CN106973324A - A kind of poster generation method and device - Google Patents
A kind of poster generation method and device Download PDFInfo
- Publication number
- CN106973324A CN106973324A CN201710192648.7A CN201710192648A CN106973324A CN 106973324 A CN106973324 A CN 106973324A CN 201710192648 A CN201710192648 A CN 201710192648A CN 106973324 A CN106973324 A CN 106973324A
- Authority
- CN
- China
- Prior art keywords
- image
- face
- poster
- characteristic information
- described image
- 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
-
- 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]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing 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
- H04N21/44—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream, rendering scenes according to MPEG-4 scene graphs
- H04N21/44008—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream, rendering scenes according to MPEG-4 scene graphs involving operations for analysing video streams, e.g. detecting features or characteristics in the video stream
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
- G06V10/443—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components by matching or filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
-
- 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]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing 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
- H04N21/44—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream, rendering scenes according to MPEG-4 scene graphs
- H04N21/4402—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream, rendering scenes according to MPEG-4 scene graphs involving reformatting operations of video signals for household redistribution, storage or real-time display
- H04N21/440245—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream, rendering scenes according to MPEG-4 scene graphs involving reformatting operations of video signals for household redistribution, storage or real-time display the reformatting operation being performed only on part of the stream, e.g. a region of the image or a time segment
-
- 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]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/47—End-user applications
- H04N21/472—End-user interface for requesting content, additional data or services; End-user interface for interacting with content, e.g. for content reservation or setting reminders, for requesting event notification, for manipulating displayed content
- H04N21/47205—End-user interface for requesting content, additional data or services; End-user interface for interacting with content, e.g. for content reservation or setting reminders, for requesting event notification, for manipulating displayed content for manipulating displayed content, e.g. interacting with MPEG-4 objects, editing locally
-
- 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]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/47—End-user applications
- H04N21/478—Supplemental services, e.g. displaying phone caller identification, shopping application
-
- 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]
- H04N21/80—Generation or processing of content or additional data by content creator independently of the distribution process; Content per se
- H04N21/83—Generation or processing of protective or descriptive data associated with content; Content structuring
- H04N21/84—Generation or processing of descriptive data, e.g. content descriptors
-
- 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]
- H04N21/80—Generation or processing of content or additional data by content creator independently of the distribution process; Content per se
- H04N21/83—Generation or processing of protective or descriptive data associated with content; Content structuring
- H04N21/845—Structuring of content, e.g. decomposing content into time segments
- H04N21/8456—Structuring of content, e.g. decomposing content into time segments by decomposing the content in the time domain, e.g. in time segments
Abstract
A kind of poster generation method of disclosure and device, applied to DTV cloud platform, programm name and performer concordance list of the methods described in the DTV cloud platform determine pending video frequency program；The image of key frame is obtained from pending video frequency program；Judge whether described image meets human face scanning rule, the human face scanning rule is used to characterize the characteristic information that can recognize that face from described image；If so, then scanning the face characteristic information of described image, and the face characteristic information is matched in the protagonist Face Sample Storehouse pre-set；If the match is successful, the poster of the pending video frequency program is exported according to described image.The present invention simultaneously need not be participated in manually, greatly reduce workload, and, the image for generating poster is the image matched with Face Sample Storehouse, face i.e. in poster is the face acted the leading role, and reduces the unmatched risk of the content of content and program of poster, improves Consumer's Experience.
Description
Technical field
The application is related to video detection technology field, more specifically to a kind of poster generation method and device.
Background technology
DTV cloud platform system can access nearly 200 sets of direct broadcast bands in real time in operation, while being also faced with from Duo Jia
Content supplier (CP) imports hundreds and thousands of movie or television serials and watched for user.In order to allow user being capable of previewing program
Content, each program is required for configuring the higher poster of respective quality.
The poster generation method of existing video frequency program is usually that the mode of artificial random screenshotss in a program carries out picture
Interception, then using one more conveniently picture processing tools generate the corresponding poster of program.
But, not only workload is huge for such a mode, and many posters are chosen to many inessential personage's pictures
As poster, there is the unmatched risk of the content of content and program of poster, it is impossible to ensure objective and accurate by program
Appearance is shown in the form of poster.
The content of the invention
In view of this, this application provides a kind of poster generation method and device, for solving workload in the prior art
Greatly, exist poster content and program content unmatched risk the problem of.
To achieve these goals, it is proposed that scheme it is as follows：
This application discloses a kind of poster generation method, applied to DTV cloud platform, including：
Programm name and performer's title in the DTV cloud platform determine pending video frequency program；
The image of key frame is obtained from the pending video frequency program；
Judge whether described image meets human face scanning rule, the human face scanning rule is used to characterize from described image
It can recognize that the characteristic information of face；
If so, then scanning described image obtains face characteristic information, and the face characteristic information is being pre-set
The face characteristic information with performer's title matched in Face Sample Storehouse is acted the leading role to be matched；
If the match is successful, described image is output as to the poster associated with the programm name.
It is preferred that, if after the match is successful, methods described also includes：
Enhancing processing is carried out to described image, the enhancing image higher than the definition of described image is obtained；
The enhancing image is subjected to Image Coding and obtains pending image；
Described image is output as into the poster associated with the programm name includes the pending image being output as
The poster associated with the programm name.
It is preferred that, it is described that described image progress enhancing processing is included：
The black surround of described image is detected, the black surround is cut, obtains cutting image；
According to pre-defined poster resolution ratio, the cutting image is zoomed in and out and obtains zoomed image；
The brightness of the zoomed image, contrast and/or brightness are compensated according to default regulation rule and are adjusted so as to
To the enhancing image；The regulation rule is used to make the definition of the zoomed image higher.
It is preferred that, the protagonist Face Sample Storehouse pre-set is set up through the following steps：
Performer's title is obtained from performer's concordance list in the DTV cloud platform；
Obtain the face screening conditions set by user；
The standard faces image for meeting the face screening conditions is obtained from preset facial image；
Extract the face characteristic information of the standard faces image；
The face characteristic information is associated with performer's title；
Foundation includes the protagonist Face Sample Storehouse of multiple face characteristic informations.
It is preferred that, the face screening conditions entreat position, face size to be not less than the pictures of 64x 64 in the picture including face
Element and/or exclusion side face.
Another aspect of the present invention provides a kind of poster generating means, applied to DTV cloud platform, including：
Determining module, is determined pending for the programm name and performer's concordance list in the DTV cloud platform
Video frequency program；
Image collection module, the image for obtaining key frame from the pending video frequency program；
Judge module, for judging whether described image meets human face scanning rule, the human face scanning rule is used for table
Levy the characteristic information that face is can recognize that from described image；
Matching module, if for meeting the human face scanning rule, scanning described image obtains face characteristic information, and
The face characteristic information is matched in the protagonist Face Sample Storehouse pre-set；
Output module, if for the match is successful, described image to be output as to the sea associated with the programm name
Report.
It is preferred that, in addition to：
Processing module, for carrying out enhancing processing to described image, obtains the enhancing higher than the definition of described image
Image；
Coding module, pending image is obtained for the enhancing image to be carried out into Image Coding；
The output module by the pending image specifically for being output as the poster associated with the programm name.
It is preferred that, the processing unit includes：
Subelement is cut, the black surround for detecting described image is cut to the black surround, obtain cutting image；
Subelement is scaled, for according to pre-defined poster resolution ratio, zooming in and out and being contracted to the cutting image
Put image；
Adjust subelement, for the brightness of the zoomed image, contrast and/or brightness according to default regulation rule
Compensate adjustment and obtain the enhancing image；The regulation rule is used to make the definition of the zoomed image higher.
It is preferred that, in addition to Sample Storehouse sets up module；
The Sample Storehouse, which sets up module, to be included：
Acquiring unit, for obtaining performer's title from performer's concordance list in the DTV cloud platform；
Setting unit, for obtaining the face screening conditions set by user；
First extraction unit, the standard faces of the face screening conditions are met for being obtained from preset facial image
Image；
Second extraction unit, the face characteristic information for extracting the standard faces image；
Associative cell, for the face characteristic information is associated with performer's title；
Unit is set up, includes the protagonist Face Sample Storehouse of multiple face characteristic informations for setting up.
It is preferred that, the face screening conditions entreat position, face size to be not less than the pictures of 64x 64 in the picture including face
Element and/or exclusion side face.
It can be seen from above-mentioned technical scheme that, poster generation method and device that the embodiment of the present application is provided are applied to
DTV cloud platform, programm name and performer title of the methods described in the DTV cloud platform determines pending
Video frequency program；The image of key frame is obtained from the pending video frequency program；Judge whether described image meets human face scanning
Rule, the human face scanning rule is used to characterize the characteristic information that can recognize that face from described image；If so, then scanning
Described image obtains face characteristic information, and by the face characteristic information in the protagonist Face Sample Storehouse pre-set with institute
The face characteristic information that performer's title matches is stated to be matched；If the match is successful, by described image be output as with it is described
The associated poster of programm name.The present invention simultaneously need not be participated in manually, greatly reduce workload, also, generate poster
Image is that the face in the image matched with Face Sample Storehouse, i.e. poster is the face acted the leading role, reduce the content of poster with
The unmatched risk of content of program, it is ensured that the objective and accurate content by program is shown in the form of poster, and then
Improve Consumer's Experience.
Brief description of the drawings
, below will be to embodiment or existing in order to illustrate more clearly of the embodiment of the present application or technical scheme of the prior art
There is the accompanying drawing used required in technology description to be briefly described, it should be apparent that, drawings in the following description are only this
The embodiment of application, for those of ordinary skill in the art, on the premise of not paying creative work, can also basis
The accompanying drawing of offer obtains other accompanying drawings.
Fig. 1 is a kind of poster generation method flow chart disclosed in the embodiment of the present application；
Fig. 2 is another poster generation method flow chart disclosed in the embodiment of the present application；
Fig. 3 is the disclosed schematic flow sheet for setting up the protagonist Face Sample Storehouse pre-set of the embodiment of the present application；
Fig. 4 is a kind of structural representation of poster generating means disclosed in the embodiment of the present invention.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present application, the technical scheme in the embodiment of the present application is carried out clear, complete
Site preparation is described, it is clear that described embodiment is only some embodiments of the present application, rather than whole embodiments.It is based on
Embodiment in the application, it is every other that those of ordinary skill in the art are obtained under the premise of creative work is not made
Embodiment, belongs to the scope of the application protection.
For the ease of understanding technical scheme, technical term used in the present invention is explained below.
TS：A kind of media transport stream that Transport Stream, International Standards Organization MPEG are defined；
PES：Packetized Elementary Stream, the basic stream packets of encapsulation；
ES：A kind of audio frequency and video packaged media transport stream that Elementray Stream, national standards organizations MPEG are defined,
The original base code stream exported by encoder, it comprise only necessary to decoder and with original picture or original audio phase
Close information.
Automation is extracted：One kind is parsed and key frame of video Auto-Sensing and decoding process automatically based on TS programs.
Technical scheme is described in detail below.
Referring to Fig. 1, Fig. 1 is a kind of poster generation method flow chart disclosed in the embodiment of the present application.
As shown in figure 1, this method is applied to DTV cloud platform, including：
S101, the programm name in the DTV cloud platform and performer's title determine pending video frequency program；
In the embodiment of the present invention, programm name and performer's title can be according to being pre-established in DTV cloud platform
Directly obtained in database, either receive by the input of user or obtained from content provider.Performer's title can also be from
Obtained in performer's concordance list, it is, of course, also possible to obtained from a variety of other channels, then this is without repeating, as long as can get
Need the programm name and performer's title of generation poster.
Under DTV cloud platform, live TV stream, review, the program such as program request is defined with International Standards Organization MPEG and DVB
Based on TS transformats, therefore pending video frequency program of the invention is all to meet the TS data files that MPEG and DVB are defined.
S102, from the pending video frequency program obtain key frame image；
After pending video frequency program is got, that is, after obtaining corresponding TS data files, obtain crucial
The image of frame.It is the important frame in video inter-frame compression coding；It is the coded frame of a full frame compression.
The following steps can be used in actual use：
The tape handling video frequency program is parsed using TS resolvers, video numbering, video code model etc. is obtained
Essential information, then filters video and numbers corresponding packet, obtain complete encapsulated data packet PES, finally parse the encapsulation
Packet PES, obtains the key frame data of video and per frame corresponding timestamp information, finally according to the key frame data and
Timestamp information is decoded, and obtains the image of key frame.
S103, judge whether described image meets human face scanning rule, human face scanning rule is used to characterize from described
The characteristic information of face is can recognize that in image；
In the embodiment of the present invention, after the image for the key frame for having obtained pending video frequency program, the image is judged,
Determine if to meet human face scanning rule.The human face scanning rule is used to characterize can recognize that face from described image
Characteristic information, for example whether whether for positive face, the basic demand of human face scanning can be carried out including trunk etc..
If do not met, in return to step S102.
S104, if so, then scanning described image obtains face characteristic information, and the face characteristic information is set in advance
The face characteristic information matched in the protagonist Face Sample Storehouse put with performer's title is matched；
After the basic demand of human face scanning is met, the image is scanned, that is, carries out recognition of face, face characteristic letter
Breath parsing, obtains the face characteristic information of the image.The face characteristic information is facial contour, eyes, nose, face, chin
Deng the data corresponding to facial key feature points.
Also, the face characteristic information is matched with the sample in the protagonist Face Sample Storehouse pre-set, to sentence
Whether the face in the disconnected image is featured performer.
The mode of setting up of the Face Sample Storehouse is introduced later.
If S105, the match is successful, and described image is output as to the poster associated with the programm name.
If the match is successful, it is featured performer to prove the face in image, is not utility man, supporting role, so
The protagonist in pending video frequency program is picked out.Then the image is exported into poster.The mode for exporting poster using image belongs to
In mature technology of the prior art, herein without excessively repeating.By said process, just obtain related to programm name
The poster of connection.It can be stored in as the poster of the program in DTV cloud platform.
If it should be noted that it fails to match, return to step S102 or terminating this process.
Existing poster can not bring most direct perception to user, greatly reduce attraction of the program to user, be unfavorable for
The experience of user, and such result is current very universal.In order to solve this problem, the embodiment of the present application provides above-mentioned sea
Report generation method.
According to above-mentioned technical proposal as can be seen that the application above method is applied to DTV cloud platform, methods described
Programm name and performer's title in the DTV cloud platform determine pending video frequency program；Pending regarded from described
The image of key frame is obtained in frequency program；Judge whether described image meets human face scanning rule, the human face scanning rule is used
The characteristic information of face is can recognize that from described image in sign；If so, then scanning described image obtains face characteristic letter
Breath, and the face that the face characteristic information is matched in the protagonist Face Sample Storehouse pre-set with performer's title
Characteristic information is matched；If the match is successful, described image is output as to the poster associated with the programm name.This
Invent and need not manually participate in, greatly reduce workload, also, the image of generation poster is matched with Face Sample Storehouse
Image, i.e., the face in poster be act the leading role face, reduce the unmatched risk of the content of content and program of poster, protect
Demonstrate,prove the objective and accurate content by program to be shown in the form of poster, and then improve Consumer's Experience.
Referring to Fig. 2, Fig. 2 is another poster generation method flow chart disclosed in the embodiment of the present application.
As shown in Fig. 2 this method is applied to DTV cloud platform, including：
S201, the programm name in the DTV cloud platform and performer's title determine pending video frequency program；
S202, from the pending video frequency program obtain key frame image；
S203, judge whether described image meets human face scanning rule, human face scanning rule is used to characterize from described
The characteristic information of face is can recognize that in image；
S204, if so, then scanning described image obtains face characteristic information, and the face characteristic information is set in advance
The face characteristic information matched in the protagonist Face Sample Storehouse put with performer's title is matched；
It should be noted that step S201- steps S204 is identical with above-mentioned steps S101- steps S104, herein without
Repeat.
If S205, the match is successful, enhancing processing is carried out to described image, obtains higher than the definition of described image
Strengthen image；
In the embodiment of the present application, after the match is successful, enhancing processing can be also carried out to image, it is higher to obtain definition
Enhancing image.
Specifically, described include to described image progress enhancing processing：
The black surround of described image is detected, the black surround is cut, obtains cutting image；
According to pre-defined poster resolution ratio, the cutting image is zoomed in and out and obtains zoomed image；
Adjustment is compensated according to default regulation rule to the brightness of the zoomed image, contrast and/or brightness, obtained
To the enhancing image；The regulation rule is used to make the definition of the zoomed image higher.
In the embodiment of the present application, the black and white to image is detected, if having detected black surround, to the black surround portion of image
Divide and cut, obtain cutting image.The size and scope of cutting can be performed according to the setting of user.
Then according to the predefined resolution ratio of poster, such as 80*60, processing is zoomed in and out to image, is scaled
Image.The process of scaling can be performed proportionally, can also directly be cut out when cutting according to the multiple of the resolution ratio
Cut image.
The parameter of image definition is influenceed according to adjustment on such as brightness, contrast and/or brightness of zoomed image afterwards
Rule compensates adjustment, obtains strengthening image.Wherein, regulation rule is set according to the optimal definition reference value of image
Put, by the parameter adjustment of zoomed image to most suitable state.
It is, of course, also possible to which to the other parameters of zoomed image, the parameter such as tone, exposure is adjusted so that contracting
The display effect for putting image is more suitable for user's appreciation.
S206, by it is described enhancing image carry out Image Coding, be output as the poster associated with the programm name.
Finally enhancing image is carried out after Image Coding, the poster associated with the programm name is exported.
It should be noted that Image Coding and the process of output belong to the technology of comparative maturity in the prior art.Herein
Without repeating.
Watched due to being directly all not well suited for user by poster Many times obtained from image, influence the body of user
Test, therefore, the present invention also carries out enhancing processing to image, obtains strengthening image, so, processing picture output poster will be strengthened
Effect just meets have viewed for user very much.
The foregoing description present invention has protagonist Sample Storehouse, with reference to Fig. 3, acts the leading role Face Sample Storehouse to how to set up below and carries out
It is discussed in detail.
Fig. 3 is the schematic flow sheet for the protagonist Face Sample Storehouse that the foundation that the embodiment of the present application is provided is pre-set.
The protagonist Face Sample Storehouse pre-set is set up through the following steps through the following steps：
S301, acquisition performer's title from performer's concordance list of the DTV cloud platform；
The face screening conditions that S302, acquisition are set by user；
It is preferred that, the face screening conditions entreat position, face size to be not less than the pictures of 64x 64 in the picture including face
Element and/or exclusion side face.
In the embodiment of the present invention, protagonist Face Sample Storehouse has been pre-established, during the foundation of the protagonist Face Sample Storehouse,
Performer's title is obtained first from performer's concordance list, the face screening conditions that user sets are obtained.For example：Face validity is set
Put, pixel size is set, face validity, which is set, for example ensures that face entreats position in the picture, excludes side face etc., pixel size
Set such as being set to 64*64 pixels.
S303, obtained from preset facial image and meet the standard faces images of the face screening conditions；
It should be noted that before protagonist Face Sample Storehouse is set up, the image of protagonist can be collected in advance, such as description,
Stage photo etc., it is of course also possible to be directly directly connected to other image data bases, obtains image from image data base.
After performer's title and face screening conditions is obtained, the standard faces for meeting the face screening conditions are obtained
Image.Obtain the standard faces image of the performer.
S304, the face characteristic information for extracting the standard faces image；
It is S305, the face characteristic information is associated with performer's title；
After standard faces image has been obtained, the face characteristic information in the image is extracted, the process of extraction uses existing
Ripe face identification method in technology, herein without repeating.It is preferred that, first eyes are positioned, then after progress
Continuous process.
Then it is associated with performer's title so that the face characteristic information is corresponding with the performer.This has been obtained to drill
The face characteristic information of member.
S306, foundation include the protagonist Face Sample Storehouse of multiple face characteristic informations.
Finally, by multiple face characteristic information storages to acting the leading role in Face Sample Storehouse, process is set up in completion.
A specific example is named to illustrate above-mentioned to set up process.
Step 1：The initialization of sample library module, including characteristic model initialization, face preference parameter are set, each performer
The setting of sample size etc.；
Step 2：Performer's facial image is inputted by back-stage management user；
Step 3：According to the preset preference parameter of the face of system preliminary design, face validation checking is carried out to input picture, led to
Often ensure that face entreats position in the picture, face size is not less than the pixels of 64x 64, excludes side face etc.；If face validity is examined
Survey successfully, continue executing with step 4, otherwise skip to step 7 and exit whole flow process；
Step 4：Eyes positioning is carried out on the basis of the result of step 3；
Step 5：Feature extraction is carried out on the basis of deployment 3,4, and is converted into face characterization parameter；
Step 6：The face characterization parameter of calculating is registered into storage；Associate corresponding performer's attribute；
Step 7：Flow terminates.
It can be increased acting the leading role the face characteristic information in Face Sample Storehouse, be deleted, being changed, inquire about etc. and to operate, with
And extraction and the sign of face characteristic information.
The protagonist Face Sample Storehouse set up in the present invention has following features.
1) discrimination is higher；
2) system response time is fast, can quickly be run on platform, and the system resource needed is few；
3) small, each performer can provide much images, and quality can be ensured；
4) face Expressive Features allow to take more memory space.
Therefore, using technology provided by the present invention, the video pictures of featured performer of program can be extracted as poster,
So that program browsing is more directly perceived, attract user, the experience of user is greatly promoted.
Another aspect of the present invention provides a kind of poster generating means.
Referring to Fig. 4, Fig. 4 is a kind of structural representation for poster generating means that the present invention is provided.
A kind of poster generating means that the present invention is provided, applied to DTV cloud platform, including：
Determining module 401, determines to treat for the programm name in the DTV cloud platform and performer's concordance list
Handle video frequency program；
Image collection module 402, the image for obtaining key frame from the pending video frequency program；
Judge module 403, for judging whether described image meets human face scanning rule, the human face scanning rule is used for
Characterize the characteristic information that face is can recognize that from described image；
Matching module 404, if for meeting the human face scanning rule, scanning described image obtains face characteristic letter
Breath, and the face characteristic information is matched in the protagonist Face Sample Storehouse pre-set；
Output module 405, if for the match is successful, described image be output as associated with the programm name
Poster.
It is preferred that, in addition to：
Processing module, for carrying out enhancing processing to described image, obtains the enhancing higher than the definition of described image
Image；
Coding module, pending image is obtained for the enhancing image to be carried out into Image Coding；
The output module by the pending image specifically for being output as the poster associated with the programm name.
It is preferred that, the processing unit includes：
Subelement is cut, the black surround for detecting described image is cut to the black surround, obtain cutting image；
Subelement is scaled, for according to pre-defined poster resolution ratio, zooming in and out and being contracted to the cutting image
Put image；
Adjust subelement, for the brightness of the zoomed image, contrast and/or brightness according to default regulation rule
Compensate adjustment and obtain the enhancing image；The regulation rule is used to make the definition of the zoomed image higher.
It is preferred that, in addition to Sample Storehouse sets up module；
The Sample Storehouse, which sets up module, to be included：
Acquiring unit, for obtaining performer's title from performer's concordance list in the DTV cloud platform；
Setting unit, for obtaining the face screening conditions set by user；
First extraction unit, the standard faces of the face screening conditions are met for being obtained from preset facial image
Image；
Second extraction unit, the face characteristic information for extracting the standard faces image；
Associative cell, for the face characteristic information is associated with performer's title；
Unit is set up, includes the protagonist Face Sample Storehouse of multiple face characteristic informations for setting up.
It is preferred that, the face screening conditions entreat position, face size to be not less than the pictures of 64x 64 in the picture including face
Element and/or exclusion side face.
It should be noted that a kind of poster generating means of the present embodiment can use one kind in above method embodiment
Poster generation method, for realizing whole technical schemes in above method embodiment, the function of its modules can basis
Method in above method embodiment is implemented, and it implements process and can refer to associated description in above-described embodiment, this
Place is repeated no more.
The poster generating means that the embodiment of the present application is provided, applied to DTV cloud platform, described device cover half really
Root tuber determines pending video frequency program according to the programm name and performer's title in the DTV cloud platform；Image collection module
The image of key frame is obtained from the pending video frequency program；Judge module judges whether described image meets human face scanning rule
Then, the human face scanning rule is used to characterize the characteristic information that can recognize that face from described image；Matching module is used for
If meeting the human face scanning rule, scanning described image obtains face characteristic information, and the face characteristic information is existed
Matched in the protagonist Face Sample Storehouse pre-set；If the match is successful for output module, by described image be output as with
The associated poster of the programm name.The present invention simultaneously need not be participated in manually, greatly reduce workload, also, generation sea
The image of report is that the face in the image matched with Face Sample Storehouse, i.e. poster is the face acted the leading role, and can be brought to user
Most direct perception, improves the experience of user.
Finally, in addition it is also necessary to explanation, herein, such as first and second or the like relational terms be used merely to by
One entity or operation make a distinction with another entity or operation, and not necessarily require or imply these entities or operation
Between there is any this actual relation or order.Moreover, term " comprising ", "comprising" or its any other variant meaning
Covering including for nonexcludability, so that process, method, article or equipment including a series of key elements not only include that
A little key elements, but also other key elements including being not expressly set out, or also include be this process, method, article or
The intrinsic key element of equipment.In the absence of more restrictions, the key element limited by sentence "including a ...", is not arranged
Except also there is other identical element in the process including the key element, method, article or equipment.
The embodiment of each in this specification is described by the way of progressive, and what each embodiment was stressed is and other
Between the difference of embodiment, each embodiment identical similar portion mutually referring to.
The foregoing description of the disclosed embodiments, enables professional and technical personnel in the field to realize or use the application.
A variety of modifications to these embodiments will be apparent for those skilled in the art, as defined herein
General Principle can in other embodiments be realized in the case where not departing from spirit herein or scope.Therefore, the application
The embodiments shown herein is not intended to be limited to, and is to fit to and principles disclosed herein and features of novelty phase one
The most wide scope caused.
Claims (10)
1. a kind of poster generation method, applied to DTV cloud platform, it is characterised in that including：
Programm name and performer's title in the DTV cloud platform determine pending video frequency program；
The image of key frame is obtained from the pending video frequency program；
Judge whether described image meets human face scanning rule, the human face scanning rule is used for sign can from described image
Identify the characteristic information of face；
If so, then scanning described image obtains face characteristic information, and by the face characteristic information in the protagonist pre-set
The face characteristic information matched in Face Sample Storehouse with performer's title is matched；
If the match is successful, described image is output as to the poster associated with the programm name.
2. according to the method described in claim 1, it is characterised in that if after the match is successful, methods described also includes：
Enhancing processing is carried out to described image, the enhancing image higher than the definition of described image is obtained；
The enhancing image is subjected to Image Coding and obtains pending image；
Described image is output as into the poster associated with the programm name includes the pending image being output as and institute
State the associated poster of programm name.
3. method according to claim 2, it is characterised in that described to include to described image progress enhancing processing：
The black surround of described image is detected, the black surround is cut, obtains cutting image；
According to pre-defined poster resolution ratio, the cutting image is zoomed in and out and obtains zoomed image；
Adjustment is compensated according to default regulation rule to the brightness of the zoomed image, contrast and/or brightness and obtains institute
State enhancing image；The regulation rule is used to make the definition of the zoomed image higher.
4. the method according to claims 1 to 3 any one, it is characterised in that the protagonist face sample pre-set
This storehouse is set up through the following steps：
Performer's title is obtained from performer's concordance list in the DTV cloud platform；
Obtain the face screening conditions set by user；
The standard faces image for meeting the face screening conditions is obtained from preset facial image；
Extract the face characteristic information of the standard faces image；
The face characteristic information is associated with performer's title；
Foundation includes the protagonist Face Sample Storehouse of multiple face characteristic informations.
5. method according to claim 4, it is characterised in that the face screening conditions entreat position in the picture including face
Put, face size is not less than 64x64 pixels and/or excludes side face.
6. a kind of poster generating means, applied to DTV cloud platform, it is characterised in that including：
Determining module, pending video is determined for the programm name and performer's concordance list in the DTV cloud platform
Program；
Image collection module, the image for obtaining key frame from the pending video frequency program；
Judge module, for judging whether described image meets human face scanning rule, human face scanning rule be used to characterizing from
The characteristic information of face is can recognize that in described image；
Matching module, if for meeting human face scanning rule, scanning described image obtains face characteristic information, and by institute
Face characteristic information is stated to be matched in the protagonist Face Sample Storehouse pre-set；
Output module, if for the match is successful, described image to be output as to the poster associated with the programm name.
7. device according to claim 6, it is characterised in that also include：
Processing module, for carrying out enhancing processing to described image, obtains the enhancing image higher than the definition of described image；
Coding module, pending image is obtained for the enhancing image to be carried out into Image Coding；
The output module by the pending image specifically for being output as the poster associated with the programm name.
8. device according to claim 7, it is characterised in that the processing unit includes：
Subelement is cut, the black surround for detecting described image is cut to the black surround, obtain cutting image；
Subelement is scaled, for according to pre-defined poster resolution ratio, being zoomed in and out to the cutting image and obtaining scaling figure
Picture；
Subelement is adjusted, for being carried out to the brightness of the zoomed image, contrast and/or brightness according to default regulation rule
Compensation adjustment obtains the enhancing image；The regulation rule is used to make the definition of the zoomed image higher.
9. the device according to claim 6 to 8 any one, it is characterised in that also set up module including Sample Storehouse；
The Sample Storehouse, which sets up module, to be included：
Acquiring unit, for obtaining performer's title from performer's concordance list in the DTV cloud platform；
Setting unit, for obtaining the face screening conditions set by user；
First extraction unit, the standard faces figure of the face screening conditions is met for being obtained from preset facial image
Picture；
Second extraction unit, the face characteristic information for extracting the standard faces image；
Associative cell, for the face characteristic information is associated with performer's title；
Unit is set up, includes the protagonist Face Sample Storehouse of multiple face characteristic informations for setting up.
10. device according to claim 9, it is characterised in that the face screening conditions are entreated in the picture including face
Position, face size are not less than 64x64 pixels and/or exclusion side face.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710192648.7A CN106973324A (en) | 2017-03-28 | 2017-03-28 | A kind of poster generation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710192648.7A CN106973324A (en) | 2017-03-28 | 2017-03-28 | A kind of poster generation method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106973324A true CN106973324A (en) | 2017-07-21 |
Family
ID=59335619
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710192648.7A Pending CN106973324A (en) | 2017-03-28 | 2017-03-28 | A kind of poster generation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106973324A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108833939A (en) * | 2018-06-20 | 2018-11-16 | 北京优酷科技有限公司 | Generate the method and device of the poster of video |
| CN109241307A (en) * | 2018-08-29 | 2019-01-18 | 山东浪潮商用系统有限公司 | A kind of performers and clerks' contents management method and system |
| CN109271542A (en) * | 2018-09-28 | 2019-01-25 | 百度在线网络技术（北京）有限公司 | Cover determines method, apparatus, equipment and readable storage medium storing program for executing |
| WO2020253766A1 (en) * | 2019-06-19 | 2020-12-24 | 北京字节跳动网络技术有限公司 | Picture generation method and apparatus, electronic device, and storage medium |
| CN113010711A (en) * | 2021-04-01 | 2021-06-22 | 杭州初灵数据科技有限公司 | Method and system for automatically generating movie poster based on deep learning |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104751107A (en) * | 2013-12-30 | 2015-07-01 | 中国移动通信集团公司 | Key data determination method, device and equipment for video |
| CN105307003A (en) * | 2014-07-22 | 2016-02-03 | 三星电子株式会社 | Method and apparatus for displaying video |
-
2017
- 2017-03-28 CN CN201710192648.7A patent/CN106973324A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104751107A (en) * | 2013-12-30 | 2015-07-01 | 中国移动通信集团公司 | Key data determination method, device and equipment for video |
| CN105307003A (en) * | 2014-07-22 | 2016-02-03 | 三星电子株式会社 | Method and apparatus for displaying video |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108833939A (en) * | 2018-06-20 | 2018-11-16 | 北京优酷科技有限公司 | Generate the method and device of the poster of video |
| CN109241307A (en) * | 2018-08-29 | 2019-01-18 | 山东浪潮商用系统有限公司 | A kind of performers and clerks' contents management method and system |
| CN109271542A (en) * | 2018-09-28 | 2019-01-25 | 百度在线网络技术（北京）有限公司 | Cover determines method, apparatus, equipment and readable storage medium storing program for executing |
| WO2020253766A1 (en) * | 2019-06-19 | 2020-12-24 | 北京字节跳动网络技术有限公司 | Picture generation method and apparatus, electronic device, and storage medium |
| CN113010711A (en) * | 2021-04-01 | 2021-06-22 | 杭州初灵数据科技有限公司 | Method and system for automatically generating movie poster based on deep learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106973324A (en) | A kind of poster generation method and device | |
| KR102082816B1 (en) | Method for improving the resolution of streaming files | |
| CN110933490A (en) | Automatic adjustment method for picture quality and tone quality, smart television and storage medium | |
| CN110267061B (en) | News splitting method and system | |
| CN107180074A (en) | A kind of video classification methods and device | |
| US9076071B2 (en) | Logo recognition | |
| CN102484734A (en) | Transforming video data in accordance with three dimensional input formats | |
| DE112015005408T5 (en) | Systems and methods for identifying users who have viewed a television advertisement | |
| US20120213438A1 (en) | Method and apparatus for identifying video program material or content via filter banks | |
| CN108933935A (en) | Detection method, device, storage medium and the computer equipment of video communication system | |
| CN202998337U (en) | Video program identification system | |
| US20150249871A1 (en) | Information Push Method And System, Digital Television Receiving Terminal, And Computer Storage Medium | |
| CN103577421A (en) | Method, device and system applying two-dimension code | |
| CN106060537A (en) | Method and device for assessing video quality | |
| CN102999844A (en) | Intelligent anti-counterfeiting anti-channel-conflict inquiry and forensics method | |
| CN109660762A (en) | Size figure correlating method and device in intelligent candid device | |
| CN104333732B (en) | A kind of distributed video analysis method and system | |
| CN117056863B (en) | Big data processing method based on multi-mode data fusion | |
| CN114596259A (en) | Method, device, equipment and storage medium for determining reference-free video quality | |
| US11048946B2 (en) | System and method for identifying cognate image sequences | |
| CN109040784A (en) | Commercial detection method and device | |
| EP3905696A1 (en) | Image processing device and method | |
| CN107169004A (en) | A kind of property data base update method and device | |
| CN113569719B (en) | Video infringement judging method and device, storage medium and electronic equipment | |
| CN115499677A (en) | Audio and video synchronization detection method and device based on live broadcast |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 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 |
Application publication date: 20170721 |
|
| RJ01 | Rejection of invention patent application after publication |