CN109309865B - Age type goodness of fit recognition mechanism - Google Patents
Age type goodness of fit recognition mechanism Download PDFInfo
- Publication number
- CN109309865B CN109309865B CN201810984617.XA CN201810984617A CN109309865B CN 109309865 B CN109309865 B CN 109309865B CN 201810984617 A CN201810984617 A CN 201810984617A CN 109309865 B CN109309865 B CN 109309865B
- Authority
- CN
- China
- Prior art keywords
- edge
- equipment
- image
- age
- goodness
- 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.)
- Active
Links
- 230000007246 mechanism Effects 0.000 title claims abstract description 39
- 238000000605 extraction Methods 0.000 claims description 41
- 230000000877 morphologic effect Effects 0.000 claims description 24
- 238000003708 edge detection Methods 0.000 claims description 18
- 230000007797 corrosion Effects 0.000 claims description 13
- 238000005260 corrosion Methods 0.000 claims description 13
- 238000000034 method Methods 0.000 claims description 13
- 206010000060 Abdominal distension Diseases 0.000 claims description 6
- 208000024330 bloating Diseases 0.000 claims description 6
- 238000001514 detection method Methods 0.000 claims description 6
- 230000001360 synchronised effect Effects 0.000 claims description 5
- 238000004519 manufacturing process Methods 0.000 claims description 4
- 238000006243 chemical reaction Methods 0.000 description 8
- 230000011218 segmentation Effects 0.000 description 5
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000007812 deficiency Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
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
- H04N21/439—Processing of audio elementary streams
-
- 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
-
- 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 or rendering scenes according to encoded video stream scene graphs
-
- 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
- H04N21/81—Monomedia components thereof
- H04N21/8106—Monomedia components thereof involving special audio data, e.g. different tracks for different languages
- H04N21/8113—Monomedia components thereof involving special audio data, e.g. different tracks for different languages comprising music, e.g. song in MP3 format
-
- 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
- H04N21/81—Monomedia components thereof
- H04N21/8126—Monomedia components thereof involving additional data, e.g. news, sports, stocks, weather forecasts
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
- Television Signal Processing For Recording (AREA)
Abstract
The present invention relates to a kind of age type goodness of fit recognition mechanisms, it include: that audio reads equipment, it is connect with video playback apparatus, presss from both sides interior head audio file corresponding with file destination for obtaining video file, and determine Presence of the Moment type corresponding with the head audio file；Video playback apparatus, for according to the user's choice, obtain the video files names chosen by user, corresponding video file folder is found in video file data library based on the video files names, the file destination including video content is obtained from video file folder, and plays the file destination；Configuration file reads equipment, connect with the video playback apparatus, presss from both sides interior configuration file corresponding with the file destination for obtaining the video file, reads the configuration file to obtain the corresponding head duration.Through the invention, the goodness of fit of Presence of the Moment type Yu head age type is improved.
Description
Technical field
The present invention relates to selection field more particularly to a kind of age type goodness of fit recognition mechanisms of dubbing in background music.
Background technique
The editing to video is realized in video editing, and there are mainly two types of modes, and one is pass through conversion realization, MultiMedia Field
Also referred to as editing is converted, and one is direct editings, without conversion.
Editing conversion, an important process are decoding re-encoding, cut-point are searched according to user instructions, in encoding and decoding
In the process, encoding and decoding are automatically stopped according to cut-point.Compared to directly dividing, due to there is complicated encoding-decoding process,
Speed is relatively slow.But also just because of the encoding-decoding process of segmentation conversion, segmentation conversion also has importing video higher
Compatibility has recompiled as complete video because it exports video, the change of matter has occurred, the higher compatibility that solid segmentation is converted
Property be even including program flow etc. various formats importing divide.Meanwhile divide conversion contain two processes, i.e., segmentation and
Conversion, that is to say, that this technology realizes more demands, and the software of prominent domestic profession can see all-round converter here
Editing conversion.Particularly with needing to play an important role Video segmentation while being transplanted in mobile device.
Summary of the invention
In order to solve the Presence of the Moment type technical problem not high with the goodness of fit of head age type, the present invention provides one
Kind age type goodness of fit recognition mechanism.
The present invention at least has the important inventive point of following two:
(1) the head duration for playing video and Presence of the Moment type are obtained by way of reading configuration file, and are adopted
The judgement to head age type is completed with targetedly image procossing mechanism, particular, it is important that described in also further judging
Whether accurately the goodness of fit of Presence of the Moment type and the head age type provides important references information for dubbing in background music for Presence of the Moment；
(2) edge noise performance is eliminated using corrosion expansion process to handle better than opening and closing operation processing and opening and closing operation
Target detail is protected to build on the basis of carrying out noise profile situation analysis to image better than the characteristic of corrosion expansion process
The Morphological scale-space mechanism of image content-based feature.
According to an aspect of the present invention, a kind of age type goodness of fit recognition mechanism is provided, the mechanism includes:
Audio reads equipment, connect with video playback apparatus, corresponding with file destination in video file folder for obtaining
Head audio file, and determine Presence of the Moment type corresponding with the head audio file.
More specifically, in the age type goodness of fit recognition mechanism, further includes:
Video playback apparatus, for according to the user's choice, obtaining the video files names chosen by user, based on described
Video files names find corresponding video file folder in video file data library, obtain packet from video file folder
The file destination of video content is included, and plays the file destination.
More specifically, in the age type goodness of fit recognition mechanism, further includes:
Configuration file reads equipment, connect with the video playback apparatus, presss from both sides interior and institute for obtaining the video file
The corresponding configuration file of file destination is stated, reads the configuration file to obtain the corresponding head duration.
More specifically, in the age type goodness of fit recognition mechanism, further includes:
Contents extraction equipment reads equipment with the video playback apparatus and the configuration file respectively and connect, is used for base
Each frame image in head position is intercepted from the file destination in the head duration, head position will be in
Each frame image is exported as contents extraction image；Edge detection equipment is connect, for receiving with the contents extraction equipment
Contents extraction image is stated, each gray value of each pixel of the contents extraction image is obtained, is based on each pixel
The departure degree of gray value mean value of gray value to each pixel of its neighborhood determine whether it is edge pixel point；It draws in region
Subset is connect with the edge detection equipment, for receiving each edge pixel point in the contents extraction image, is based on
Each edge pixel point and each surrounding picture for being less than or equal to presetted pixel point quantity to the distance of each edge pixel point
Vegetarian refreshments forms the fringe region in the contents extraction image, will remove the contents extraction image after the fringe region as non-
Fringe region；Distribution situation detection device is connect with the region division equipment, for receiving in the contents extraction image
Each fringe region and each non-edge, determine the noise pixel point in each fringe region quantity and each
The quantity of noise pixel point in non-edge, the quantity of the noise pixel point added up in each fringe region is to obtain edge
Noise spot sum, the quantity of the noise pixel point added up in each non-edge is to obtain non-edge noise spot sum；Processing
Equipment is triggered, is connect with the distribution situation detection device, calculates and forms each fringe region in the contents extraction image
The sum of each pixel calculates to obtain edge pixel point sum and forms each non-edge in the contents extraction image
Each pixel sum to obtain non-edge pixels point sum, by the edge noise point sum divided by the edge pixel
Point sum is to obtain edge noise ratio, by the non-edge noise spot sum divided by the non-edge pixels point sum to obtain
Non-edge noise proportional, and when the edge noise ratio is more than the non-edge noise proportional, issue edge processing triggering
Signal, and when the edge noise ratio is less than the non-edge noise proportional, issue contents processing trigger signal；Corrosion
Bloating plant is connect, for receiving the edge respectively with the edge detection equipment and processing triggering equipment
When managing trigger signal, expansion process after first corroding is executed, to the contents extraction image to obtain corrosion expanding image；Opening and closing fortune
Equipment is calculated, is connect respectively with the edge detection equipment and processing triggering equipment, for receiving the contents processing
When trigger signal, closed operation is handled after executing first opening operation to the contents extraction image, to obtain opening and closing operation image；Signal
Merge equipment, connect respectively with the corrosion bloating plant and the opening and closing operation equipment, for expanding the corrosion received
Image or opening and closing operation image export the Morphological scale-space image as Morphological scale-space image；Content recognition equipment, with
The signal merges equipment connection, for receiving each frame Morphological scale-space image, to the Morphological scale-space image execute with
Lower movement: obtaining each image-region that each human object in the Morphological scale-space image is respectively at, and identifies each
A image-region corresponding clothes age each refers to the clothes age using as the reference clothes age, to obtain and export；Age
Identification apparatus is connect with the content recognition equipment, corresponding each with reference to clothes for receiving each Morphological scale-space image
The age is filled, and head age type is determined based on each Morphological scale-space image corresponding each reference clothes age；The goodness of fit
Judge equipment, reads equipment with the audio respectively and the age identification apparatus is connect, for receiving the Presence of the Moment type
With the head age type, and the goodness of fit of the Presence of the Moment type Yu the head age type is judged, coincide when described
When degree is less than or equal to preset percentage threshold value, failure signal of dubbing in background music is issued.
More specifically, in the age type goodness of fit recognition mechanism: the goodness of fit judges that equipment is also used to work as institute
When stating the goodness of fit greater than the preset percentage threshold value, accurate signal of dubbing in background music is issued.
More specifically, in the age type goodness of fit recognition mechanism: the edge detection equipment is mentioned in the content
When the departure degree for taking the gray value of the pixel in image to the gray value mean value of each pixel of its neighborhood is more than limitation, really
Fixed its is edge pixel point.
More specifically, in the age type goodness of fit recognition mechanism: the edge detection equipment is mentioned in the content
When the departure degree for taking the gray value of the pixel in image to the gray value mean value of each pixel of its neighborhood is less than limitation,
Determine that it is non-edge pixels point.
More specifically, in the age type goodness of fit recognition mechanism: in the age identification apparatus, based on each
Morphological scale-space image is corresponding each to determine that head age type includes: the reference that frequency of occurrence is most with reference to the clothes age
The clothes age, corresponding age type was as head age type.
Detailed description of the invention
Embodiment of the present invention is described below with reference to attached drawing, in which:
Fig. 1 is to judge equipment according to the goodness of fit of the age type goodness of fit recognition mechanism shown in embodiment of the present invention
Internal structure chart.
Specific embodiment
The embodiment of age type goodness of fit recognition mechanism of the invention is described in detail below with reference to accompanying drawings.
Video editing is the software that non-linear editing is carried out to video source, belongs to Multimedia Making Software scope.Software passes through
The materials such as the picture of addition, background music, special efficacy, scene are mixed again with video, video source is cut, is merged,
By secondary coding, the new video with different manifestations power is generated.
In order to overcome above-mentioned deficiency, the present invention has built a kind of age type goodness of fit recognition mechanism, can effectively solve the problem that
Corresponding technical problem.
Fig. 1 is to judge equipment according to the goodness of fit of the age type goodness of fit recognition mechanism shown in embodiment of the present invention
Internal structure chart.
The age type goodness of fit recognition mechanism shown according to an embodiment of the present invention includes:
Audio reads equipment, connect with video playback apparatus, corresponding with file destination in video file folder for obtaining
Head audio file, and determine Presence of the Moment type corresponding with the head audio file.
Then, continue that the specific structure of age type goodness of fit recognition mechanism of the invention is further detailed.
In the age type goodness of fit recognition mechanism, further includes:
Video playback apparatus, for according to the user's choice, obtaining the video files names chosen by user, based on described
Video files names find corresponding video file folder in video file data library, obtain packet from video file folder
The file destination of video content is included, and plays the file destination.
In the age type goodness of fit recognition mechanism, further includes:
Configuration file reads equipment, connect with the video playback apparatus, presss from both sides interior and institute for obtaining the video file
The corresponding configuration file of file destination is stated, reads the configuration file to obtain the corresponding head duration.
In the age type goodness of fit recognition mechanism, further includes:
Contents extraction equipment reads equipment with the video playback apparatus and the configuration file respectively and connect, is used for base
Each frame image in head position is intercepted from the file destination in the head duration, head position will be in
Each frame image is exported as contents extraction image；
Edge detection equipment is connect with the contents extraction equipment, for receiving the contents extraction image, described in acquisition
Each gray value of each pixel of contents extraction image, based on the gray value of each pixel to each pixel of its neighborhood
The departure degree of the gray value mean value of point determines whether it is edge pixel point；
Region division equipment is connect with the edge detection equipment, each in the contents extraction image for receiving
Edge pixel point is counted based on each edge pixel point and to the distance of each edge pixel point less than or equal to presetted pixel
Each surrounding pixel point of amount forms the fringe region in the contents extraction image, will remove the content after the fringe region
Image is extracted as non-edge；
Distribution situation detection device is connect with the region division equipment, for receiving in the contents extraction image
Each fringe region and each non-edge, determine the noise pixel point in each fringe region quantity and each
The quantity of noise pixel point in non-edge, the quantity of the noise pixel point added up in each fringe region is to obtain edge
Noise spot sum, the quantity of the noise pixel point added up in each non-edge is to obtain non-edge noise spot sum；
Processing triggering equipment, connect with the distribution situation detection device, calculates and forms in the contents extraction image respectively
The sum of each pixel of a fringe region is calculated and is formed in the contents extraction image respectively to obtain edge pixel point sum
The sum of each pixel of a non-edge to obtain non-edge pixels point sum, by the edge noise point sum divided by
The edge pixel point sum is to obtain edge noise ratio, by the non-edge noise spot sum divided by the non-edge pixels
Point sum is issued to obtain non-edge noise proportional, and when the edge noise ratio is more than the non-edge noise proportional
Edge processing trigger signal, and when the edge noise ratio is less than the non-edge noise proportional, issue contents processing
Trigger signal；
Corrode bloating plant, is connect respectively with the edge detection equipment and processing triggering equipment, for receiving
When to the edge processing trigger signal, expansion process after first corroding is executed to the contents extraction image, it is swollen to obtain corrosion
Swollen image；
Opening and closing operation equipment is connect, for receiving respectively with the edge detection equipment and processing triggering equipment
When to the contents processing trigger signal, closed operation is handled after executing first opening operation to the contents extraction image, to be opened
Closed operation image；
Signal merges equipment, connect respectively with the corrosion bloating plant and the opening and closing operation equipment, for that will receive
The corrosion expanding image or opening and closing operation image arrived exports the Morphological scale-space image as Morphological scale-space image；
Content recognition equipment merges equipment with the signal and connect, for receiving each frame Morphological scale-space image, to institute
It states Morphological scale-space image and executes following movement: obtaining what each human object in the Morphological scale-space image was respectively at
Each image-region identifies each image-region corresponding clothes age using as the reference clothes age, to obtain and export
It is each to refer to the clothes age；
Age identification apparatus is connect with the content recognition equipment, corresponding for receiving each Morphological scale-space image
It is each refer to the clothes age, and based on each Morphological scale-space image it is corresponding it is each reference the clothes age determine the head age
Type；
The goodness of fit judges equipment, reads equipment with the audio respectively and the age identification apparatus is connect, for receiving
The Presence of the Moment type and the head age type, and judge coincideing for the Presence of the Moment type and the head age type
Degree issues failure signal of dubbing in background music when the goodness of fit is less than or equal to preset percentage threshold value.
In the age type goodness of fit recognition mechanism: the goodness of fit judges that equipment is also used to when the goodness of fit is big
When the preset percentage threshold value, accurate signal of dubbing in background music is issued.
In the age type goodness of fit recognition mechanism: the edge detection equipment is in the contents extraction image
The gray value of pixel to each pixel of its neighborhood gray value mean value departure degree be more than limitation when, determine that it is edge
Pixel.
In the age type goodness of fit recognition mechanism: the edge detection equipment is in the contents extraction image
When the departure degree of gray value mean value of the gray value of pixel to each pixel of its neighborhood is less than limitation, determine that it is non-
Edge pixel point.
In the age type goodness of fit recognition mechanism: in the age identification apparatus, based at each morphology
Reason image is corresponding each to determine that head age type includes: the reference clothes age that frequency of occurrence is most with reference to the clothes age
Corresponding age type is as head age type.
In addition, can also include: DDR memory device in the age type goodness of fit recognition mechanism, it coincide with described
Degree judges that equipment connects, for storing the preset percentage threshold value, and when the goodness of fit judges that equipment is powered by institute
It states preset percentage threshold value and is sent to the goodness of fit and judge equipment.
DDR=Double Data Rate, i.e. Double Data Rate synchronous DRAM.Strictly speaking DDR should be cried
DDR SDRAM, people's habit are known as DDR, wherein SDRAM is Synchronous Dynamic Random Access
The abbreviation of Memory, i.e. Synchronous Dynamic Random Access Memory.And DDR SDRAM is the contracting of Double Data Rate SDRAM
It writes, is the meaning of Double Data Rate synchronous DRAM.DDR memory is developed on the basis of sdram memory, still
SDRAM production system so is continued to use, therefore for memory manufacturer, only the equipment for manufacturing common SDRAM need to slightly be improved, i.e.,
The production that DDR memory can be achieved, can effectively reduce cost.
Using age type goodness of fit recognition mechanism of the invention, for Presence of the Moment type in the prior art and head age
The not high technical problem of the goodness of fit of type, obtained by way of reading configuration file play video the head duration and
Presence of the Moment type, and the judgement to head age type is completed using targetedly image procossing mechanism, particular, it is important that also
Further judge the goodness of fit of the Presence of the Moment type Yu the head age type, whether is accurately provided for dubbing in background music for Presence of the Moment
Important references information；More handled it is essential that also eliminating edge noise performance using corrosion expansion process better than opening and closing operation, with
And opening and closing operation processing protection target detail is carrying out noise profile situation analysis to image better than the characteristic of corrosion expansion process
On the basis of, the Morphological scale-space mechanism of image content-based feature is built, to solve above-mentioned technical problem.
It is understood that although the present invention has been disclosed in the preferred embodiments as above, above-described embodiment not to
Limit the present invention.For any person skilled in the art, without departing from the scope of the technical proposal of the invention,
Many possible changes and modifications all are made to technical solution of the present invention using the technology contents of the disclosure above, or are revised as
With the equivalent embodiment of variation.Therefore, anything that does not depart from the technical scheme of the invention are right according to the technical essence of the invention
Any simple modifications, equivalents, and modifications made for any of the above embodiments still fall within the range of technical solution of the present invention protection
It is interior.
Claims (5)
1. a kind of age type goodness of fit recognition mechanism, which is characterized in that the mechanism includes:
Audio reads equipment, connect with video playback apparatus, presss from both sides interior head corresponding with file destination for obtaining video file
Audio file, and determine Presence of the Moment type corresponding with the head audio file；
Video playback apparatus is based on the video for according to the user's choice, obtaining the video files names chosen by user
File name finds corresponding video file folder in video file data library, and obtaining from video file folder includes view
The file destination of frequency content, and play the file destination；
Configuration file reads equipment, connect with the video playback apparatus, presss from both sides the interior and mesh for obtaining the video file
The corresponding configuration file of file is marked, reads the configuration file to obtain the corresponding head duration；
Contents extraction equipment reads equipment with the video playback apparatus and the configuration file respectively and connect, for being based on institute
State the head duration intercepts each frame image in head position from the file destination, will be in each of head position
Frame image is exported as contents extraction image；
Edge detection equipment is connect with the contents extraction equipment, for receiving the contents extraction image, obtains the content
The each gray value for extracting each pixel of image, based on the gray value of each pixel to each pixel of its neighborhood
The departure degree of gray value mean value determines whether it is edge pixel point；
Region division equipment is connect with the edge detection equipment, for receiving each edge in the contents extraction image
Pixel is less than or equal to presetted pixel point quantity based on each edge pixel point and to the distance of each edge pixel point
Each surrounding pixel point forms the fringe region in the contents extraction image, will remove the contents extraction after the fringe region
Image is as non-edge；
Distribution situation detection device is connect with the region division equipment, each in the contents extraction image for receiving
Fringe region and each non-edge determine quantity and each non-side of the noise pixel point in each fringe region
The quantity of noise pixel point in edge region, the quantity of the noise pixel point added up in each fringe region is to obtain edge noise
Point sum, the quantity of the noise pixel point added up in each non-edge is to obtain non-edge noise spot sum；
Processing triggering equipment, connect with the distribution situation detection device, calculates and form each side in the contents extraction image
The sum of each pixel in edge region is calculated each non-in the composition contents extraction image with obtaining edge pixel point sum
The sum of each pixel of fringe region is to obtain non-edge pixels point sum, by the edge noise point sum divided by described
Edge pixel point sum is total divided by the non-edge pixels point by the non-edge noise spot sum to obtain edge noise ratio
Number issues edge to obtain non-edge noise proportional, and when the edge noise ratio is more than the non-edge noise proportional
Trigger signal is handled, and when the edge noise ratio is less than the non-edge noise proportional, issues contents processing triggering
Signal；
Corrode bloating plant, is connect respectively with the edge detection equipment and processing triggering equipment, for receiving
When stating edge processing trigger signal, expansion process after first corroding is executed, to the contents extraction image to obtain corrosion expansion plans
Picture；
Opening and closing operation equipment is connect, for receiving respectively with the edge detection equipment and processing triggering equipment
When stating contents processing trigger signal, closed operation is handled after executing first opening operation to the contents extraction image, to obtain opening and closing fortune
Nomogram picture；
Signal merges equipment, connect respectively with the corrosion bloating plant and the opening and closing operation equipment, for what will be received
Corrode expanding image or opening and closing operation image as Morphological scale-space image, and exports the Morphological scale-space image；
Content recognition equipment merges equipment with the signal and connect, for receiving each frame Morphological scale-space image, to the shape
State processing image executes following movement: obtain each human object in the Morphological scale-space image be respectively at it is each
Image-region, identify each image-region corresponding clothes age using as the reference clothes age, it is each to obtain and export
With reference to the clothes age；
Age identification apparatus is connect with the content recognition equipment, corresponding each for receiving each Morphological scale-space image
A reference clothes age, and head age class is determined based on each Morphological scale-space image corresponding each reference clothes age
Type；
The goodness of fit judges equipment, reads equipment with the audio respectively and the age identification apparatus is connect, described for receiving
Presence of the Moment type and the head age type, and judge the goodness of fit of the Presence of the Moment type Yu the head age type,
When the goodness of fit is less than or equal to preset percentage threshold value, failure signal of dubbing in background music is issued；
DDR memory device judges that equipment is connect with the goodness of fit, for storing the preset percentage threshold value, and described
The goodness of fit judges that the preset percentage threshold value, which is sent to the goodness of fit, when equipment is powered judges equipment；The DDR is deposited
The DDR in equipment is stored up, i.e., Double Data Rate synchronous DRAM, DDR memory are developed on the basis of sdram memory
, still continue to use SDRAM production system.
2. age type goodness of fit recognition mechanism as described in claim 1, it is characterised in that:
The goodness of fit judges that equipment is also used to when the goodness of fit is greater than the preset percentage threshold value, and sending is dubbed in background music accurate
Signal.
3. age type goodness of fit recognition mechanism as described in claim 1, it is characterised in that:
The gray value of pixel of the edge detection equipment in the contents extraction image is to each pixel of its neighborhood
When the departure degree of gray value mean value is more than limitation, edge pixel point is determined that it is.
4. age type goodness of fit recognition mechanism as described in claim 1, it is characterised in that:
The gray value of pixel of the edge detection equipment in the contents extraction image is to each pixel of its neighborhood
When the departure degree of gray value mean value is less than limitation, non-edge pixels point is determined that it is.
5. age type goodness of fit recognition mechanism as described in claim 1, it is characterised in that:
In the age identification apparatus, head are determined based on each Morphological scale-space image corresponding each reference clothes age
Age type includes: using the most reference clothes age corresponding age type of frequency of occurrence as head age type.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810984617.XA CN109309865B (en) | 2018-08-28 | 2018-08-28 | Age type goodness of fit recognition mechanism |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810984617.XA CN109309865B (en) | 2018-08-28 | 2018-08-28 | Age type goodness of fit recognition mechanism |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109309865A CN109309865A (en) | 2019-02-05 |
| CN109309865B true CN109309865B (en) | 2019-06-07 |
Family
ID=65224225
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810984617.XA Active CN109309865B (en) | 2018-08-28 | 2018-08-28 | Age type goodness of fit recognition mechanism |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109309865B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101859562A (en) * | 2010-07-01 | 2010-10-13 | 无锡骏聿科技有限公司 | Method for matching conventional images with karaoke melodies in real time |
| CN102075695A (en) * | 2010-12-30 | 2011-05-25 | 中国科学院自动化研究所 | New generation intelligent cataloging system and method facing large amount of broadcast television programs |
| CN106022278A (en) * | 2016-05-26 | 2016-10-12 | 天津艾思科尔科技有限公司 | Method and system for detecting people wearing burka in video images |
| CN106375779A (en) * | 2016-08-30 | 2017-02-01 | 乐视控股（北京）有限公司 | Method, apparatus and system for acquiring the permission to use music |
| CN106534888A (en) * | 2016-11-03 | 2017-03-22 | 天脉聚源(北京)传媒科技有限公司 | Method and system for selecting background music based on video content |
| CN107124623A (en) * | 2017-05-12 | 2017-09-01 | 腾讯科技（深圳）有限公司 | The transmission method and device of music file information |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8446490B2 (en) * | 2010-05-25 | 2013-05-21 | Intellectual Ventures Fund 83 Llc | Video capture system producing a video summary |
-
2018
- 2018-08-28 CN CN201810984617.XA patent/CN109309865B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101859562A (en) * | 2010-07-01 | 2010-10-13 | 无锡骏聿科技有限公司 | Method for matching conventional images with karaoke melodies in real time |
| CN102075695A (en) * | 2010-12-30 | 2011-05-25 | 中国科学院自动化研究所 | New generation intelligent cataloging system and method facing large amount of broadcast television programs |
| CN106022278A (en) * | 2016-05-26 | 2016-10-12 | 天津艾思科尔科技有限公司 | Method and system for detecting people wearing burka in video images |
| CN106375779A (en) * | 2016-08-30 | 2017-02-01 | 乐视控股（北京）有限公司 | Method, apparatus and system for acquiring the permission to use music |
| CN106534888A (en) * | 2016-11-03 | 2017-03-22 | 天脉聚源(北京)传媒科技有限公司 | Method and system for selecting background music based on video content |
| CN107124623A (en) * | 2017-05-12 | 2017-09-01 | 腾讯科技（深圳）有限公司 | The transmission method and device of music file information |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109309865A (en) | 2019-02-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109544166B (en) | Risk identification method and risk identification device | |
| EP3557447A1 (en) | False address information identification method and device | |
| Hadwiger et al. | GPU-accelerated deep shadow maps for direct volume rendering | |
| CN102693359B (en) | A kind of method and device of the member's social modeling that founds a family | |
| HK1092236A1 (en) | Processor for exact pointer identification | |
| CN110490075B (en) | Method, apparatus and computer readable medium for obtaining stable frame | |
| CN115344505B (en) | Memory access method based on perception classification | |
| CN109309865B (en) | Age type goodness of fit recognition mechanism | |
| TWI718379B (en) | Evaluation method, device and equipment for users using shared items | |
| CN106033324A (en) | Data storage method and device | |
| CN107168651A (en) | A kind of small documents polymerize storage processing method | |
| CN110458688A (en) | A kind of method for processing business, device and equipment | |
| CN109756775A (en) | Age type goodness of fit discrimination method | |
| CN105575409A (en) | Method for writing MP4 file into optical disc under embedded host computer | |
| CN114299953A (en) | Speaker role distinguishing method and system combining mouth movement analysis | |
| CN108769572A (en) | Monitor video file generated, device and terminal device | |
| CN111464882B (en) | Video abstract generation method, device, equipment and medium | |
| CN108093356A (en) | One kind is uttered long and high-pitched sounds detection method and device | |
| CN116661706A (en) | Cache cleaning analysis method and system for solid state disk | |
| CN110852443A (en) | Feature stability detection method, device and computer readable medium | |
| CN104637496B (en) | Computer system and audio comparison method | |
| US20210192252A1 (en) | Method and apparatus for filtering images and electronic device | |
| CN109949337A (en) | Moving target detecting method and device based on Gaussian mixture model-universal background model | |
| CN103440186B (en) | Method and system for testing cache acceleration | |
| CN105592281B (en) | MPEG video processing method, device and system |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20190514 Address after: Room 1103, Building 21, 39 Jibang Road, Zhongming Town, Shanghai 202163 Applicant after: SHANGHAI JILIAN NETWORK TECHNOLOGY CO., LTD. Address before: 226600 Minghao Road, Santang Industrial Park, Haian Town, Haian County, Nantong City, Jiangsu Province Applicant before: Jiang Liying |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |