CN106470358B - Video memory image identification method and device of smart television - Google Patents
Video memory image identification method and device of smart television Download PDFInfo
- Publication number
- CN106470358B CN106470358B CN201510519197.4A CN201510519197A CN106470358B CN 106470358 B CN106470358 B CN 106470358B CN 201510519197 A CN201510519197 A CN 201510519197A CN 106470358 B CN106470358 B CN 106470358B
- Authority
- CN
- China
- Prior art keywords
- picture
- recognized
- identified
- current picture
- 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.)
- Expired - Fee Related
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—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 OR CALCULATING; 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 OR CALCULATING; 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Signal Processing (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a video memory image identification method of an intelligent television, which is characterized in that when a game application is started on the intelligent television, the package name of the application and the resolution of the intelligent television are obtained; acquiring a pre-stored picture to be identified and the attribute thereof from the cloud; reading pictures frame by frame from a video memory, and intercepting a sub-picture with the same initial position and size as the current picture to be identified from the read pictures; and identifying the current picture to be identified according to whether the image similarity between the sub-picture and the current picture to be identified is larger than or equal to a preset value and/or whether the character color ratio of the sub-picture is the same as the character color ratio of the picture to be identified. The invention can sense the television content without modifying the application, and provides preparation for processing actions in the future.
Description
Technical Field
The invention relates to the field of image processing, in particular to a video memory image identification method and device of an intelligent television.
Background
The intelligent television is a new television product which is provided with a full-open platform, carries an operating system, and can automatically install and uninstall various application software and continuously expand and upgrade functions while users enjoy common television contents. The smart television can continuously bring rich personalized experience to users different from the experience of using a cable digital television receiver (set top box). The game playing through the intelligent television is the most popular experience; the existing game playing through the intelligent television requires a game player to stare at the game all the time so as to issue an instruction in time when operation is required to be carried out to play the game or continue the process; this often causes the game player to be at the cost of giving up his own physiological needs or to be highly concentrated for a long time in order not to miss important scenes, threatening the physical health of the game player. There is no method for the player to perceive the scene in an important scene. The existing smart televisions are not capable of perceiving television content.
Disclosure of Invention
The invention aims to provide a video memory image identification method and device of an intelligent television, so that a user can sense the arrival of a frame which the user wants to know in time.
The invention discloses a video memory image identification method of an intelligent television, which executes the following steps when a game application is started on the intelligent television:
the method comprises the following steps: acquiring the package name of the application and the resolution of the intelligent television;
step two: according to the packet name and the resolution, acquiring a pre-stored picture to be identified and the attribute thereof from the cloud;
step three: reading pictures from a video memory frame by frame;
step four: intercepting a sub-picture with the same initial position and size as the current picture to be identified from the read picture;
step five: and identifying the current picture to be identified according to whether the image similarity between the sub-picture and the current picture to be identified is larger than or equal to a preset value and/or whether the character color ratio of the sub-picture is the same as the character color ratio of the picture to be identified.
In the method, the picture to be identified comprises an image picture and/or a character picture, and the image picture attribute comprises a picture initial position and a picture initial size; the text and picture attributes comprise a picture starting position, a size and a text color ratio.
In the method, the image similarity between the sub-picture and the current picture to be identified is calculated by the following steps:
calculating gray histograms of the sub-picture and the current picture to be identified;
and calculating the Babbitt coefficient of the gray histogram to obtain the image similarity of the sub-picture and the current picture to be identified.
In the above method, the fifth step specifically includes the following steps:
step a: judging the type of the current picture to be identified; if the current picture to be identified is an image picture, executing the step b; if the current picture to be identified is a character picture, executing the step c; if the current picture to be identified comprises an image picture and a character picture, executing the step d;
step b: calculating the image similarity between the sub-picture and the current picture to be recognized, judging whether the similarity is larger than or equal to a preset value, if so, successfully recognizing the current picture to be recognized, and turning to the step l; otherwise, executing step k;
step c: calculating the character color ratio of the sub-picture, judging whether the character color ratio is the same as the character color ratio of the current picture to be recognized, if so, successfully recognizing the current picture to be recognized, and turning to the step l; otherwise, executing step k;
step d: reading a preset identification mode, and if the image is in priority, executing the step e; if the characters are preferred, executing the step g; if the image and the characters have the same priority, executing the step i;
step e: calculating the image similarity between the sub-picture and the current picture to be recognized, judging whether the similarity is larger than or equal to a preset value, if so, successfully recognizing the current picture to be recognized, and turning to the step l; otherwise, executing step f;
step f: calculating the character color ratio of the sub-picture, judging whether the character color ratio is the same as the character color ratio of the current picture to be recognized, if so, successfully recognizing the current picture to be recognized, and turning to the step l; otherwise, executing step k;
step g: calculating the character color ratio of the sub-picture, judging whether the character color ratio is the same as the character color ratio of the current picture to be recognized, if so, successfully recognizing the current picture to be recognized, and turning to the step l; otherwise, executing step h;
step h: calculating the image similarity between the sub-picture and the current picture to be recognized, judging whether the similarity is larger than or equal to a preset value, if so, successfully recognizing the current picture to be recognized, and turning to the step l; otherwise, executing step k;
step i: calculating the image similarity of the sub-picture and the current picture to be identified, judging whether the similarity is greater than or equal to a preset value, and if so, executing the step j; otherwise, executing step k;
step j: calculating the character color ratio of the sub-picture, judging whether the character color ratio is the same as the character color ratio of the current picture to be recognized, if so, successfully recognizing the current picture to be recognized, and turning to the step l; otherwise, executing step k;
step k: judging whether the current identified picture is the last picture in the pictures to be identified, if so, executing the step l; otherwise, the next picture to be identified is executed in the fourth step;
step l: and reading the next frame of picture in the video memory, and turning to the step four to execute the residual pictures to be identified.
In the method, the gray histogram of the picture is calculated by the following steps:
calculating the total number of pixel points of the picture and the pixel value of each pixel point according to the length and the width of the picture, calculating the proportion value of red (r ═ 16) &0xFF), green (g ═ 8) &0xFF) and blue (b ═ 0) &0xFF) in the pixel value according to the pixel value of each pixel point, and then according to a formula:
color＝0.299*r+0.587*g+0.114*b
calculating an ashing color value color of the current pixel;
wherein r is the proportion value of red in the pixel value of the current pixel point; g is the occupation ratio of green in pixel values of the current pixel point; b is the proportion value of green in the pixel value of the current pixel point;
calculating the proportion value of the ashing color value color of the current pixel in the total number of the pixel points;
and the proportion values of the ashing color values color of all the pixels of the picture in the total number of the pixels form a gray histogram of the picture.
In the above method, the above babbitt coefficient is calculated by the following formula:
wherein, i is the serial number of the elements in the gray histogram, and the initial value is 0; n is the length of the grey histogram; ai represents the ith element in the gray histogram of the sub-picture; bi represents the ith element in the grey histogram of the picture to be recognized.
The invention further discloses a video memory image recognition device of the intelligent television, which comprises a monitoring module, a data processing module and an image recognition module, wherein the monitoring module, the data processing module and the image recognition module are arranged in the video memory image recognition device
The detection module is used for monitoring whether the game application is started or not and informing the data processing module when the game application is started;
a data processing module: the method comprises the steps of obtaining the package name of an application and the resolution of the intelligent television; according to the packet name and the resolution, acquiring a pre-stored picture to be identified and the attribute thereof from the cloud;
the picture identification module is used for reading pictures from the video memory frame by frame; intercepting a sub-picture with the same initial position and size as the current picture to be identified from the read picture; and identifying the current picture to be identified according to whether the image similarity between the sub-picture and the current picture to be identified is larger than or equal to a preset value and/or whether the character color ratio of the sub-picture is the same as the character color ratio of the picture to be identified.
In the method, the picture identification module is further used for calculating gray histograms of the sub-picture and the current picture to be identified and the Babbitt coefficient of the gray histogram; and the image recognition module is used for judging the type of the current image to be recognized and a preset recognition mode.
The invention can sense the TV content without modifying the application, thereby providing preparation for the processing of future action; the intelligent television is more intelligent.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the invention and not to limit the invention. In the drawings:
fig. 1 is a flowchart of a video memory image recognition method of an intelligent television according to a preferred embodiment of the present invention;
fig. 2 is a schematic block diagram of a preferred embodiment of the image recognition apparatus for video memory of the smart tv set according to the present invention.
Detailed Description
In order to make the technical problems, technical solutions and advantageous effects to be solved by the present invention clearer and clearer, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
As shown in fig. 1, it is a flowchart of a preferred embodiment of a video memory image recognition method of an intelligent television set according to the present invention; in this embodiment, the smart television adopts an android system; the method specifically comprises the following steps:
step S001: monitoring whether a game application is started on the intelligent television, if so, executing the step S002; otherwise, continuing to execute the step;
step S002: acquiring the package name and the television resolution of the application;
step S003: according to the packet name and the resolution, acquiring a pre-stored picture to be identified and the attribute thereof from the cloud;
the picture to be identified comprises an image picture and/or a character picture, and the attribute of the image picture comprises the initial position and the size of the picture; the text and picture attributes comprise a picture starting position, a size and a text color ratio.
In the step, the picture to be identified and the attribute thereof acquired from the cloud can be stored locally;
step S004: reading pictures from a video memory frame by frame;
step S005: intercepting a sub-picture with the same initial position and size as the current picture to be identified from the current read picture;
step S006: identifying the current picture to be identified according to whether the image similarity between the sub-picture and the current picture to be identified is larger than or equal to a preset value and/or whether the character color ratio of the sub-picture is the same as the character color ratio of the picture to be identified; the method specifically comprises the following steps:
step S0061: judging the type of the current picture to be identified; if the current picture to be identified is an image picture, executing a step S0062; if the current picture to be identified is a character picture, executing a step S0063; if the current picture to be identified comprises an image picture and a character picture, executing a step S0064;
step S0062: calculating the image similarity between the sub-picture and the current picture to be recognized, and judging whether the similarity is greater than or equal to a preset value S, if so, successfully recognizing the current picture to be recognized, and finishing the processing of the current picture to be recognized; otherwise, the current picture to be recognized fails to be recognized, and the current picture to be recognized is processed;
the invention calculates the image similarity p between the sub-picture and the current picture to be identified by the following steps:
calculating gray histograms of the sub-picture and the current picture to be identified; the specific calculation process of the gray histogram is as follows:
calculating the total number of pixel points of the picture and the pixel value of each pixel point according to the length and the width of the picture, calculating the proportion value of red (r ═ 16) &0xFF), green (g ═ 8) &0xFF) and blue (b ═ 0) &0xFF) in the pixel value according to the pixel value of each pixel point, and then calculating the proportion value of the red (r ═ 16) &0xFF, the green (g ═ 8) &0xFF) and the blue (b ═ 0) &0xFF according to a formula
color＝0.299*r+0.587*g+0.114*b
Calculating an ashing color value color of the current pixel, wherein r is a proportion value of red in a pixel value of the current pixel point; g is the occupation ratio of green in pixel values of the current pixel point; b is the proportion value of green in the pixel value of the current pixel point;
finally, calculating the proportion value of the ashing color value color of the current pixel in the total number of the pixel points;
and (3) forming an array L by the proportion values of the ashing color values of all the pixels in the total number of the pixels, wherein the L is the gray histogram of the picture.
According to the gray histograms of the sub-picture and the current picture to be identified and the following formula:
calculating the Babbitt coefficient P of the sub-picture and the current picture to be identified, wherein the P value is the image similarity of the sub-picture and the current picture to be identified;
wherein, i is the serial number of the elements in the gray histogram, and the initial value is 0; n is the length of the grey histogram; ai represents the ith element in the gray histogram of the sub-picture; bi represents the ith element in the gray histogram of the picture to be identified; the length n of the gray histograms of the sub-picture and the current picture to be recognized is the same as each other in size;
step S0063: calculating the character color ratio of the sub-picture, judging whether the character color ratio is the same as the character color ratio of the current picture to be recognized, if so, successfully recognizing the current picture to be recognized, and finishing the processing of the current picture to be recognized; otherwise, the current picture to be recognized fails to be recognized, and the current picture to be recognized is processed;
the character color proportion of the sub-picture is the percentage of the color, which is the same as the character color in the current picture to be identified, in the sub-picture to the sub-picture;
step S0064: checking a preset identification mode, and if the image is in priority, executing a step S0065; if the character is preferred, executing step S0067; if the image and the characters have the same priority, executing a step S0069;
step S0065: calculating the image similarity between the sub-picture and the current picture to be recognized, and judging whether the similarity is greater than or equal to a preset value S, if so, successfully recognizing the current picture to be recognized, and finishing the processing of the current picture to be recognized; otherwise, executing a step S0066;
step S0066: calculating the character color ratio of the sub-picture, judging whether the character color ratio is the same as the character color ratio of the current picture to be recognized, if so, successfully recognizing the current picture to be recognized, and finishing the processing of the current picture to be recognized; otherwise, the current picture to be recognized fails to be recognized, and the current picture to be recognized is processed;
step S0067: calculating the character color ratio of the sub-picture, judging whether the character color ratio is the same as the character color ratio of the current picture to be recognized, if so, successfully recognizing the current picture to be recognized, and finishing the processing of the current picture to be recognized; otherwise, executing a step S0068;
step S0068: calculating the image similarity between the sub-picture and the current picture to be recognized, and judging whether the similarity is greater than or equal to a preset value S, if so, successfully recognizing the current picture to be recognized, and finishing the processing of the current picture to be recognized; otherwise, the current picture to be recognized fails to be recognized, and the current picture to be recognized is processed;
step S0069: calculating the image similarity between the sub-picture and the current picture to be identified, judging whether the similarity is greater than or equal to a preset value S, and if so, executing a step S0070; otherwise, the current picture to be recognized fails to be recognized, and the current picture to be recognized is processed;
step S0070: calculating the character color ratio of the sub-picture, judging whether the character color ratio is the same as the character color ratio of the current picture to be recognized, if so, successfully recognizing the current picture to be recognized, and finishing the processing of the current picture to be recognized; otherwise, the current picture to be recognized fails to be recognized, and the current picture to be recognized is processed;
step S007: judging whether the identification is successful, if so, executing step S008; otherwise, executing step S009;
step S008: reading the next frame of picture in the video memory, and turning to the step S005 to execute the rest pictures to be identified;
step S009: judging whether the currently identified picture is the last picture in the pictures to be identified, if so, executing the step S008; otherwise, executing step S010;
step S010: and the next picture to be identified is executed in step S005.
Fig. 2 is a schematic block diagram of a preferred embodiment of the video memory image recognition apparatus for an intelligent television set according to the present invention; the present embodiment includes a monitoring module 10, a data processing module 20 and a picture recognition module 30, wherein the above-mentioned components
The detection module 10 is used for monitoring whether the game application is started or not on the smart television, and notifying the data processing module 20 when the game application is started;
the data processing module 20: the method comprises the steps of obtaining the package name of an application and the resolution of the intelligent television; according to the packet name and the resolution, acquiring a pre-stored picture to be identified and the attribute thereof from the cloud;
the picture identification module 30 is used for reading pictures from the video memory frame by frame; intercepting a sub-picture with the same initial position and size as the current picture to be identified from the read picture; calculating gray histograms of the sub-picture and the current picture to be identified and the Babbitt coefficient of the gray histogram; judging the type of the current picture to be identified and a preset identification mode; and identifying the current picture to be identified according to the type of the current picture to be identified, a preset identification mode, whether the image similarity between the sub-picture and the current picture to be identified is larger than or equal to a preset value and/or whether the character color ratio of the sub-picture is the same as the character color ratio of the picture to be identified.
While the foregoing description shows and describes the preferred embodiments of the present invention, it is to be understood, as noted above, that the invention is not limited to the forms disclosed herein, but is not intended to be exhaustive or to exclude other embodiments and may be used in various other combinations, modifications, and environments and is capable of changes within the scope of the inventive concept described herein, as determined by the above teachings or as determined by the skill or knowledge of the relevant art. And that modifications and variations may be effected by those skilled in the art without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (7)
1. A video memory image identification method of an intelligent television is characterized in that when a game application is started on the intelligent television, the method executes the following steps:
the method comprises the following steps: acquiring the package name of the application and the resolution of the intelligent television;
step two: according to the packet name and the resolution, acquiring a pre-stored picture to be recognized and the attribute thereof from a cloud;
step three: reading pictures from a video memory frame by frame;
step four: intercepting a sub-picture with the same initial position and size as the current picture to be identified from the read picture;
step five: identifying the current picture to be identified according to whether the image similarity between the sub-picture and the current picture to be identified is larger than or equal to a preset value and/or whether the character color ratio of the sub-picture is the same as the character color ratio of the picture to be identified;
wherein the fifth step specifically comprises the following steps:
step a: judging the type of the current picture to be identified; if the current picture to be identified is an image picture, executing the step b; if the current picture to be identified is a character picture, executing the step c; if the current picture to be identified comprises an image picture and a character picture, executing the step d;
step b: calculating the image similarity between the sub-picture and the current picture to be recognized, judging whether the similarity is larger than or equal to a preset value, if so, successfully recognizing the current picture to be recognized, and turning to the step l; otherwise, executing step k;
step c: calculating the character color ratio of the sub-picture, judging whether the character color ratio is the same as the character color ratio of the current picture to be recognized, if so, successfully recognizing the current picture to be recognized, and turning to the step l; otherwise, executing step k;
step d: reading a preset identification mode, and if the image is in priority, executing the step e; if the characters are preferred, executing the step g; if the image and the characters have the same priority, executing the step i;
step e: calculating the image similarity between the sub-picture and the current picture to be recognized, judging whether the similarity is larger than or equal to a preset value, if so, successfully recognizing the current picture to be recognized, and turning to the step l; otherwise, executing step f;
step f: calculating the character color ratio of the sub-picture, judging whether the character color ratio is the same as the character color ratio of the current picture to be recognized, if so, successfully recognizing the current picture to be recognized, and turning to the step l; otherwise, executing step k;
step g: calculating the character color ratio of the sub-picture, judging whether the character color ratio is the same as the character color ratio of the current picture to be recognized, if so, successfully recognizing the current picture to be recognized, and turning to the step l; otherwise, executing step h;
step h: calculating the image similarity between the sub-picture and the current picture to be recognized, judging whether the similarity is larger than or equal to a preset value, if so, successfully recognizing the current picture to be recognized, and turning to the step l; otherwise, executing step k;
step i: calculating the image similarity of the sub-picture and the current picture to be identified, judging whether the similarity is greater than or equal to a preset value, and if so, executing the step j; otherwise, executing step k;
step j: calculating the character color ratio of the sub-picture, judging whether the character color ratio is the same as the character color ratio of the current picture to be recognized, if so, successfully recognizing the current picture to be recognized, and turning to the step l; otherwise, executing step k;
step k: judging whether the current identified picture is the last picture in the pictures to be identified, if so, executing the step l; otherwise, the next picture to be identified is executed in the fourth step;
step l: and reading the next frame of picture in the video memory, and turning to the step four to execute the residual pictures to be identified.
2. The method according to claim 1, wherein the picture to be identified comprises an image picture and/or a text picture, and the image picture attribute comprises a picture starting position and a size; the character picture attributes comprise a picture starting position, a size and a character color ratio.
3. The method according to claim 1, wherein the method calculates the image similarity of the sub-picture and the current picture to be recognized by:
calculating gray histograms of the sub-picture and the current picture to be identified;
and calculating the Babbitt coefficient of the gray histogram to obtain the image similarity of the sub-picture and the current picture to be identified.
4. The method of claim 3, wherein the grey histogram of the picture is calculated by:
calculating the total number of pixel points of the picture and the pixel value of each pixel point according to the length and the width of the picture, calculating the proportion value of red (r ═ 16) &0xFF), green (g ═ 8) &0xFF) and blue (b ═ 0) &0xFF) in the pixel value according to the pixel value of each pixel point, and then according to a formula:
color＝0.299*r+0.587*g+0.114*b
calculating an ashing color value color of the current pixel;
wherein r is the proportion value of red in the pixel value of the current pixel point; g is the occupation ratio of green in pixel values of the current pixel point; b is the proportion value of green in the pixel value of the current pixel point;
calculating the proportion value of the ashing color value color of the current pixel in the total number of the pixel points;
and the proportion values of the ashing color values color of all the pixels of the picture in the total number of the pixels form a gray histogram of the picture.
5. The method of claim 3, wherein the Babbitt factor is calculated by the formula:
wherein, i is the serial number of the elements in the gray histogram, and the initial value is 0; n is the length of the grey histogram; ai represents the ith element in the gray histogram of the sub-picture; bi represents the ith element in the grey histogram of the picture to be recognized.
6. The display memory image recognition device of the intelligent television is characterized by comprising a monitoring module, a data processing module and an image recognition module, wherein the image recognition module is used for recognizing the display memory image of the intelligent television
The monitoring module is used for monitoring whether the game application is started or not and informing the data processing module when the game application is started;
a data processing module: the method comprises the steps of obtaining the package name of an application and the resolution of the intelligent television; according to the packet name and the resolution, obtaining a pre-stored picture to be recognized and the attribute thereof from a cloud end;
the picture identification module is used for reading pictures from the video memory frame by frame; intercepting a sub-picture with the same initial position and size as the current picture to be identified from the read picture; identifying the current picture to be identified according to whether the image similarity between the sub-picture and the current picture to be identified is larger than or equal to a preset value and/or whether the character color ratio of the sub-picture is the same as the character color ratio of the picture to be identified;
wherein the picture identification module is specifically configured to perform:
step a: judging the type of the current picture to be identified; if the current picture to be identified is an image picture, executing the step b; if the current picture to be identified is a character picture, executing the step c; if the current picture to be identified comprises an image picture and a character picture, executing the step d;
step b: calculating the image similarity between the sub-picture and the current picture to be recognized, judging whether the similarity is larger than or equal to a preset value, if so, successfully recognizing the current picture to be recognized, and turning to the step l; otherwise, executing step k;
step c: calculating the character color ratio of the sub-picture, judging whether the character color ratio is the same as the character color ratio of the current picture to be recognized, if so, successfully recognizing the current picture to be recognized, and turning to the step l; otherwise, executing step k;
step d: reading a preset identification mode, and if the image is in priority, executing the step e; if the characters are preferred, executing the step g; if the image and the characters have the same priority, executing the step i;
step e: calculating the image similarity between the sub-picture and the current picture to be recognized, judging whether the similarity is larger than or equal to a preset value, if so, successfully recognizing the current picture to be recognized, and turning to the step l; otherwise, executing step f;
step f: calculating the character color ratio of the sub-picture, judging whether the character color ratio is the same as the character color ratio of the current picture to be recognized, if so, successfully recognizing the current picture to be recognized, and turning to the step l; otherwise, executing step k;
step g: calculating the character color ratio of the sub-picture, judging whether the character color ratio is the same as the character color ratio of the current picture to be recognized, if so, successfully recognizing the current picture to be recognized, and turning to the step l; otherwise, executing step h;
step h: calculating the image similarity between the sub-picture and the current picture to be recognized, judging whether the similarity is larger than or equal to a preset value, if so, successfully recognizing the current picture to be recognized, and turning to the step l; otherwise, executing step k;
step i: calculating the image similarity of the sub-picture and the current picture to be identified, judging whether the similarity is greater than or equal to a preset value, and if so, executing the step j; otherwise, executing step k;
step j: calculating the character color ratio of the sub-picture, judging whether the character color ratio is the same as the character color ratio of the current picture to be recognized, if so, successfully recognizing the current picture to be recognized, and turning to the step l; otherwise, executing step k;
step k: judging whether the current identified picture is the last picture in the pictures to be identified, if so, executing the step l, otherwise, continuously intercepting a sub-picture with the same initial position and size as the current picture to be identified from the read picture;
step l: and reading the next frame of picture in the video memory, and continuously intercepting the sub-picture with the same initial position and size as the current picture to be identified from the read picture.
7. The apparatus of claim 6, wherein the picture recognition module is further configured to calculate a gray histogram and a Babbitt coefficient of the gray histogram of the sub-picture and the current picture to be recognized; and the image recognition module is used for judging the type of the current image to be recognized and a preset recognition mode.
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 CN106470358A (en) | 2017-03-01 |
| CN106470358B true 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) |
Families Citing this family (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 | A system based on video recognition and image extraction |
| 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 | A system based on video recognition and image extraction |
| 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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106470358A (en) | 2017-03-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11778263B2 (en) | Live streaming video interaction method and apparatus, and computer device | |
| KR102402513B1 (en) | Method and apparatus for executing a content | |
| US20170163953A1 (en) | Method and electronic device for processing image containing human face | |
| WO2016148807A1 (en) | Detecting segments of a video program | |
| WO2017035949A1 (en) | Intelligent home device interaction method and system based on intelligent television video scene | |
| CN110121098B (en) | Video playing method and device, storage medium and electronic device | |
| CN106604106A (en) | Player control display control method and apparatus thereof | |
| WO2017129118A1 (en) | Graphic instruction data processing method, apparatus and system | |
| CN116540963B (en) | Mapping relation calculation method, color calibration method, device and electronic equipment | |
| CN115396705B (en) | Screen operation verification method, platform and system | |
| CN107509115A (en) | A kind of method and device for obtaining live middle Wonderful time picture of playing | |
| CN111880711B (en) | Display control method, display control device, electronic equipment and storage medium | |
| EP4030766A1 (en) | Methods, systems, and media for color palette extraction for video content item | |
| CN107633479A (en) | A kind of method and apparatus of special display effect in the application | |
| CN114202480A (en) | Image processing method and device and electronic equipment | |
| US20170161875A1 (en) | Video resolution method and apparatus | |
| CN111294651A (en) | Still picture anti-afterimage method and device based on play data stream and storage medium | |
| CN108401173B (en) | Mobile live broadcast interactive terminal, method and computer readable storage medium | |
| CN106470358B (en) | Video memory image identification method and device of smart television | |
| CN109167989B (en) | VR video processing method and system | |
| KR20130089931A (en) | System and method for providing paduk situation stands using application | |
| CN108470362A (en) | A kind of method and apparatus for realizing video toning | |
| US10715732B2 (en) | Transmission apparatus, setting apparatus, transmission method, reception method, and storage medium | |
| WO2016161899A1 (en) | Multimedia information processing method, device and computer storage medium | |
| CN110839151A (en) | Game projection optimization method and related device |
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 |