, and if the check module 304 does not pass, then starts the binarization module 305, then starts the character recognition module 303 and the check module 304 again, which corresponds to the path 2 in the method embodiment.
The functions of the functional modules in the embodiments of the present invention may be specifically implemented according to the method in the above method embodiments, and the specific implementation process may refer to the related description of the above method embodiments, which is not described herein again.
The above description relates to various modules. These modules typically include hardware and/or a combination of hardware and software. The modules may also include computer-readable media containing instructions that, when executed by a processor, perform various functional features of the present invention. Accordingly, the scope of the invention is not limited by the specific hardware and/or software characteristics of the modules explicitly mentioned in the embodiments, unless explicitly claimed. As a non-limiting example, the present invention may in embodiments be implemented by one or more processors executing software instructions. It should be noted that the above description of the various modules is divided into these modules for clarity of illustration. However, in actual implementation, the boundaries of the various modules may be fuzzy. For example, any or all of the functional modules herein may share various hardware and/or software elements. Also for example, any and/or all of the functional modules herein may be implemented in whole or in part by a common processor executing software instructions. Additionally, various software sub-modules executed by one or more processors may be shared among the various software modules. Accordingly, the scope of the present invention is not limited by the mandatory boundaries between the various hardware and/or software elements, unless explicitly claimed otherwise.
EXAMPLE III
Based on the same inventive concept, this embodiment discloses a system for online monitoring of network integrated process program filing, which is characterized by comprising a processor and a memory, where the memory stores a computer program, and the computer program is executed by the processor to implement the steps of the method according to the first embodiment.
Example four
Based on the same inventive concept, this embodiment discloses a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the steps of the method according to the first embodiment are implemented, and the specific implementation process may refer to the related description of the above method embodiments, and will not be described herein again.
While the present invention has been described with reference to the embodiments shown in the drawings, the present invention is not limited to the embodiments, which are illustrative and not restrictive, and it will be apparent to those skilled in the art that various changes and modifications can be made therein without departing from the spirit and scope of the invention as defined in the appended claims.
Claims (5)
1. A method for online monitoring of network integrated process program filing is characterized by comprising the following steps:
a frame extraction step: performing frame extraction processing on the video;
character cutting: cutting each frame picture to obtain a character part;
character recognition: performing character recognition on the picture;
a checking step: checking the recognized characters to obtain a checking result;
before the character recognition step is executed, a binarization step is executed; or, starting the binarization step when the verification result is determined to be not passed through the verification in the verification step, and then executing the character recognition step and the verification step again;
the binarization step comprises the following steps: carrying out binarization processing on the cut character part;
the binarization processing comprises the following steps: performing parallel processing on the cut character part by adopting two binarization modes to obtain two binarization pictures;
the character recognition step is used for parallelly carrying out character recognition on the two binary images;
in the verification step, the identification characters of the two binary images are verified in parallel, and if the two verifications are passed, the identification characters of the two binary images are returned as record numbers; if both the two verifications fail, returning the result that the verification fails; if one check passes and the other check does not pass, returning the identification characters of the binary image passing the check as a record number;
the first binarization processing mode of the two binarization modes is as follows: changing the picture into a grey-scale image; calculating the sum totalSum of the pixel values of all the pixel points; finding a pixel value thread, wherein the sum of all pixel values smaller than thread is smaller than totalSum, wherein b represents a preset threshold value; then, the found thread is used as a threshold value of binaryzation to carry out binaryzation on the gray level picture;
the second binarization processing mode of the two binarization modes is as follows: and forming a circular area by taking the common pixels in the record number as the circle center and the preset pixel distance as the radius, wherein the pixels fall in the circular area to serve as one part, and the pixels fall out of the circular area to serve as the other part, so that all the pixels of the whole picture are divided into two parts.
2. The method of claim 1, wherein verifying the recognized text comprises: counting the number of the recognized characters, and if the counted number of the characters does not meet the requirement of the number of the characters, judging that the verification is not passed; if the requirement of the number of the numbers is met, the correctness of the recognized characters is judged according to the record number rule, if the recognized characters are correct, the verification is judged to be passed, the recognized characters are used as record numbers, and if the recognized characters are incorrect, the verification is judged not to be passed.
3. A system for online monitoring of network integrated art program records is characterized by comprising:
the frame extracting module is used for carrying out frame extracting processing on the video;
the character cutting module is used for cutting each frame of picture to obtain a character part;
the character recognition module is used for carrying out character recognition on the picture;
the verification module is used for verifying the recognized characters to obtain a verification result; the binarization module is used for carrying out binarization processing on the cut character parts;
the picture cut by the character cutting module is sent to a binarization module for binarization processing, and then sent to a character recognition module for character recognition; or, starting the binarization module when the verification module determines that the verification result is that the verification is not passed, and then starting the character recognition module and the verification module again;
the binarization processing comprises the following steps: performing parallel processing on the cut character part by adopting two binarization modes to obtain two binarization pictures;
the character recognition module performs character recognition on the two binary images in parallel;
the verification module is used for verifying the identification characters of the two binary images in parallel, and if the two verifications are passed, the identification characters of the two binary images are returned as record numbers; if both the two verifications fail, returning the result that the verification fails; if one check passes and the other check does not pass, returning the identification characters of the binary image passing the check as a record number;
the first binarization processing mode of the two binarization modes is as follows: changing the picture into a grey-scale image; calculating the sum totalSum of the pixel values of all the pixel points; finding a pixel value thread, wherein the sum of all pixel values smaller than thread is smaller than totalSum, wherein b represents a preset threshold value; then, the found thread is used as a threshold value of binaryzation to carry out binaryzation on the gray level picture;
the second binarization processing mode of the two binarization modes is as follows: and forming a circular area by taking the common pixels in the record number as the circle center and the preset pixel distance as the radius, wherein the pixels fall in the circular area to serve as one part, and the pixels fall out of the circular area to serve as the other part, so that all the pixels of the whole picture are divided into two parts.
4. A system for online monitoring of network art program filing comprising a processor and a memory, the memory storing a computer program which, when executed by the processor, carries out the steps of the method according to any one of claims 1-2.
5. A computer-readable storage medium, characterized in that a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1-2.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911236486.8A CN111064977B (en) | 2019-12-05 | 2019-12-05 | Method, system and readable storage medium for online monitoring of network integrated art program record |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911236486.8A CN111064977B (en) | 2019-12-05 | 2019-12-05 | Method, system and readable storage medium for online monitoring of network integrated art program record |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111064977A CN111064977A (en) | 2020-04-24 |
| CN111064977B true CN111064977B (en) | 2021-12-03 |
Family
ID=70300055
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911236486.8A Active CN111064977B (en) | 2019-12-05 | 2019-12-05 | Method, system and readable storage medium for online monitoring of network integrated art program record |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111064977B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112019925B (en) * | 2020-10-29 | 2021-01-22 | 蘑菇车联信息科技有限公司 | Video watermark identification processing method and device |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6470094B1 (en) * | 2000-03-14 | 2002-10-22 | Intel Corporation | Generalized text localization in images |
| CN104978565B (en) * | 2015-05-11 | 2019-06-28 | 厦门翼歌软件科技有限公司 | A kind of pictograph extracting method of universality |
| CN107862258A (en) * | 2017-10-24 | 2018-03-30 | 广东小天才科技有限公司 | Method of calibration, device, equipment and the storage medium of video Chinese version content |
| CN109635628A (en) * | 2018-10-23 | 2019-04-16 | 深圳壹账通智能科技有限公司 | ID card information verification method, device, equipment and computer readable storage medium |
| CN109901968A (en) * | 2019-01-31 | 2019-06-18 | 阿里巴巴集团控股有限公司 | A kind of automation page data method of calibration and device |
-
2019
- 2019-12-05 CN CN201911236486.8A patent/CN111064977B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN111064977A (en) | 2020-04-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8607331B2 (en) | Captcha image authentication method and system | |
| CN105704005B (en) | Malicious user reporting method and device, and reported information processing method and device | |
| CN107368827B (en) | Character recognition method and device, user equipment and server | |
| CN112861648B (en) | Character recognition method, character recognition device, electronic equipment and storage medium | |
| US10282627B2 (en) | Method and apparatus for processing handwriting data | |
| CN108366052B (en) | Processing method and system for verification short message | |
| CN111064977B (en) | Method, system and readable storage medium for online monitoring of network integrated art program record | |
| CN115018565A (en) | Advertisement media image identification method, system, equipment and readable storage medium | |
| CN111860590A (en) | License plate voting method and device, computer equipment and storage medium | |
| CN110533020B (en) | Character information identification method and device and storage medium | |
| WO2023272991A1 (en) | Data processing method and apparatus, computer device, and storage medium | |
| CN113792661A (en) | Image detection method, image detection device, electronic equipment and storage medium | |
| CN113792662A (en) | Image detection method, image detection device, electronic equipment and storage medium | |
| CN113568934A (en) | Data query method and device, electronic equipment and storage medium | |
| CN111539206A (en) | Method, device and equipment for determining sensitive information and storage medium | |
| CN112712394A (en) | Client thread sharing method, system, computer and readable storage medium | |
| CN112132794A (en) | Text positioning method, device and equipment for audit video and readable storage medium | |
| CN112749696A (en) | Text detection method and device | |
| CN113705666B (en) | Split network training method, use method, device, equipment and storage medium | |
| CN114743205A (en) | Image tampering detection method and device | |
| CN113515670A (en) | Method, device and storage medium for identifying state of movie and television resource | |
| CN115730104A (en) | Live broadcast room processing method, device, equipment and medium | |
| CN111343105A (en) | Cutoff identification method and device based on deep learning | |
| CN108446695B (en) | Method and device for data annotation and electronic equipment | |
| CN106293348B (en) | Information interaction method and device applied to new media |
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 |