CN106470358A - The video memory image-recognizing method of intelligent TV set and device - Google Patents
The video memory image-recognizing method of intelligent TV set and device Download PDFInfo
- Publication number
- CN106470358A CN106470358A CN201510519197.4A CN201510519197A CN106470358A CN 106470358 A CN106470358 A CN 106470358A CN 201510519197 A CN201510519197 A CN 201510519197A CN 106470358 A CN106470358 A CN 106470358A
- Authority
- CN
- China
- Prior art keywords
- picture
- identified
- currently
- pictures
- sub
- 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.)
- Granted
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
- H04N21/47—End-user applications
- H04N21/478—Supplemental services, e.g. displaying phone caller identification, shopping application
- H04N21/4781—Games
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/758—Involving statistics of pixels or of feature values, e.g. histogram matching
-
- 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
- H04N21/435—Processing of additional data, e.g. decrypting of additional data, reconstructing software from modules extracted from the transport stream
Abstract
The invention discloses a kind of video memory image-recognizing method of intelligent TV set, when said method has game class application to start on intelligent TV set, obtain the bag name of application and the resolution of intelligent TV set;And obtain the picture to be identified prestoring and its attribute from high in the clouds;Read picture frame by frame from video memory, intercept from the picture reading and the currently original position of picture to be identified and equivalently-sized sub-pictures;Whether preset value is more than or equal to, and/or whether the word color accounting of sub-pictures is identical with the word color accounting of picture to be identified, and currently picture to be identified is identified according to the image similarity of sub-pictures and currently picture to be identified.The present invention need not change application, you can perception television content, and the process for following generation action provides preparation.
Description
Technical field
The present invention relates to image processing field, the video memory image recognition side of more particularly, to a kind of intelligent TV set
Method and device.
Background technology
Intelligent television, is with full open model platform, is equipped with operating system, and user is appreciating commonly electricity
While depending on content, can voluntarily install and uninstall types of applications software, persistently function be expanded and rise
The new tv product of level.Intelligent television can constantly be brought to be different to user and be connect using cable digital TV
Receipts machine (Set Top Box), abundant individualized experience.Wherein, game is played by intelligent TV set, just
It is wherein most popular experience;Existing object for appreciation by intelligent TV set is played, and needs game player's moment
Dig-in game, carry out instruction in time when needing operation to issue, to be played or to be continued flow process;
This often makes game player to not miss important scenes, to abandon own physiological demand as cost, or
Person's spiritual high concentration for a long time, threat game player's is healthy.Either with or without a kind of method, permissible
Come in important scenes interim, allow player to perceive.Existing intelligent television can't perceive television content.
Content of the invention
It is an object of the present invention to provide a kind of video memory image-recognizing method of intelligent TV set and device, with
So that when user wants the frame known to arrive, perceiving in time.
The invention discloses a kind of video memory image-recognizing method of intelligent TV set, said method is in intelligent electricity
During depending on there being game class application to start on machine, execute following steps:
Step one:Obtain the bag name of above-mentioned application and the resolution of intelligent TV set;
Step 2:According to above-mentioned bag name and resolution, obtain the picture to be identified prestoring and its genus from high in the clouds
Property;
Step 3:Picture is read frame by frame from video memory;
Step 4:Intercept from the picture of above-mentioned reading and the currently original position of picture to be identified and size
Identical sub-pictures;
Step 5:Whether it is more than or equal to according to the image similarity of above-mentioned sub-pictures and currently picture to be identified
Preset value, and/or the word color accounting of the above-mentioned sub-pictures whether word color accounting with picture to be identified
Identical, currently picture to be identified is identified.
In said method, above-mentioned picture to be identified includes image graphic and/or word picture, above-mentioned image graph
Piece attribute includes picture original position and size;Above-mentioned word picture attribute includes picture original position, chi
Very little and word color accounting.
In said method, said method calculates the figure of sub-pictures and currently picture to be identified as follows
As similarity:
Calculate the grey Color Histogram of above-mentioned sub-pictures and current picture to be identified;
Calculate above-mentioned Lycoperdon polymorphum Vitt histogrammic Pasteur coefficient, obtain above-mentioned sub-pictures and currently picture to be identified
Image similarity.
In said method, above-mentioned steps five specifically include following steps:
Step a:Judge the type of currently picture to be identified;If currently picture to be identified is image graphic,
Execution step b;If currently picture to be identified is word picture, execution step c;If currently figure to be identified
Piece includes image graphic and word picture, then execution step d;
Step b:Calculate the image similarity of sub-pictures and currently picture to be identified, and judge above-mentioned similar
Whether degree is more than or equal to preset value, and if so, then currently picture recognition success to be identified, proceeds to step l;No
Then, execution step k;
Step c:Calculate the word color accounting of sub-pictures, and judge whether the literary composition with currently picture to be identified
Word color accounting is identical, and if so, then currently picture recognition success to be identified, proceeds to step l;Otherwise, hold
Row step k;
Step d:Read default recognition method, if image is preferential, then execution step e;If word
Preferentially, then execution step g;If image and word same priority, then execution step i;
Step e:Calculate the image similarity of sub-pictures and currently picture to be identified, and judge above-mentioned similarity
Whether it is more than or equal to preset value, if so, then currently picture recognition success to be identified, proceeds to step l;Otherwise,
Execution step f;
Step f:Calculate the word color accounting of sub-pictures, and judge whether the literary composition with currently picture to be identified
Word color accounting is identical, and if so, then currently picture recognition success to be identified, proceeds to step l;Otherwise, hold
Row step k;
Step g:Calculate the word color accounting of sub-pictures, and judge whether and currently picture to be identified
Word color accounting is identical, and if so, then currently picture recognition success to be identified, proceeds to step l;Otherwise,
Execution step h;
Step h:Calculate the image similarity of sub-pictures and currently picture to be identified, and judge above-mentioned similar
Whether degree is more than or equal to preset value, and if so, then currently picture recognition success to be identified, proceeds to step l;No
Then, execution step k;
Step i:Calculate the image similarity of sub-pictures and currently picture to be identified, and judge above-mentioned similarity
Whether it is more than or equal to preset value, if so, then execution step j;Otherwise, execution step k;
Step j:Calculate the word color accounting of sub-pictures, and judge whether the literary composition with currently picture to be identified
Word color accounting is identical, and if so, then currently picture recognition success to be identified, proceeds to step l;Otherwise, hold
Row step k;
Step k:Whether the picture judging current identification is last in picture to be identified, if so,
Then execution step l;Otherwise, next picture to be identified is proceeded to step 4 execution;
Step l:Read the next frame picture in video memory, remaining picture to be identified is proceeded to step 4 execution.
In said method, the grey Color Histogram of above-mentioned picture calculates as follows:
Length according to picture and width, calculate the pixel sum of picture and the pixel value of each pixel, then
According to the pixel value of each pixel, calculate red (r=(pixel>>16) &0xFF), green (g=(pixel>>8)
&0xFF), blue (b=(pixel>>0) &0xFF) ratio value in pixel value, then according to formula:
Color=0.299*r+0.587*g+0.114*b
Calculate ashing color-values color of current pixel;
Wherein, r is red ratio value in the pixel value of current pixel point;G is green in current pixel point
Pixel value in accounting value;B is green ratio value in the pixel value of current pixel point;
Ratio value in pixel sum for ashing color-values color of calculating current pixel;
Ratio value in pixel sum for ashing color-values color of all pixels of picture forms this figure
The grey Color Histogram of piece.
In said method, above-mentioned Pasteur's coefficient is calculated by equation below:
Wherein, i is the sequence number of element in grey Color Histogram, and its initial value is 0;N is that Lycoperdon polymorphum Vitt is histogrammic
Length;Ai represents i-th element in sub-pictures ash Color Histogram;Bi represents the Lycoperdon polymorphum Vitt of picture to be identified
I-th element in rectangular histogram.
The present invention further discloses a kind of video memory pattern recognition device of intelligent TV set, said apparatus bag
Include monitoring modular, data processing module and picture recognition module, wherein, above-mentioned
Detection module, for monitoring whether intelligent television has game class application to start, and is having game class to answer
During with starting, notify above-mentioned data processing module;
Data processing module:For obtaining the bag name of application and the resolution of intelligent TV set;And according to upper
State bag name and resolution, obtain the picture to be identified prestoring and its attribute from high in the clouds;
Picture recognition module, for reading picture frame by frame from video memory;And cut from the picture of above-mentioned reading
Take and the currently original position of picture to be identified and equivalently-sized sub-pictures;And according to above-mentioned sub-pictures
Whether it is more than or equal to preset value with the image similarity of currently picture to be identified, and/or the literary composition of above-mentioned sub-pictures
Whether word color accounting is identical with the word color accounting of picture to be identified, and currently picture to be identified is carried out
Identification.
In said method, above-mentioned picture recognition module is additionally operable to calculate sub-pictures and current picture to be identified
Grey Color Histogram and Lycoperdon polymorphum Vitt histogrammic Pasteur coefficient;And for judging the type of currently picture to be identified
And default recognition method.
The present invention is in the case of need not changing application, you can perception television content, and then occurs for following
The process of action provides preparation;Make intelligent television more intelligent.
Brief description
Accompanying drawing described herein is used for providing a further understanding of the present invention, constitutes of the present invention
Point, the schematic description and description of the present invention is used for explaining the present invention, does not constitute to the present invention's
Improper restriction.In the accompanying drawings:
Fig. 1 is the flow process of the video memory image-recognizing method preferred embodiment of intelligent TV set of the present invention
Figure;
Fig. 2 is the principle frame of the preferred embodiment of intelligent TV set video memory pattern recognition device of the present invention
Figure.
Specific embodiment
In order that the technical problem to be solved, technical scheme and beneficial effect are clearer, bright
In vain, below in conjunction with drawings and Examples, the present invention will be described in further detail.It should be appreciated that this
The described specific embodiment in place, only in order to explain the present invention, is not intended to limit the present invention.
As shown in figure 1, being the video memory image-recognizing method preferred embodiment of intelligent TV set of the present invention
Flow chart;In the present embodiment, intelligent television adopts Android system;Specifically include following steps:
Step S001:Whether there is game class application to start on monitoring intelligent TV set, if so, then execute step
Rapid S002;Otherwise, continue executing with this step;
Step S002:Obtain bag name and the television set resolution of above-mentioned application;
Step S003:According to above-mentioned bag name and resolution, from high in the clouds obtain the picture to be identified prestoring and its
Attribute;
Picture to be identified includes image graphic and/or word picture, and above-mentioned image graphic attribute includes picture to be risen
Beginning position and size;Above-mentioned word picture attribute includes picture original position, size and word color accounting.
The picture to be identified obtaining from high in the clouds and its attribute can be saved in locally by this step;
Step S004:Picture is read frame by frame from video memory;
Step S005:Intercept and the currently original position of picture to be identified and chi from the current picture reading
Very little identical sub-pictures;
Step S006:Whether it is more than or equal in advance according to the image similarity of sub-pictures and currently picture to be identified
If value, and/or the word color accounting of the above-mentioned sub-pictures whether word color accounting phase with picture to be identified
With identification currently picture to be identified;This step specifically includes following steps:
Step S0061:Judge the type of currently picture to be identified;If currently picture to be identified is image graph
Piece, then execution step S0062;If currently picture to be identified is word picture, execution step S0063;
If currently picture to be identified includes image graphic and word picture, execution step S0064;
Step S0062:Calculate the image similarity of sub-pictures and currently picture to be identified, and judge above-mentioned
Whether similarity is more than or equal to preset value S, and if so, then currently picture recognition success to be identified, currently treats
Identification picture processing terminates;Otherwise, currently picture recognition failure to be identified, currently picture processing to be identified
Terminate;
The present invention calculates the image similarity p of sub-pictures and currently picture to be identified as follows:
Calculate the grey Color Histogram of above-mentioned sub-pictures and current picture to be identified;The histogrammic concrete meter of Lycoperdon polymorphum Vitt
Calculation process is as follows:
Length according to picture and width, calculate the pixel sum of picture and the pixel value of each pixel, then
According to the pixel value of each pixel, calculate red (r=(pixel>>16) &0xFF), green (g=(pixel>>8)
&0xFF), blue (b=(pixel>>0) &0xFF) ratio value in pixel value, then according to formula
Color=0.299*r+0.587*g+0.114*b
Calculate ashing color-values color of current pixel, wherein, r is the red pixel value in current pixel point
In ratio value;G is green accounting value in the pixel value of current pixel point;B is green in current pixel
Ratio value in the pixel value of point;
Finally ratio value in pixel sum for ashing color-values color of calculating current pixel;
Ratio value in pixel sum for ashing color-values color of all pixels forms array L, and L is
Grey Color Histogram for picture.
According to sub-pictures and the currently grey Color Histogram of picture to be identified and equation below:
Calculate Pasteur's FACTOR P of above-mentioned sub-pictures and current picture to be identified, P value be above-mentioned sub-pictures and
The currently image similarity of picture to be identified;
Wherein, i is the sequence number of element in grey Color Histogram, and its initial value is 0;N is that Lycoperdon polymorphum Vitt is histogrammic
Length;Ai represents i-th element in sub-pictures ash Color Histogram;Bi represents the Lycoperdon polymorphum Vitt of picture to be identified
I-th element in rectangular histogram;Because sub-pictures are identical with the size of currently picture to be identified, therefore they
Histogrammic length n of Lycoperdon polymorphum Vitt identical;
Step S0063:Calculate the word color accounting of sub-pictures, and judge whether and currently figure to be identified
The word color accounting of piece is identical, if so, then currently picture recognition success to be identified, currently figure to be identified
Piece process terminates;Otherwise, currently picture recognition failure to be identified, currently picture processing to be identified terminates;
The word color accounting of sub-pictures be sub-pictures in currently picture to be identified in word color phase
Same color accounts for the percentage ratio of above-mentioned sub-pictures;
Step S0064:Check default recognition method, if image is preferential, then execution step S0065;
If word is preferential, then execution step S0067;If image and word same priority, then execution step
S0069;
Step S0065:Calculate the image similarity of sub-pictures and currently picture to be identified, and judge above-mentioned
Whether similarity is more than or equal to preset value S, and if so, then currently picture recognition success to be identified, currently treats
Identification picture processing terminates;Otherwise, execution step S0066;
Step S0066:Calculate the word color accounting of sub-pictures, and judge whether and currently figure to be identified
The word color accounting of piece is identical, if so, then currently picture recognition success to be identified, currently figure to be identified
Piece process terminates;Otherwise, currently picture recognition failure to be identified, currently picture processing to be identified terminates;
Step S0067:Calculate the word color accounting of sub-pictures, and judge whether and currently figure to be identified
The word color accounting of piece is identical, if so, then currently picture recognition success to be identified, currently figure to be identified
Piece process terminates;Otherwise, execution step S0068;
Step S0068:Calculate the image similarity of sub-pictures and currently picture to be identified, and judge above-mentioned
Whether similarity is more than or equal to preset value S, and if so, then currently picture recognition success to be identified, currently treats
Identification picture processing terminates;Otherwise, currently picture recognition failure to be identified, currently picture processing to be identified
Terminate;
Step S0069:Calculate the image similarity of sub-pictures and currently picture to be identified, and judge above-mentioned
Whether similarity is more than or equal to preset value S, if so, then execution step S0070;Otherwise, currently to be identified
Picture recognition failure, currently picture processing to be identified terminates;
Step S0070:Calculate the word color accounting of sub-pictures, and judge whether and currently figure to be identified
The word color accounting of piece is identical, if so, then currently picture recognition success to be identified, currently figure to be identified
Piece process terminates;Otherwise, currently picture recognition failure to be identified, currently picture processing to be identified terminates;
Step S007:Whether interpretation identifies successfully, if so, then execution step S008;Otherwise, execute step
Rapid S009;
Step S008:Read the next frame picture in video memory, and step is proceeded to remaining picture to be identified
S005 executes;
Step S009:Whether the picture judging current identification is last in picture to be identified, if so,
Then execution step S008;Otherwise, execution step S010;
Step S010:Next picture to be identified is proceeded to the execution of step S005.
As shown in Fig. 2 being the preferred embodiment of the present invention above-mentioned intelligent TV set video memory pattern recognition device
Theory diagram;The present embodiment includes monitoring modular 10, data processing module 20 and picture recognition module
30, wherein, above-mentioned
Detection module 10, for monitoring whether intelligent television has game class application to start, and is having game class
When application starts, notify data processing module 20;
Data processing module 20:For obtaining the bag name of application and the resolution of intelligent TV set;And according to
Above-mentioned bag name and resolution, obtain the picture to be identified prestoring and its attribute from high in the clouds;
Picture recognition module 30, for reading picture frame by frame from video memory;And from the picture of above-mentioned reading
Intercept and the currently original position of picture to be identified and equivalently-sized sub-pictures;Calculate sub-pictures and current
The grey Color Histogram of picture to be identified and Lycoperdon polymorphum Vitt histogrammic Pasteur coefficient;Judge currently picture to be identified
Type and default recognition method;And according to the currently type of picture to be identified, default recognition method
And whether sub-pictures are more than or equal to preset value and/or above-mentioned son with the image similarity of currently picture to be identified
Whether the word color accounting of picture is identical with the word color accounting of picture to be identified, to currently to be identified
Picture is identified.
Described above illustrate and describes the preferred embodiments of the present invention, but as previously mentioned it should be understood that this
Invention is not limited to form disclosed herein, is not to be taken as the exclusion to other embodiment, and can
For various other combinations, modification and environment, and can pass through in invention contemplated scope described herein
The technology of above-mentioned teaching or association area or knowledge are modified.And the change that those skilled in the art are carried out and
Change, then all should be in the protection domain of claims of the present invention without departing from the spirit and scope of the present invention
Interior.
Claims (8)
1. a kind of video memory image-recognizing method of intelligent TV set is it is characterised in that methods described is in intelligence
When having game class application to start on energy television set, execute following steps:
Step one:Obtain the bag name of described application and the resolution of intelligent TV set;
Step 2:According to described bag name and resolution, obtain the picture to be identified prestoring and its genus from high in the clouds
Property;
Step 3:Picture is read frame by frame from video memory;
Step 4:Intercept from the picture of described reading and the currently original position of picture to be identified and size
Identical sub-pictures;
Step 5:Whether it is more than or equal to according to the image similarity of described sub-pictures and currently picture to be identified
Preset value, and/or whether the word color accounting of described sub-pictures accounted for the word color of picture to be identified
Ratio is identical, and currently picture to be identified is identified.
2. the method for claim 1 is it is characterised in that described picture to be identified includes image
Picture and/or word picture, described image picture attribute includes picture original position and size;Described literary composition
Word picture attribute includes picture original position, size and word color accounting.
3. the method for claim 1 is it is characterised in that methods described is counted as follows
The image similarity of operator picture and currently picture to be identified:
Calculate the grey Color Histogram of described sub-pictures and current picture to be identified;
Calculate described Lycoperdon polymorphum Vitt histogrammic Pasteur coefficient, obtain described sub-pictures and currently picture to be identified
Image similarity.
4. the method for claim 1 it is characterised in that described step 5 specifically include following
Step:
Step a:Judge the type of currently picture to be identified;If currently picture to be identified is image graphic,
Then execution step b;If currently picture to be identified is word picture, execution step c;If currently waiting to know
Other picture includes image graphic and word picture, then execution step d;
Step b:Calculate the image similarity of sub-pictures and currently picture to be identified, and judge described similar
Whether degree is more than or equal to preset value, and if so, then currently picture recognition success to be identified, proceeds to step l;
Otherwise, execution step k;
Step c:Calculate the word color accounting of sub-pictures, and judge whether and currently picture to be identified
Word color accounting is identical, and if so, then currently picture recognition success to be identified, proceeds to step l;No
Then, execution step k;
Step d:Read default recognition method, if image is preferential, then execution step e;If civilian
Word is preferential, then execution step g;If image and word same priority, then execution step i;
Step e:Calculate the image similarity of sub-pictures and currently picture to be identified, and judge described similar
Whether degree is more than or equal to preset value, and if so, then currently picture recognition success to be identified, proceeds to step l;
Otherwise, execution step f;
Step f:Calculate the word color accounting of sub-pictures, and judge whether and currently picture to be identified
Word color accounting is identical, and if so, then currently picture recognition success to be identified, proceeds to step l;No
Then, execution step k;
Step g:Calculate the word color accounting of sub-pictures, and judge whether and currently picture to be identified
Word color accounting is identical, and if so, then currently picture recognition success to be identified, proceeds to step l;No
Then, execution step h;
Step h:Calculate the image similarity of sub-pictures and currently picture to be identified, and judge described similar
Whether degree is more than or equal to preset value, and if so, then currently picture recognition success to be identified, proceeds to step l;
Otherwise, execution step k;
Step i:Calculate the image similarity of sub-pictures and currently picture to be identified, and judge described similar
Whether degree is more than or equal to preset value, if so, then execution step j;Otherwise, execution step k;
Step j:Calculate the word color accounting of sub-pictures, and judge whether and currently picture to be identified
Word color accounting is identical, and if so, then currently picture recognition success to be identified, proceeds to step l;No
Then, execution step k;
Step k:Whether the picture judging current identification is last in picture to be identified, if so,
Then execution step l;Otherwise, next picture to be identified is proceeded to step 4 execution;
Step l:Read the next frame picture in video memory, step 4 is proceeded to remaining picture to be identified and holds
OK.
5. method as claimed in claim 3 is it is characterised in that the grey Color Histogram of described picture leads to
Cross following steps to calculate:
Length according to picture and width, calculate the pixel sum of picture and the pixel value of each pixel,
Further according to the pixel value of each pixel, calculate red (r=(pixel>>16) &0xFF), green (g=(pixel
>>8) &0xFF), blue (b=(pixel>>0) &0xFF) ratio value in pixel value, then basis
Formula:
Color=0.299*r+0.587*g+0.114*b
Calculate ashing color-values color of current pixel;
Wherein, r is red ratio value in the pixel value of current pixel point;G is green in current pixel point
Pixel value in accounting value;B is green ratio value in the pixel value of current pixel point;
Ratio value in pixel sum for ashing color-values color of calculating current pixel;
Ratio value in pixel sum for ashing color-values color of all pixels of picture forms this figure
The grey Color Histogram of piece.
6. method as claimed in claim 3 is it is characterised in that described Pasteur's coefficient passes through public affairs as follows
Formula calculates:
Wherein, i is the sequence number of element in grey Color Histogram, and its initial value is 0;N is grey Color Histogram
Length;Ai represents i-th element in sub-pictures ash Color Histogram;Bi represents the ash of picture to be identified
I-th element in Color Histogram.
7. a kind of video memory pattern recognition device of intelligent TV set is it is characterised in that described device includes
Monitoring modular, data processing module and picture recognition module, wherein, described
Detection module, for monitoring whether intelligent television has game class application to start, and is having game class to answer
During with starting, notify described data processing module;
Data processing module:For obtaining the bag name of application and the resolution of intelligent TV set;And according to institute
State bag name and resolution, obtain the picture to be identified prestoring and its attribute from high in the clouds;
Picture recognition module, for reading picture frame by frame from video memory;And cut from the picture of described reading
Take and the currently original position of picture to be identified and equivalently-sized sub-pictures;And according to described sub-pictures
Whether it is more than or equal to preset value with the image similarity of currently picture to be identified, and/or described sub-pictures
Whether word color accounting is identical with the word color accounting of picture to be identified, and currently picture to be identified is entered
Row identification.
8. device as claimed in claim 7 is it is characterised in that described picture recognition module is additionally operable to
Calculating sub-pictures and the currently grey Color Histogram of picture to be identified and Lycoperdon polymorphum Vitt histogrammic Pasteur coefficient;And
For judging the currently type of picture to be identified and default recognition method.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510519197.4A CN106470358B (en) | 2015-08-21 | 2015-08-21 | Video memory image identification method and device of smart television |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510519197.4A CN106470358B (en) | 2015-08-21 | 2015-08-21 | Video memory image identification method and device of smart television |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106470358A true CN106470358A (en) | 2017-03-01 |
CN106470358B CN106470358B (en) | 2020-09-25 |
Family
ID=58228930
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510519197.4A Expired - Fee Related CN106470358B (en) | 2015-08-21 | 2015-08-21 | Video memory image identification method and device of smart television |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106470358B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107509115A (en) * | 2017-08-29 | 2017-12-22 | 武汉斗鱼网络科技有限公司 | A kind of method and device for obtaining live middle Wonderful time picture of playing |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6590999B1 (en) * | 2000-02-14 | 2003-07-08 | Siemens Corporate Research, Inc. | Real-time tracking of non-rigid objects using mean shift |
CN101790049A (en) * | 2010-02-25 | 2010-07-28 | 深圳市茁壮网络股份有限公司 | Newscast video segmentation method and system |
CN102222227A (en) * | 2011-04-25 | 2011-10-19 | 中国华录集团有限公司 | Video identification based system for extracting film images |
CN103325124A (en) * | 2012-03-21 | 2013-09-25 | 东北大学 | Target detecting and tracking system and method using background differencing method based on FPGA |
CN104754367A (en) * | 2015-04-07 | 2015-07-01 | 腾讯科技(北京)有限公司 | Multimedia information processing method and device |
CN104811787A (en) * | 2014-10-27 | 2015-07-29 | 深圳市腾讯计算机系统有限公司 | Game video recording method and game video recording device |
-
2015
- 2015-08-21 CN CN201510519197.4A patent/CN106470358B/en not_active Expired - Fee Related
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6590999B1 (en) * | 2000-02-14 | 2003-07-08 | Siemens Corporate Research, Inc. | Real-time tracking of non-rigid objects using mean shift |
CN101790049A (en) * | 2010-02-25 | 2010-07-28 | 深圳市茁壮网络股份有限公司 | Newscast video segmentation method and system |
CN102222227A (en) * | 2011-04-25 | 2011-10-19 | 中国华录集团有限公司 | Video identification based system for extracting film images |
CN103325124A (en) * | 2012-03-21 | 2013-09-25 | 东北大学 | Target detecting and tracking system and method using background differencing method based on FPGA |
CN104811787A (en) * | 2014-10-27 | 2015-07-29 | 深圳市腾讯计算机系统有限公司 | Game video recording method and game video recording device |
CN104754367A (en) * | 2015-04-07 | 2015-07-01 | 腾讯科技(北京)有限公司 | Multimedia information processing method and device |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107509115A (en) * | 2017-08-29 | 2017-12-22 | 武汉斗鱼网络科技有限公司 | A kind of method and device for obtaining live middle Wonderful time picture of playing |
Also Published As
Publication number | Publication date |
---|---|
CN106470358B (en) | 2020-09-25 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11170210B2 (en) | Gesture identification, control, and neural network training methods and apparatuses, and electronic devices | |
CN107105310B (en) | Human image replacing method and device in video live broadcast and recording and broadcasting system | |
Hsieh et al. | A real time hand gesture recognition system using motion history image | |
CN110555796B (en) | Image adjusting method, device, storage medium and equipment | |
CN109816769A (en) | Scene based on depth camera ground drawing generating method, device and equipment | |
SG11202000063SA (en) | Access control method, access control apparatus, system, and storage medium | |
US20140240311A1 (en) | Method and device for performing transition between street view images | |
EP3860133A1 (en) | Audio and video quality enhancement method and system employing scene recognition, and display device | |
CN113377198B (en) | Screen saver interaction method and device, electronic equipment and storage medium | |
CN110175980A (en) | Image definition recognition methods, image definition identification device and terminal device | |
CN108665541B (en) | A kind of ground drawing generating method and device and robot based on laser sensor | |
CN102982336A (en) | Method and system for recognition model generation | |
JP2018045608A5 (en) | ||
CN105915793A (en) | Intelligent watch shooting processing method and device | |
CN107179981A (en) | A kind of method of game resource optimization | |
CN104185012B (en) | 3 D video form automatic testing method and device | |
CN112070137A (en) | Training data set generation method, target object detection method and related equipment | |
CN108520263A (en) | A kind of recognition methods of panoramic picture, system and computer storage media | |
CN107609465A (en) | A kind of multi-dimension testing method for Face datection | |
CN106816054A (en) | For the interactive teaching method and terminal of intelligent robot | |
CN106470358A (en) | The video memory image-recognizing method of intelligent TV set and device | |
CN103139591A (en) | Three dimensional (3D) video color automatic revising method based on graph processor | |
CN116152121B (en) | Curved surface screen generating method and correcting method based on distortion parameters | |
CN113778233B (en) | Method and device for controlling display equipment and readable medium | |
CN109241885A (en) | A kind of method and device of special area in intelligent recognition video |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20200925 Termination date: 20210821 |
|
CF01 | Termination of patent right due to non-payment of annual fee |