CN105631015A - Intelligent multimedia player - Google Patents
Intelligent multimedia player Download PDFInfo
- Publication number
- CN105631015A CN105631015A CN201511012948.XA CN201511012948A CN105631015A CN 105631015 A CN105631015 A CN 105631015A CN 201511012948 A CN201511012948 A CN 201511012948A CN 105631015 A CN105631015 A CN 105631015A
- Authority
- CN
- China
- Prior art keywords
- content
- audio
- frequency
- image
- information
- 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
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/78—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/783—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
- G06F16/7834—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using audio features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/73—Querying
- G06F16/735—Filtering based on additional data, e.g. user or group profiles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/78—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/783—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
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/03—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the type of extracted parameters
- G10L25/18—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the type of extracted parameters the extracted parameters being spectral information of each sub-band
Abstract
The invention relates to an intelligent multimedia player which comprises an image datum lossless compression system, an image content sentiment analysis system, an audio content analysis system and a weight fusion system, and corresponding automatic recognition and filtering systems are established based on contents expressed by videos, images and audios. According to the intelligent multimedia player, the intelligent multimedia player conducts automatic shield on sensitive and harmful information, so that the physical and psychological health of a viewer can be protected to the maximum degree while continuous playing of the video content is guaranteed, and harmonious development of the society is promoted.
Description
[technical field]
The present invention relates to a kind of intelligent multimedia player, belong to image and audio signal processing technique field.
[background technology]
Along with the development of internet and the Multimedia technology such as image and audio frequency, various content of multimedia is full of in each corner of internet, and these contents comprise video image, also comprise the content of individual making and shooting. But, current video content is also full of image or the audio contents such as a large amount of pornographic and violence, and the grievous injury physical and mental health of numerous teenagers, endangers the stability and development of society.
Current domestic and international various player also arises, of a great variety, but or cannot accomplish monitor in real time and the broadcasting of control multimedia video content. Comparing conventional method is increase some control plug-in units in these websites, or simply by hiding for video DVD etc. so that viewing person cannot touch such video content, this be one completely by the process of manual control. Its defect is mainly manifested in 2 aspects: (1) this kind of manual control needs intervene people's viewing or understand this section of video in advance, but what this can not accomplish often; (2) in one section of video, part that is pornographic and violence may be sub-fraction content wherein, is also not too suit reason to shielding completely of this video.
In sum, we are badly in need of the intelligent multimedia player that an energy automatically identifies the harmful content such as pornographic and violence in video display process so that viewing person is not subject to the impact of harmful content while not affecting this video content of viewing.
[summary of the invention]
It is an object of the invention to: a kind of intelligent multimedia player is provided; corresponding automatically identification and filtering system is set up based on the content expressed by video, image and audio frequency; and after running into sensitivity and harmful information, carry out automatic shield; thus while ensureing video content Continuous Play, protect the physical and mental health of viewing person to greatest extent, promote the harmonious development of society.
For achieving the above object, the technical solution used in the present invention is:
A kind of intelligent multimedia player of the present invention, comprises following four parts:
(1), the harmless compression system of view data: owing to the resolving power of multi-media image is too high, frame-skipping easily occurs when last demonstration or loses the situation of frame, all first by bilinearity interpolation algorithm, the process of every two field picture must being carried out high-quality compression of images to it, Normal squeezing is to the size of 640*480 for this reason;
(2), the sentiment analysis system of image content: after the compressed image content obtaining above-mentioned 640*480, the compressed image of 640*480 is carried out the emotion content analysis of the degree of depth, the segmentation that comprises different zones in image, the feature extracting each region and set up regional relation matrix, the dependency definition of different zones and judge whether according to decision model to belong to normal, separate the grade weight of image level;
(3), audio content analysis system, wherein audio content analysis system is operated by following step:
Audio signal content under step one, the different frequency of acquisition present frame;
Step 2, to obtain audio signal content use a Gaussian filter to carry out denoising;
Step 3, denoising and filtered audio-frequency information are carried out spectral decomposition, make the histogram in different frequency section clear, and obtain multiple basic audio-frequency information, the quantity of information of such as high frequency, the difference of High-frequency and low-frequency, the position etc. that high frequency occurs;
Step 4, the elementary audio information after above-mentioned analysis and existing sensitivity and harmful content are carried out similarity comparison, draw the sensitivity of audio-frequency information and the grade weight of harmful content, in general, similarity is more high, is likely more responsive and harmful content;
(4), weight fusion system: by the grade weight of image level, weight fusion also carries out content judgement, after the image analysis result of summary and the analytical results of audio frequency, carry out whether comprehensive descision belongs to responsive and harmful information, its basic mode is this integrate score is exactly responsive and harmful information higher than certain threshold value, and to belong to responsive and harmful information carry out shielding processing, it is possible to be stamp mosaic, it is also possible to carry out skipping not showing.
After adopting said structure; the useful effect of the present invention is: the present invention sets up corresponding automatically identification and filtering system based on the content expressed by video, image and audio frequency; and after running into sensitivity and harmful information, carry out automatic shield; thus while ensureing video content Continuous Play, protect the physical and mental health of viewing person to greatest extent, promote the harmonious development of society.
[accompanying drawing explanation]
Accompanying drawing described herein is used to provide a further understanding of the present invention, forms the part of the application, but does not form inappropriate limitation of the present invention, in the accompanying drawings:
Fig. 1 is the schematic flow sheet of the present invention;
Fig. 2 is sentiment analysis schematic diagram to image content in the present invention;
Fig. 3 is to audio content analysis schematic diagram in the present invention.
[embodiment]
Below in conjunction with accompanying drawing and specific embodiment, the present invention being described in detail, illustrative examples and explanation wherein are only used for explaining the present invention, but not as a limitation of the invention.
As Figure 1-3, a kind of intelligent multimedia player, comprises following four parts:
(1), the harmless compression system of view data: owing to the resolving power of multi-media image is too high, frame-skipping easily occurs when last demonstration or loses the situation of frame, all first by bilinearity interpolation algorithm, the process of every two field picture must being carried out high-quality compression of images to it, Normal squeezing is to the size of 640*480 for this reason;
(2), the sentiment analysis system of image content: after the compressed image content obtaining above-mentioned 640*480, the compressed image of 640*480 is carried out the emotion content analysis of the degree of depth, the segmentation that comprises different zones in image, the feature extracting each region and set up regional relation matrix, the dependency definition of different zones and judge whether according to decision model to belong to normal, separate the grade weight of image level;
(3), audio content analysis system, wherein audio content analysis system is operated by following step:
Audio signal content under step one, the different frequency of acquisition present frame;
Step 2, to obtain audio signal content use a Gaussian filter to carry out denoising;
Step 3, denoising and filtered audio-frequency information are carried out spectral decomposition, make the histogram in different frequency section clear, and obtain multiple basic audio-frequency information, the quantity of information of such as high frequency, the difference of High-frequency and low-frequency, the position etc. that high frequency occurs;
Step 4, the elementary audio information after above-mentioned analysis and existing sensitivity and harmful content are carried out similarity comparison, draw the sensitivity of audio-frequency information and the grade weight of harmful content, in general, similarity is more high, is likely more responsive and harmful content;
(4), weight fusion system: by the grade weight of image level, weight fusion also carries out content judgement, after the image analysis result of summary and the analytical results of audio frequency, carry out whether comprehensive descision belongs to responsive and harmful information, its basic mode is this integrate score is exactly responsive and harmful information higher than certain threshold value, and to belong to responsive and harmful information carry out shielding processing, it is possible to be stamp mosaic, it is also possible to carry out skipping not showing.
The present invention can also can exist as the plug-in unit of network player as the player of independent operating on computer and cell phone platform.
Wherein pass through following operation as the multimedia player of computer and cell phone platform:
1. user passes through at computer, mobile phone, and mobile terminal etc. install this software, filtering content and filter type are arranged simultaneously;
2. this player receives video content, utilizes depth analysis model to carry out emotion content analysis;
3., if there is responsive and harmful content, by automatic shield, but do not affect the Continuous Play of video;
Wherein can play by following operation as the plug-in unit of network player:
1. user is by installing corresponding plug-in unit for websites such as videos, filtering content and filter type is arranged simultaneously;
2., time user watches various video online, content of multimedia will be utilized depth analysis model to carry out emotion content analysis by software plug-in unit;
3., if there is responsive and harmful content, by automatic shield, but do not affect the Continuous Play of video.
The above is only the better embodiment of the present invention, therefore all equivalences done according to the structure described in patent application scope of the present invention, feature and principle change or modify, and are included within the scope of patent application of the present invention.
Claims (1)
1. an intelligent multimedia player, it is characterised in that: comprise following four parts:
(1), the harmless compression system of view data: owing to the resolving power of multi-media image is too high, frame-skipping easily occurs when last demonstration or loses the situation of frame, all first by bilinearity interpolation algorithm, the process of every two field picture must being carried out high-quality compression of images to it, Normal squeezing is to the size of 640*480 for this reason;
(2), the sentiment analysis system of image content: after the compressed image content obtaining above-mentioned 640*480, the compressed image of 640*480 is carried out the emotion content analysis of the degree of depth, the segmentation that comprises different zones in image, the feature extracting each region and set up regional relation matrix, the dependency definition of different zones and judge whether according to decision model to belong to normal, separate the grade weight of image level;
(3), audio content analysis system, wherein audio content analysis system is operated by following step:
Audio signal content under step one, the different frequency of acquisition present frame;
Step 2, to obtain audio signal content use a Gaussian filter to carry out denoising;
Step 3, denoising and filtered audio-frequency information are carried out spectral decomposition, make the histogram in different frequency section clear, and obtain multiple basic audio-frequency information, the quantity of information of such as high frequency, the difference of High-frequency and low-frequency, the position etc. that high frequency occurs;
Step 4, the elementary audio information after above-mentioned analysis and existing sensitivity and harmful content are carried out similarity comparison, draw the sensitivity of audio-frequency information and the grade weight of harmful content, in general, similarity is more high, is likely more responsive and harmful content;
(4), weight fusion system: by the grade weight of image level, weight fusion also carries out content judgement, after the image analysis result of summary and the analytical results of audio frequency, carry out whether comprehensive descision belongs to responsive and harmful information, its basic mode is this integrate score is exactly responsive and harmful information higher than certain threshold value, and to belong to responsive and harmful information carry out shielding processing, it is possible to be stamp mosaic, it is also possible to carry out skipping not showing.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201511012948.XA CN105631015A (en) | 2015-12-31 | 2015-12-31 | Intelligent multimedia player |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201511012948.XA CN105631015A (en) | 2015-12-31 | 2015-12-31 | Intelligent multimedia player |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105631015A true CN105631015A (en) | 2016-06-01 |
Family
ID=56045948
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201511012948.XA Pending CN105631015A (en) | 2015-12-31 | 2015-12-31 | Intelligent multimedia player |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105631015A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106954052A (en) * | 2017-03-22 | 2017-07-14 | 成都市极米科技有限公司 | Virgin locking method and system |
| WO2018023453A1 (en) * | 2016-08-02 | 2018-02-08 | 步晓芳 | Patent information pushing method performed during automatic pornography identification, and recognition system |
| WO2018023452A1 (en) * | 2016-08-02 | 2018-02-08 | 步晓芳 | Method for collecting usage condition of adult shot identification technique, and recognition system |
| WO2018023454A1 (en) * | 2016-08-02 | 2018-02-08 | 步晓芳 | Automatic pornography identification method, and recognition system |
| WO2019127654A1 (en) * | 2017-12-30 | 2019-07-04 | 惠州学院 | Method and system for identifying harmful videos on basis of user ip and credits content |
| WO2019127656A1 (en) * | 2017-12-30 | 2019-07-04 | 惠州学院 | User ip and video copy-based harmful video identification method and system |
| CN112381159A (en) * | 2020-11-18 | 2021-02-19 | 北京金山云网络技术有限公司 | Sensitive data identification method, device and equipment |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020159630A1 (en) * | 2001-03-29 | 2002-10-31 | Vasile Buzuloiu | Automated detection of pornographic images |
| CN101470897A (en) * | 2007-12-26 | 2009-07-01 | 中国科学院自动化研究所 | Sensitive film detection method based on audio/video amalgamation policy |
| CN101819638A (en) * | 2010-04-12 | 2010-09-01 | 中国科学院计算技术研究所 | Establishment method of pornographic detection model and pornographic detection method |
| CN102163286A (en) * | 2010-02-24 | 2011-08-24 | 中国科学院自动化研究所 | Pornographic image evaluating method |
-
2015
- 2015-12-31 CN CN201511012948.XA patent/CN105631015A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020159630A1 (en) * | 2001-03-29 | 2002-10-31 | Vasile Buzuloiu | Automated detection of pornographic images |
| CN101470897A (en) * | 2007-12-26 | 2009-07-01 | 中国科学院自动化研究所 | Sensitive film detection method based on audio/video amalgamation policy |
| CN102163286A (en) * | 2010-02-24 | 2011-08-24 | 中国科学院自动化研究所 | Pornographic image evaluating method |
| CN101819638A (en) * | 2010-04-12 | 2010-09-01 | 中国科学院计算技术研究所 | Establishment method of pornographic detection model and pornographic detection method |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018023453A1 (en) * | 2016-08-02 | 2018-02-08 | 步晓芳 | Patent information pushing method performed during automatic pornography identification, and recognition system |
| WO2018023452A1 (en) * | 2016-08-02 | 2018-02-08 | 步晓芳 | Method for collecting usage condition of adult shot identification technique, and recognition system |
| WO2018023454A1 (en) * | 2016-08-02 | 2018-02-08 | 步晓芳 | Automatic pornography identification method, and recognition system |
| CN106954052A (en) * | 2017-03-22 | 2017-07-14 | 成都市极米科技有限公司 | Virgin locking method and system |
| WO2019127654A1 (en) * | 2017-12-30 | 2019-07-04 | 惠州学院 | Method and system for identifying harmful videos on basis of user ip and credits content |
| WO2019127656A1 (en) * | 2017-12-30 | 2019-07-04 | 惠州学院 | User ip and video copy-based harmful video identification method and system |
| CN112381159A (en) * | 2020-11-18 | 2021-02-19 | 北京金山云网络技术有限公司 | Sensitive data identification method, device and equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105631015A (en) | Intelligent multimedia player | |
| CN106557937B (en) | Advertisement pushing method and device | |
| CN102307274B (en) | Motion detection method based on edge detection and frame difference | |
| JP6557592B2 (en) | Video scene division apparatus and video scene division program | |
| CN104123396B (en) | A kind of abstract of football video generation method and device based on cloud TV | |
| EP2034426A1 (en) | Moving image analyzing, method and system | |
| EP2954690A1 (en) | Attention estimation to control the delivery of data and audio/video content | |
| CN106507188A (en) | A kind of video TV station symbol recognition device and method of work based on convolutional neural networks | |
| CN102903124A (en) | Moving object detection method | |
| CN105872588A (en) | Method and device for loading advertisement in video | |
| CN105718861A (en) | Method and device for identifying video streaming data category | |
| CN103678299A (en) | Method and device for monitoring video abstract | |
| CN101790049A (en) | Newscast video segmentation method and system | |
| CN102883179A (en) | Objective evaluation method of video quality | |
| Jiang et al. | An adaptive video shot segmentation scheme based on dual-detection model | |
| CN103092332A (en) | Digital image interactive method and system of television | |
| WO2013170362A1 (en) | Method and system of identifying non-distinctive images/objects in a digital video and tracking such images/objects using temporal and spatial queues | |
| CN105488206B (en) | A kind of Android application evolution recommended method based on crowdsourcing | |
| CN103067702A (en) | Video concentration method used for video with still picture | |
| CN104978733A (en) | Smoke detection method and smoke detection device | |
| CN105245817B (en) | Video recording playback method and its device | |
| CN107798304B (en) | Method for rapidly auditing video | |
| Porteous et al. | Interactive storytelling via video content recombination | |
| CN107483916A (en) | The control method of audio frequency and video archival quality detecting system | |
| CN103034997A (en) | Foreground detection method for separation of foreground and background of surveillance video |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into 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: 20160601 |