CN110213656A - A kind of IPTV content tampering kind identification method and system based on the comparison of picture portion domain - Google Patents

A kind of IPTV content tampering kind identification method and system based on the comparison of picture portion domain Download PDF

Info

Publication number
CN110213656A
CN110213656A CN201910521919.8A CN201910521919A CN110213656A CN 110213656 A CN110213656 A CN 110213656A CN 201910521919 A CN201910521919 A CN 201910521919A CN 110213656 A CN110213656 A CN 110213656A
Authority
CN
China
Prior art keywords
image
comparison
iptv
picture portion
program
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.)
Pending
Application number
CN201910521919.8A
Other languages
Chinese (zh)
Inventor
杨明生
谢恩鹏
张宇
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shandong Yunman Intelligent Technology Co Ltd
Original Assignee
Shandong Yunman Intelligent Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shandong Yunman Intelligent Technology Co Ltd filed Critical Shandong Yunman Intelligent Technology Co Ltd
Priority to CN201910521919.8A priority Critical patent/CN110213656A/en
Publication of CN110213656A publication Critical patent/CN110213656A/en
Pending legal-status Critical Current

Links

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N17/00Diagnosis, testing or measuring for television systems or their details
    • H04N17/004Diagnosis, testing or measuring for television systems or their details for digital television systems
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/43Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
    • H04N21/442Monitoring of processes or resources, e.g. detecting the failure of a recording device, monitoring the downstream bandwidth, the number of times a movie has been viewed, the storage space available from the internal hard disk
    • H04N21/44204Monitoring of content usage, e.g. the number of times a movie has been viewed, copied or the amount which has been watched
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/43Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
    • H04N21/442Monitoring of processes or resources, e.g. detecting the failure of a recording device, monitoring the downstream bandwidth, the number of times a movie has been viewed, the storage space available from the internal hard disk
    • H04N21/4425Monitoring of client processing errors or hardware failure

Landscapes

  • Engineering & Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • General Health & Medical Sciences (AREA)
  • Television Systems (AREA)
  • Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)

Abstract

The invention discloses a kind of IPTV content tampering kind identification methods and system based on the comparison of picture portion domain, belong to IPTV monitoring technical field.IPTV content tampering kind identification method based on the comparison of picture portion domain of the invention, comprising the following steps: S1, make to take out frame processing for the program of integrated broadcasting centre, generate image;S2, the program of IPTV user is made to take out frame processing, generates image;S3, the image of step S1 is divided into region, calculates reference zone characteristic value using mean value hash algorithm subregion;S4, the picture portion domain by step S2 use mean value hash algorithm subregion zoning characteristic value.The IPTV content tampering kind identification method based on the comparison of picture portion domain of the invention is to the program for having been determined as content tampering, it is compared based on picture portion domain, can intelligent recognition its content tampering type, logo is distorted, subtitle is distorted, and has good application value.

Description

It is a kind of based on picture portion domain comparison IPTV content tampering kind identification method and System
Technical field
The present invention relates to IPTV monitoring technical fields, specifically provide it is a kind of based on picture portion domain comparison IPTV content usurp Change kind identification method and system.
Background technique
Video data itself is made of picture one by one, and tool (such as ffmepg) can be used to extract these pictures Out, this process is called pumping frame.
The programming source of IPTV operator (hereinafter referred to as: operator) is in integrated Broadcast Control platform.Operator distorts sometimes Program data, such as modification logo, addition subtitle, addition advertising segment etc., eventually lead to the program that IPTV terminal user sees It is inconsistent with original program.TV programme logo is normally at top left region, and program credits are located at lower area.Therefore can pass through It is inconsistent to compare any block region in video, to infer the type of content tampering.There is special related software monitoring is such to usurp to this Change.
But common inspection software can only find, report and distort problem in violation of rules and regulations, be related to violation type and then need manually to examine It reads.
Summary of the invention
Technical assignment of the invention is in view of the above problems, to provide a kind of for the section for having been determined as content tampering Mesh is compared based on picture portion domain, can intelligent recognition its content tampering type, logo is distorted, subtitle is distorted based on image The IPTV content tampering kind identification method of subregion comparison.
The further technical assignment of the present invention is to provide a kind of IPTV content tampering type based on the comparison of picture portion domain Identifying system.
To achieve the above object, the present invention provides the following technical scheme that
A kind of IPTV content tampering kind identification method based on the comparison of picture portion domain, method includes the following steps:
S1, the program of integrated broadcasting centre is made to take out frame processing, generates image;
S2, the program of IPTV user is made to take out frame processing, generates image;
S3, the image of step S1 is divided into region, calculates reference zone characteristic value using mean value hash algorithm subregion;
S4, the picture portion domain by step S2 use mean value hash algorithm subregion zoning characteristic value;
The regional characteristic value in reference zone characteristic value and step S4 in S5, comparison step S3 determines that specified region is No matching is consistent;
If S6, logo region are inconsistent, distort for logo, if caption area is inconsistent, is distorted for subtitle.
The program data of IPTV operator derives from integrated broadcasting centre, and the program data of IPTV operator is sent to IPTV User therefore can be using the program of integrated broadcasting centre as reference data, by the program of IPTV user with comparing.
Preferably, the IPTV content tampering kind identification method that should be compared based on picture portion domain further includes walking as follows It is rapid:
S7, the image whole region of step S2 and blank screen characteristic value are compared, if multiple continuous images match, for blank screen Failure.
Preferably, the IPTV content tampering kind identification method that should be compared based on picture portion domain further includes walking as follows It is rapid:
S8, by the image adjacent contrast of continuous multiple step S2, if continuous coupling, for still frame failure.
Preferably, integrated broadcasting centre of the programming source of IPTV user in step S1 in the step S2.
Preferably, the image that step S1, step S2 are obtained, carries out compression processing to picture, and carry out gray proces.
Since the image pixel for taking out frame is higher, to reduce calculation amount when image comparison, can first compressed picture, and do image Gray proces.
A kind of IPTV content tampering identification system based on the comparison of picture portion domain, the system comprise the following modules:
Image generation module: for being used as the program of integrated broadcasting centre to take out frame processing generation image and be used for IPTV The program at family is made to take out frame processing generation image;
Regional characteristic value computing module: reference zone characteristic value is calculated for subregion and for subregion zoning spy Value indicative;
Distort type judging module: for being distorted to be determined as logo according to reference zone characteristic value and regional characteristic value Or subtitle is distorted.
In image generation module, the program of integrated broadcasting centre is made to take out frame processing, generates image;By the section of IPTV user Mesh is made to take out frame processing, generates image.Since the image pixel for taking out frame is higher, to reduce calculation amount when image comparison, can first press Contract drawing piece, and do image grayscale processing.
In regional characteristic value computing module, the program of integrated broadcasting centre is made to the image dividing regions for taking out frame processing generation Domain, subregion calculate reference zone characteristic value;The program of IPTV user is made into the picture portion domain that pumping frame processing generates, subregion Zoning characteristic value.
Distort in type judging module, compare reference zone characteristic value and regional characteristic value, determine specified region whether With consistent;If logo region is inconsistent, distort for logo, if caption area is inconsistent, is distorted for subtitle.
Preferably, the IPTV content tampering identification system that should be compared based on picture portion domain further includes with lower die Block:
Fault type judgment module: the image conditions that obtain for the program according to IPTV user are judged as black screen trouble Or still frame failure.
IPTV user's program video whole region and blank screen characteristic value are compared, if multiple continuous images match, are black Shield failure.
By the image adjacent contrast of continuous multiple IPTV user's programs, if continuous coupling, for still frame failure.
It generates image preferably, image generation module is used to make the program of integrated broadcasting centre to take out frame processing and is used for The program of IPTV user is made after taking out frame processing generation image, compression processing is carried out to picture, and carry out gray proces.
Compared with prior art, the IPTV content tampering kind identification method tool of the invention based on the comparison of picture portion domain Have following prominent the utility model has the advantages that the IPTV content tampering kind identification method based on the comparison of picture portion domain can be directed to Have been determined as the program of content tampering, compared based on picture portion domain, can the type of intelligent recognition its content tampering usurped for logo Change or subtitle is distorted, may recognize that failure is black screen trouble or still frame failure, do not need manual reviews' violation type, have There is good application value.
Detailed description of the invention
Fig. 1 is the flow chart of the IPTV content tampering kind identification method of the present invention based on the comparison of picture portion domain.
Specific embodiment
Below in conjunction with drawings and examples, to the IPTV content tampering type of the invention based on the comparison of picture portion domain Recognition methods and system are described in further detail.
Embodiment
As shown in Figure 1, the IPTV content tampering kind identification method of the invention based on the comparison of picture portion domain, specific to wrap Include following steps:
S1, the program of integrated broadcasting centre is made to take out frame processing, generates image.
S2, the program of IPTV user is made to take out frame processing, generates image.
Integrated broadcasting centre of the programming source of the IPTV user of the step in step S1.
The program data of IPTV operator derives from integrated broadcasting centre, and the program data of IPTV operator is sent to IPTV User therefore can be using the program of integrated broadcasting centre as reference data, by the program of IPTV user with comparing.
Since the image pixel for taking out frame is higher, to reduce calculation amount when image comparison, can first compressed picture, and do image Gray proces.
S3, the image of step S1 is divided into region, calculates reference zone characteristic value using mean value hash algorithm subregion.
S4, the picture portion domain by step S2 use mean value hash algorithm subregion zoning characteristic value.
The regional characteristic value in reference zone characteristic value and step S4 in S5, comparison step S3 determines that specified region is No matching is consistent.
If S6, logo region are inconsistent, distort for logo, if caption area is inconsistent, is distorted for subtitle.
S7, the image whole region of step S2 and blank screen characteristic value are compared, if multiple continuous images match, for blank screen Failure.
S8, by the image adjacent contrast of continuous multiple step S2, if continuous coupling, for still frame failure.
Specific implementation process is as follows:
1) integrated broadcasting centre, IPTV terminal program are taken out into frame processing, generates image.
2) by compression of images to specified pixel (tentative 128*128), gray proces then are made to image.
3) gray level image of 128*128 is divided into different regions, such as lower area (128*20), central area (50* 50), top left region (30*30), whole region (128*128) etc. calculate characteristic value using mean value hash algorithm.
4) integrated Broadcast Control platform image and IPTV terminal image area characteristics value are compared using Hamming distance, distance is more than threshold Value (fix tentatively is 4) then thinks that the region is inconsistent.
5) determine content tampering type according to regional correlation situation: upper left, right regions are inconsistent, then it is assumed that logo is different It causes;Lower part is inconsistent, then it is assumed that is that subtitle is distorted.
A1 mean value hash:
10101010101010010010010101001010101100101010101001010101010100101000 101010101001010101010
A2 mean value hash:
01010011010010101010100101001010101011001010101010101010101010010101 010101010101010010101
A1, A2 Hamming distance are more than threshold value, it is believed that the region A1, A2 is inconsistent, is determined as that logo is inconsistent according to rule.
6) comparison IPTV terminal image whole region and regional characteristic value when blank screen, if multiple continuous images match are black Shield characteristic value, then it is assumed that black screen trouble.
7) the whole region characteristic value of multiple continuous images of comparison IPTV terminal, if continuous multiple frames Self Matching, then it is assumed that It is still frame failure.
IPTV content tampering identification system based on the comparison of picture portion domain of the invention, which includes with lower die Block:
Image generation module: for being used as the program of integrated broadcasting centre to take out frame processing generation image and be used for IPTV The program at family is made to take out frame processing generation image.
The program of integrated broadcasting centre is made to take out frame processing, generates image;The program of IPTV user is made to take out frame processing, it is raw At image.Since the image pixel for taking out frame is higher, to reduce calculation amount when image comparison, can first compressed picture, and do image Gray proces.
Regional characteristic value computing module: reference zone characteristic value is calculated for subregion and for subregion zoning spy Value indicative.
The image that the program of integrated broadcasting centre makees to take out frame processing generation is divided into region, it is special that subregion calculates reference zone Value indicative;The program of IPTV user is made into the picture portion domain that pumping frame processing generates, subregion zoning characteristic value.
Distort type judging module: for being distorted to be determined as logo according to reference zone characteristic value and regional characteristic value Or subtitle is distorted.Reference zone characteristic value and regional characteristic value are compared, determines whether specified region matches unanimously;If logo region It is inconsistent, then it distorts for logo, if caption area is inconsistent, is distorted for subtitle.
Fault type judgment module: the image conditions that obtain for the program according to IPTV user are judged as black screen trouble Or still frame failure.IPTV user's program video whole region and blank screen characteristic value are compared, if multiple continuous images match, for Black screen trouble.
By the image adjacent contrast of continuous multiple IPTV user's programs, if continuous coupling, for still frame failure.
Embodiment described above, the only present invention more preferably specific embodiment, those skilled in the art is at this The usual variations and alternatives carried out within the scope of inventive technique scheme should be all included within the scope of the present invention.

Claims (8)

1. a kind of IPTV content tampering kind identification method based on the comparison of picture portion domain, it is characterised in that: this method includes Following steps:
S1, the program of integrated broadcasting centre is made to take out frame processing, generates image;
S2, the program of IPTV user is made to take out frame processing, generates image;
S3, the image of step S1 is divided into region, calculates reference zone characteristic value using mean value hash algorithm subregion;
S4, the picture portion domain by step S2 use mean value hash algorithm subregion zoning characteristic value;
The regional characteristic value in reference zone characteristic value and step S4 in S5, comparison step S3, determine specified region whether With consistent;
If S6, logo region are inconsistent, distort for logo, if caption area is inconsistent, is distorted for subtitle.
2. the IPTV content tampering kind identification method according to claim 1 based on the comparison of picture portion domain, feature It is: further includes following steps:
S7, the image whole region of step S2 and blank screen characteristic value are compared, if multiple continuous images match, for blank screen event Barrier.
3. the IPTV content tampering kind identification method according to claim 2 based on the comparison of picture portion domain, feature It is: further includes following steps:
S8, by the image adjacent contrast of continuous multiple step S2, if continuous coupling, for still frame failure.
4. the IPTV content tampering kind identification method according to claim 1,2 or 3 based on the comparison of picture portion domain, It is characterized in that: integrated broadcasting centre of the programming source of IPTV user in step S1 in step S2.
5. the IPTV content tampering kind identification method according to claim 4 based on the comparison of picture portion domain, feature Be: the step S1, image that step S2 is obtained carries out compression processing to picture, and carries out gray proces.
6. a kind of IPTV content tampering identification system based on the comparison of picture portion domain, it is characterised in that: including with lower die Block:
Image generation module: it frame processing generation image and is used for IPTV user's for the program of integrated broadcasting centre work to be smoked Program is made to take out frame processing generation image;
Regional characteristic value computing module: reference zone characteristic value is calculated for subregion and is used for subregion zoning feature Value;
It distorts type judging module: for according to reference zone characteristic value and regional characteristic value, being distorted or word to be determined as logo Curtain is distorted.
7. the IPTV content tampering identification system according to claim 6 based on the comparison of picture portion domain, feature It is: further includes with lower module:
Fault type judgment module: the image conditions obtained for the program according to IPTV user are judged as black screen trouble or quiet Frame failure.
8. the IPTV content tampering identification system according to claim 6 or 7 based on the comparison of picture portion domain, special Sign is: image generation module is used to make the program of integrated broadcasting centre to take out frame processing and generates image and be used for IPTV user Program make to take out after frame processing generates image, compression processing is carried out to picture, and carries out gray proces.
CN201910521919.8A 2019-06-17 2019-06-17 A kind of IPTV content tampering kind identification method and system based on the comparison of picture portion domain Pending CN110213656A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910521919.8A CN110213656A (en) 2019-06-17 2019-06-17 A kind of IPTV content tampering kind identification method and system based on the comparison of picture portion domain

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910521919.8A CN110213656A (en) 2019-06-17 2019-06-17 A kind of IPTV content tampering kind identification method and system based on the comparison of picture portion domain

Publications (1)

Publication Number Publication Date
CN110213656A true CN110213656A (en) 2019-09-06

Family

ID=67793134

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910521919.8A Pending CN110213656A (en) 2019-06-17 2019-06-17 A kind of IPTV content tampering kind identification method and system based on the comparison of picture portion domain

Country Status (1)

Country Link
CN (1) CN110213656A (en)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102006498A (en) * 2010-12-10 2011-04-06 北京中科大洋科技发展股份有限公司 Safe broadcast monitoring method based on video and audio comparison
CN103067778A (en) * 2013-01-06 2013-04-24 北京华兴宏视技术发展有限公司 Data monitoring system and data monitoring method
CN103095995A (en) * 2013-01-09 2013-05-08 上海思华科技股份有限公司 Method and system for automatic technical inspection of media files
KR20140077409A (en) * 2012-12-14 2014-06-24 포항공과대학교 산학협력단 Method for learning of sequential binary code using features and apparatus for the same
CN105554449A (en) * 2015-12-11 2016-05-04 浙江宇视科技有限公司 Method and device for quickly splicing camera images
CN108810524A (en) * 2017-05-05 2018-11-13 德科仕通信(上海)有限公司 The method of IPTV flopover phenomenons detection

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102006498A (en) * 2010-12-10 2011-04-06 北京中科大洋科技发展股份有限公司 Safe broadcast monitoring method based on video and audio comparison
KR20140077409A (en) * 2012-12-14 2014-06-24 포항공과대학교 산학협력단 Method for learning of sequential binary code using features and apparatus for the same
CN103067778A (en) * 2013-01-06 2013-04-24 北京华兴宏视技术发展有限公司 Data monitoring system and data monitoring method
CN103095995A (en) * 2013-01-09 2013-05-08 上海思华科技股份有限公司 Method and system for automatic technical inspection of media files
CN105554449A (en) * 2015-12-11 2016-05-04 浙江宇视科技有限公司 Method and device for quickly splicing camera images
CN108810524A (en) * 2017-05-05 2018-11-13 德科仕通信(上海)有限公司 The method of IPTV flopover phenomenons detection

Similar Documents

Publication Publication Date Title
WO2017035949A1 (en) Intelligent home device interaction method and system based on intelligent television video scene
WO2019148912A1 (en) Image processing method, apparatus, electronic device and storage medium
US11763431B2 (en) Scene-based image processing method, apparatus, smart terminal and storage medium
CN105718871B (en) A kind of video host's recognition methods based on statistics
US20100201871A1 (en) Temporally consistent caption detection on videos using a 3D spatiotemporal method
US8194978B2 (en) Method of and apparatus for detecting and adjusting colour values of skin tone pixels
CN111144366A (en) Strange face clustering method based on joint face quality assessment
TWI419082B (en) Moving object detection method and image processing system for moving object detection
US8189913B2 (en) Method for detecting shadow of object
WO2017047494A1 (en) Image-processing device
CN107590447A (en) A kind of caption recognition methods and device
TW200526023A (en) Methods and apparatus to distinguish a signal originating from a local device from a broadcast signal
CN108615030B (en) Title consistency detection method and device and electronic equipment
WO2007092906A1 (en) Multi-mode region-of-interest video object segmentation
EP3236362B1 (en) Information pushing method and system
CN102802074B (en) Method for extracting and displaying text messages from television signal and television
CN110213656A (en) A kind of IPTV content tampering kind identification method and system based on the comparison of picture portion domain
CN103079029B (en) A kind of identification method for digital television mosaic based on macroblock edges information
CN116320624B (en) Method and system for monitoring rebroadcasting abnormality
CN108388872B (en) Method and device for identifying news headlines based on font colors
US20080063063A1 (en) Electronic device and method for block-based image processing
CN115719467A (en) Forest investigation monitoring method and system based on image recognition
TW202046699A (en) Method for detecting video quality and image processing circuit thereof
KR101171991B1 (en) Image processing sysem for improving quality of foggy image and fog detection method in the same
CN108304824B (en) News title identification method and device based on region color

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
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20190906