CN109064494A - Video floats scraps of paper detection method, device and computer readable storage medium - Google Patents
Video floats scraps of paper detection method, device and computer readable storage medium Download PDFInfo
- Publication number
- CN109064494A CN109064494A CN201811068698.5A CN201811068698A CN109064494A CN 109064494 A CN109064494 A CN 109064494A CN 201811068698 A CN201811068698 A CN 201811068698A CN 109064494 A CN109064494 A CN 109064494A
- Authority
- CN
- China
- Prior art keywords
- detected
- paper
- scraps
- picture
- video
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- 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
- H04N21/431—Generation of visual interfaces for content selection or interaction; Content or additional data rendering
-
- 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
- H04N21/431—Generation of visual interfaces for content selection or interaction; Content or additional data rendering
- H04N21/4312—Generation of visual interfaces for content selection or interaction; Content or additional data rendering involving specific graphical features, e.g. screen layout, special fonts or colors, blinking icons, highlights or animations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Signal Processing (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The disclosure discloses a kind of video floating scraps of paper detection method, video floating scraps of paper detection device, video floating scraps of paper detection hardware device and computer readable storage medium.Wherein, video floating scraps of paper detection method includes that floating scraps of paper detection is carried out at least frame picture to be detected extracted from video to be detected, and the floating scraps of paper are in the insertion video to be detected and unrelated with the video content to be detected sub- display window；It whether is determined in the video to be detected according to the testing result at least frame picture to be detected comprising the floating scraps of paper.The embodiment of the present disclosure carries out floating scraps of paper detection at least frame picture to be detected extracted from video to be detected first, wherein the floating scraps of paper are in the insertion video to be detected and unrelated with the video content to be detected sub- display window, then it whether determines in the video to be detected according to the testing result of at least frame picture to be detected comprising the floating scraps of paper, visual classification accuracy rate can be improved.
Description
Technical field
This disclosure relates to a kind of technical field of information processing, more particularly to a kind of video floating scraps of paper detection method, dress
It sets and computer readable storage medium.
Background technique
In recent years, with the rapid development of multimedia technology and computer network, the capacity of digital video is just with surprising
Speed increases.In this way, usually containing important text information from the image grabbed in digital video, this is being based on text
It is played an important role in the video data-base indexing of content.Terse retouch is carried out convenient for video main contents to a certain extent
It states and illustrates, or be convenient for visual classification, or the identification etc. convenient for illegal video.
In the prior art, the author of video is often added some words on video, for example advertising slogan, introduces language etc.,
Under normal circumstances, these words are type-scripts, and existing recognition methods is easier to identify.But there are also some scenes
Under, some scraps of paper effects can be added in the author of video in video, and some hand-written words are had in scraps of paper effect.Due to hand-written
Word it is usually more hasty and more careless, be less susceptible to identify, therefore difficult to visual classification bring, usually can be because of not identifying
Come, and is classified as no word video.
Therefore, for such video need detect it includes the floating scraps of paper, then gone out by manual identified
The text information for including in the floating scraps of paper, therefore, whether how accurate detection goes out in video just becomes comprising the floating scraps of paper
It is particularly significant.
Summary of the invention
The technical issues of disclosure solves is to provide a kind of video floating scraps of paper detection method, existing at least to be partially solved
There is the technical problem of visual classification inaccuracy.In addition, also providing a kind of video floating scraps of paper detection device, video floating scraps of paper inspection
It surveys hardware device, computer readable storage medium and the video floating scraps of paper and detects terminal.
To achieve the goals above, according to one aspect of the disclosure, the following technical schemes are provided:
A kind of video floating scraps of paper detection method, comprising:
Floating scraps of paper detection, the floating scraps of paper are carried out at least frame picture to be detected extracted from video to be detected
To be inserted into the video to be detected and unrelated with the video content to be detected sub- display window；
It whether is determined in the video to be detected according to the testing result at least frame picture to be detected comprising drift
The floating scraps of paper.
Further, the basis determines the video to be detected to the testing result of at least frame picture to be detected
In whether include floating the scraps of paper the step of, comprising:
If it is detected that including the floating scraps of paper at least frame picture to be detected, it is determined that include drift in the video to be detected
The floating scraps of paper.
Further, described that floating scraps of paper detection is carried out at least frame picture to be detected extracted from video to be detected
The step of, comprising:
For multiframe picture to be detected, the characteristics of image of each frame picture to be detected is extracted；
Compare the characteristics of image of each frame picture to be detected, if it exists include the picture to be detected of identical image feature,
Then determine that at least two frames picture to be detected includes the floating scraps of paper in the picture to be detected.
Further, described that floating scraps of paper detection is carried out at least frame picture to be detected extracted from video to be detected
The step of, comprising:
For single frames picture to be detected, the characteristic point of the picture to be detected and the adjacent features of the characteristic point are extracted
Point；
Characteristic area is determined according to the similarity of the characteristic point and the adjacent features point；
If detecting in the picture to be detected and containing at least two characteristic area, it is determined that wrapped in the picture to be detected
The scraps of paper containing floating.
Further, the method also includes:
Using the known picture comprising the floating scraps of paper and/or the known picture not comprising the floating scraps of paper as training sample；
According to whether being labeled comprising the floating scraps of paper to the training sample；
Study is trained to the training sample after the mark using deep learning sorting algorithm, obtains image classification
Device；
Described the step of floating scraps of paper detection is carried out at least frame picture to be detected extracted from video to be detected, packet
It includes:
At least frame picture to be detected is inputted into described image classifier, according to the classification knot of described image classifier
Fruit determines the testing result at least frame picture to be detected.
To achieve the goals above, according to the another aspect of the disclosure, and also the following technical schemes are provided:
A kind of video floating scraps of paper detection device, comprising:
Scraps of paper detection module is floated, for floating at least frame picture to be detected extracted from video to be detected
Scraps of paper detection, the floating scraps of paper are that in the insertion video to be detected and unrelated with the video content to be detected son is aobvious
Show window；
Float scraps of paper determining module, for according to the testing result of at least frame picture to be detected determine it is described to
It whether detects in video comprising the floating scraps of paper.
Further, the floating scraps of paper determining module is specifically used for: if it is detected that wrapping at least frame picture to be detected
The scraps of paper containing floating, it is determined that include the floating scraps of paper in the video to be detected.
Further, the floating scraps of paper detection module is specifically used for: being directed to multiframe picture to be detected, it is to be checked to extract each frame
The characteristics of image of mapping piece；Compare the characteristics of image of each frame picture to be detected, if it exists comprising identical image feature to
Detect picture, it is determined that at least two frames picture to be detected includes the floating scraps of paper in the picture to be detected.
Further, the floating scraps of paper detection module is specifically used for: being directed to single frames picture to be detected, extracts described to be checked
The adjacent features of the characteristic point of mapping piece and characteristic point point；According to the similarity of the characteristic point and the adjacent features point
Determine characteristic area；If detecting in the picture to be detected and containing at least two characteristic area, it is determined that the mapping to be checked
Include the floating scraps of paper in piece.
Further, described device further include:
Image Classifier training module, for by it is known comprising floating the scraps of paper picture and/or it is known comprising floating paper
The picture of piece is as training sample；According to whether being labeled comprising the floating scraps of paper to the training sample；Using deep learning
Sorting algorithm is trained study to the training sample after the mark, obtains Image Classifier；
The floating scraps of paper detection module is specifically used for: will at least frame picture input described image classification to be detected
Device determines the testing result at least frame picture to be detected according to the classification results of described image classifier.
To achieve the goals above, according to the another aspect of the disclosure, and also the following technical schemes are provided:
A kind of video floating scraps of paper detection hardware device, comprising:
Memory, for storing non-transitory computer-readable instruction；And
Processor, for running the computer-readable instruction, so that the processor realizes any of the above-described view when executing
Frequency drift floats the step of described in scraps of paper detection method technical solution.
To achieve the goals above, according to the another aspect of the disclosure, and also the following technical schemes are provided:
A kind of computer readable storage medium, for storing non-transitory computer-readable instruction, when the non-transitory
When computer-readable instruction is executed by computer, so that the computer executes any of the above-described video and floats scraps of paper detection method skill
The step of described in art scheme.
To achieve the goals above, according to the another aspect of the disclosure, and also the following technical schemes are provided:
A kind of video floating scraps of paper detection terminal, including any of the above-described video float scraps of paper detection device.
The embodiment of the present disclosure provides a kind of video floating scraps of paper detection method, video floating scraps of paper detection device, video drift
Floating scraps of paper detection hardware device, computer readable storage medium and the video floating scraps of paper detect terminal.Wherein, which floats paper
Chip detection method includes that floating scraps of paper detection, the drift are carried out at least frame picture to be detected extracted from video to be detected
The floating scraps of paper are in the insertion video to be detected and unrelated with the video content to be detected sub- display window；According to institute
Whether the testing result for stating at least frame picture to be detected determines in the video to be detected comprising the floating scraps of paper.The disclosure is implemented
Example carries out floating scraps of paper detection at least frame picture to be detected extracted from video to be detected first, wherein the floating scraps of paper are
Be inserted into sub- display window in the video to be detected and unrelated with the video content to be detected, then according to it is described extremely
Whether the testing result of few frame picture to be detected determines in the video to be detected comprising the floating scraps of paper, and video point can be improved
Class accuracy rate.
Above description is only the general introduction of disclosed technique scheme, in order to better understand the technological means of the disclosure, and
It can be implemented in accordance with the contents of the specification, and to allow the above and other objects, features and advantages of the disclosure can be brighter
Show understandable, it is special below to lift preferred embodiment, and cooperate attached drawing, detailed description are as follows.
Detailed description of the invention
Fig. 1 a is the flow diagram that scraps of paper detection method is floated according to the video of an embodiment of the present disclosure；
Fig. 1 b is the flow diagram that scraps of paper detection method is floated according to the video of the disclosure another embodiment；
Fig. 1 c is the flow diagram that scraps of paper detection method is floated according to the video of the disclosure another embodiment；
Fig. 1 d is the flow diagram that scraps of paper detection method is floated according to the video of the disclosure another embodiment；
Fig. 1 e is the flow diagram that scraps of paper detection method is floated according to the video of the disclosure another embodiment；
Fig. 2 a is the structural schematic diagram that the device of scraps of paper detection is floated according to the video of an embodiment of the present disclosure；
Fig. 2 b is the structural schematic diagram that scraps of paper detection device is floated according to the video of the disclosure another embodiment；
Fig. 3 is to float the structural schematic diagram that the scraps of paper detect hardware device according to the video of an embodiment of the present disclosure；
Fig. 4 is the structural schematic diagram according to the computer readable storage medium of an embodiment of the present disclosure；
Fig. 5 is to float the structural schematic diagram that the scraps of paper detect terminal according to the video of an embodiment of the present disclosure.
Specific embodiment
Illustrate embodiment of the present disclosure below by way of specific specific example, those skilled in the art can be by this specification
Disclosed content understands other advantages and effect of the disclosure easily.Obviously, described embodiment is only the disclosure
A part of the embodiment, instead of all the embodiments.The disclosure can also be subject to reality by way of a different and different embodiment
It applies or applies, the various details in this specification can also be based on different viewpoints and application, in the spirit without departing from the disclosure
Lower carry out various modifications or alterations.It should be noted that in the absence of conflict, the feature in following embodiment and embodiment can
To be combined with each other.Based on the embodiment in the disclosure, those of ordinary skill in the art are without making creative work
Every other embodiment obtained belongs to the range of disclosure protection.
It should be noted that the various aspects of embodiment within the scope of the appended claims are described below.Ying Xian
And be clear to, aspect described herein can be embodied in extensive diversified forms, and any specific structure described herein
And/or function is only illustrative.Based on the disclosure, it will be understood by one of ordinary skill in the art that one described herein
Aspect can be independently implemented with any other aspect, and can combine the two or both in these aspects or more in various ways.
For example, carry out facilities and equipments in terms of any number set forth herein can be used and/or practice method.In addition, can make
With other than one or more of aspect set forth herein other structures and/or it is functional implement this equipment and/or
Practice the method.
It should also be noted that, diagram provided in following embodiment only illustrates the basic structure of the disclosure in a schematic way
Think, component count, shape and the size when only display is with component related in the disclosure rather than according to actual implementation in schema are drawn
System, when actual implementation kenel, quantity and the ratio of each component can arbitrarily change for one kind, and its assembly layout kenel can also
It can be increasingly complex.
In addition, in the following description, specific details are provided for a thorough understanding of the examples.However, fields
The skilled person will understand that the aspect can be practiced without these specific details.
In order to solve the technical problem of visual classification inaccuracy, the embodiment of the present disclosure provides a kind of video floating scraps of paper detection
Method.As shown in Figure 1a, video floating scraps of paper detection method mainly includes the following steps S1 to step S2.Wherein:
Step S1: floating scraps of paper detection, floating are carried out at least frame picture to be detected extracted from video to be detected
The scraps of paper are in insertion video to be detected and unrelated with video content to be detected sub- display window.
Wherein, picture to be detected can be a frame or multiframe, when picture to be detected be multiframe when, it is to be detected to single frames respectively
Picture is detected, alternatively, being detected by comparing multiframe picture to be detected.
Wherein, sub- display window includes but is not limited to advertisement, pornography or the hand-written text information etc. being inserted into.
Step S2: it whether is determined in video to be detected according to the testing result at least frame picture to be detected comprising floating
The scraps of paper.
Wherein, it includes that the floating scraps of paper or multiframe are to be detected that testing result, which includes but is not limited to only frame picture to be detected,
Picture includes the floating scraps of paper, or includes the floating scraps of paper without picture to be detected.
The present embodiment is detected by carrying out the floating scraps of paper at least frame picture to be detected extracted from video to be detected,
Wherein the floating scraps of paper are in insertion video to be detected and unrelated with video content to be detected sub- display window, then according to right
Whether the testing result of at least frame picture to be detected determines in video to be detected comprising the floating scraps of paper, and visual classification can be improved
Accuracy rate.
In an alternative embodiment, as shown in Figure 1 b, step S2 is specifically included:
If it is detected that including the floating scraps of paper at least frame picture to be detected, it is determined that include floating paper in video to be detected
Piece.
Specifically, when detecting that only frame picture to be detected includes the floating scraps of paper or multiframe picture to be detected includes drift
When the floating scraps of paper, it is determined that comprising the floating scraps of paper in video to be detected, otherwise determine and do not include the floating scraps of paper in video to be detected.
The present embodiment is detected by carrying out the floating scraps of paper at least frame picture to be detected extracted from video to be detected,
The floating scraps of paper are in insertion video to be detected and unrelated with video content to be detected sub- display window, if it is detected that at least one
Include the floating scraps of paper in frame picture to be detected, it is determined that comprising the floating scraps of paper in video to be detected, visual classification standard can be improved
True rate.
In an alternative embodiment, as illustrated in figure 1 c, step S1 is specifically included:
S11: it is directed to multiframe picture to be detected, extracts the characteristics of image of each frame picture to be detected.
Wherein, characteristics of image can be the characteristic point of picture to be detected, or the characteristic area for picture to be detected.
S12: the characteristics of image of more each frame picture to be detected includes the picture to be detected of identical image feature if it exists,
Then determine that at least two frames picture to be detected includes the floating scraps of paper in picture to be detected.
Specifically, extracting the Shape context feature of this feature point when characteristics of image is the characteristic point of picture to be detected
With Scale invariant features transform (Scale-invariant feature transform, SIFT) feature, and according to characteristic point
Shape context feature and SIFT feature compare the similarity of the characteristic point between multiframe picture to be detected, obtain between picture to be detected
Characteristic point similarity matching result, obtain matched characteristic area, this feature region is identical characteristics of image.This
Example can be used for detecting floating scraps of paper the case where position changes in each frame picture of video.
When characteristics of image is the characteristic point region of picture to be detected, whether more each frame picture to be detected includes identical
Characteristic area, specifically can be used pixel matching or the method for calculating characteristic area similarity is determined.This example can be used for
Detection floating scraps of paper the case where position immobilizes in each frame picture of video.
Characteristics of image of the present embodiment by each frame picture to be detected of extraction, the image spy of more each frame picture to be detected
Sign includes the picture to be detected of identical image feature, it is determined that at least two frames picture to be detected in picture to be detected if it exists
Comprising floating the scraps of paper, so that it is determined that visual classification accuracy rate can be improved comprising the floating scraps of paper in video to be detected.
In an alternative embodiment, as shown in Figure 1 d, step S1 is specifically included:
S13: it is directed to single frames picture to be detected, extracts the characteristic point of picture to be detected and the adjacent features point of characteristic point.
Wherein, characteristic point can be SIFT feature.
S14: characteristic area is determined according to the similarity of characteristic point and adjacent features point.
S15: characteristic area is contained at least two if detecting in picture to be detected, it is determined that include drift in picture to be detected
The floating scraps of paper.
Specifically, according to the feature of detection video, it includes the pixel of single frames picture have very big correlation, and it is right
It is often unrelated with video content in the floating scraps of paper of insertion, it includes pixel of the pixel also with the single frames picture of extraction have
Very big difference can be directed to single frames picture to be detected, extract the characteristic point and characteristic point of picture to be detected according to features described above
Adjacent features point, and characteristic area is determined according to the similarity of characteristic point and adjacent features point, if detecting mapping to be checked
Characteristic area is contained at least two in piece, it is determined that include the floating scraps of paper in picture to be detected.
The present embodiment is by extracting the characteristic point of picture to be detected and the adjacent features point of characteristic point, according to characteristic point and neighbour
The similarity of nearly characteristic point determines characteristic area, contains at least two characteristic area if detecting in picture to be detected, it is determined that
Comprising the floating scraps of paper in picture to be detected, so that it is determined that video point can be improved comprising the floating scraps of paper in the video to be detected
Class accuracy rate.
In an alternative embodiment, as shown in fig. le, the method for the present embodiment further include:
S3: using the known picture comprising the floating scraps of paper and/or the known picture not comprising the floating scraps of paper as training sample.
S4: according to whether being labeled comprising the floating scraps of paper to training sample.
Specifically, before training, to distinguish the picture comprising the floating scraps of paper and the picture not comprising the floating scraps of paper, needing
Each picture is labeled.For example, the picture mark 1 comprising floating the scraps of paper is marked the picture not comprising the floating scraps of paper
0。
S5: study is trained to the training sample after mark using deep learning sorting algorithm, obtains Image Classifier.
Wherein, adoptable deep learning sorting algorithm include but is not limited to it is following any one: NB Algorithm,
Artificial neural network algorithm, genetic algorithm, K arest neighbors (K-NearestNeighbor, KNN) sorting algorithm, clustering algorithm etc..
Step S 1 is specifically included:
By at least frame picture input picture classifier to be detected, at least one is determined according to the classification results of Image Classifier
Testing result in frame picture to be detected.
The present embodiment by training image classifier, will at least frame picture input picture classifier to be detected, according to figure
As the testing result in the determining at least frame picture to be detected of the classification results of classifier, thus according to be detected to an at least frame
Whether the testing result of picture determines in video to be detected comprising the floating scraps of paper, and visual classification accuracy rate can be improved.
Those skilled in the art will be understood that on the basis of above-mentioned each embodiment, can also carry out obvious variant (example
Such as, cited mode is combined) or equivalent replacement.
Hereinbefore, although describing each step in video floating scraps of paper detection method embodiment according to above-mentioned sequence
It suddenly, can also be with it will be apparent to one skilled in the art that the step in the embodiment of the present disclosure not necessarily executes in the order described above
Other sequences such as inverted order, parallel, intersection execute, moreover, those skilled in the art can also add again on the basis of above-mentioned steps
Enter other steps, the mode of these obvious variants or equivalent replacement should also be included within the protection scope of the disclosure, herein not
It repeats again.
It is below embodiment of the present disclosure, embodiment of the present disclosure can be used for executing embodiments of the present disclosure realization
The step of, for ease of description, part relevant to the embodiment of the present disclosure is illustrated only, it is disclosed by specific technical details, it asks
Referring to embodiments of the present disclosure.
In order to solve the technical issues of how improving user experience effect, the embodiment of the present disclosure provides a kind of video floating paper
Piece detection device.The device can execute the step in above-mentioned video floating scraps of paper detection method embodiment.As shown in Figure 2 a, should
Device specifically includes that floating scraps of paper detection module 21 and floating scraps of paper determining module 22；Wherein, floating scraps of paper detection module 21 is used
In carrying out floating scraps of paper detection at least frame picture to be detected extracted from video to be detected, the floating scraps of paper are that insertion is to be checked
Survey in video and unrelated with video content to be detected sub- display window；Scraps of paper determining module 22 is floated to be used for according to at least
Whether the testing result of one frame picture to be detected determines in video to be detected comprising the floating scraps of paper.
Wherein, picture to be detected can be a frame or multiframe, when picture to be detected be multiframe when, it is to be detected to single frames respectively
Picture is detected, alternatively, being detected by comparing multiframe picture to be detected.
Wherein, sub- display window includes but is not limited to advertisement, pornography or the hand-written text information etc. being inserted into.
Wherein, it includes that the floating scraps of paper or multiframe are to be detected that testing result, which includes but is not limited to only frame picture to be detected,
Picture includes the floating scraps of paper, or includes the floating scraps of paper without picture to be detected.
The present embodiment is by floating scraps of paper detection module 21 at least frame mapping to be checked extracted from video to be detected
Piece carries out floating scraps of paper detection, wherein the floating scraps of paper are in insertion video to be detected and unrelated with video content to be detected son
Then display window is determined by floating scraps of paper determining module 22 according to the testing result at least frame picture to be detected to be checked
It whether surveys in video comprising the floating scraps of paper, visual classification accuracy rate can be improved.
In an alternative embodiment, based on shown in Fig. 2 a, floating scraps of paper determining module 22 is specifically used for: if it is detected that
Include the floating scraps of paper at least frame picture to be detected, it is determined that include the floating scraps of paper in video to be detected.
Specifically, when floating scraps of paper detection module 21 detects that only frame picture to be detected includes the floating scraps of paper, or it is more
When frame picture to be detected includes the floating scraps of paper, then floats scraps of paper determining module 22 and determines comprising floating the scraps of paper in video to be detected,
Otherwise it determines and does not include the floating scraps of paper in video to be detected.
The present embodiment is by floating scraps of paper detection module 21 at least frame mapping to be checked extracted from video to be detected
Piece carries out floating scraps of paper detection, and the floating scraps of paper are in insertion video to be detected and unrelated with video content to be detected son display
Window, if floating scraps of paper determining module 22 detects at least frame picture to be detected comprising the floating scraps of paper, it is determined that be detected
Comprising the floating scraps of paper in video, visual classification accuracy rate can be improved.
In an alternative embodiment, based on shown in Fig. 2 a, floating scraps of paper detection module 21 is specifically used for: for multiframe
Picture to be detected extracts the characteristics of image of each frame picture to be detected；The characteristics of image for comparing each frame picture to be detected, is wrapped if it exists
The picture to be detected of the feature containing identical image, it is determined that at least two frames picture to be detected includes floating paper in picture to be detected
Piece.
Wherein, characteristics of image can be the characteristic point of picture to be detected, or the characteristic area for picture to be detected.
Specifically, extracting the Shape context feature of this feature point when characteristics of image is the characteristic point of picture to be detected
And SIFT feature, and the characteristic point between multiframe picture to be detected is compared according to the Shape context feature and SIFT feature of characteristic point
Similarity, obtain the matching result of the similarity of the characteristic point between picture to be detected, obtain matched characteristic area, this feature
Region is identical characteristics of image.It is changed that this example can be used for detecting floating scraps of paper position in each frame picture of video
Situation.
When characteristics of image is the characteristic point region of picture to be detected, whether more each frame picture to be detected includes identical
Characteristic area, specifically can be used pixel matching or the method for calculating characteristic area similarity is determined.This example can be used for
Detection floating scraps of paper the case where position immobilizes in each frame picture of video.
The present embodiment extracts the characteristics of image of each frame picture to be detected by floating scraps of paper detection module 21, and more each frame waits for
The characteristics of image of picture is detected, if it exists includes the picture to be detected of identical image feature, it is determined that in picture to be detected at least
Having two frames picture to be detected includes the floating scraps of paper, to be determined in video to be detected by floating scraps of paper determining module 22 comprising drift
The floating scraps of paper, can be improved visual classification accuracy rate.
In an alternative embodiment, based on shown in Fig. 2 a, floating scraps of paper detection module 21 is specifically used for: for single frames
Picture to be detected extracts the characteristic point of picture to be detected and the adjacent features point of characteristic point；According to characteristic point and adjacent features point
Similarity determine characteristic area；If detecting in picture to be detected and containing at least two characteristic area, it is determined that mapping to be checked
Include the floating scraps of paper in piece.
Wherein, characteristic point can be SIFT feature.
Specifically, according to the feature of detection video, it includes the pixel of single frames picture have very big correlation, and it is right
It is often unrelated with video content in the floating scraps of paper of insertion, it includes pixel of the pixel also with the single frames picture of extraction have
Very big difference can be directed to single frames picture to be detected, extract the characteristic point and characteristic point of picture to be detected according to features described above
Adjacent features point, and characteristic area is determined according to the similarity of characteristic point and adjacent features point, if detecting mapping to be checked
Characteristic area is contained at least two in piece, it is determined that include the floating scraps of paper in picture to be detected.
The present embodiment extracts the characteristic point of picture to be detected and the neighbour of the characteristic point by floating scraps of paper detection module 21
Nearly characteristic point determines characteristic area according to the similarity of the characteristic point and the adjacent features point, if detecting described to be checked
Characteristic area is contained at least two in mapping piece, then by including in the determining picture to be detected of floating scraps of paper determining module 22
The scraps of paper are floated, so that it is determined that visual classification accuracy rate can be improved comprising the floating scraps of paper in the video to be detected.
In an alternative embodiment, as shown in Figure 2 b, the device of the present embodiment further include: Image Classifier training mould
Block 23；Wherein, Image Classifier training module 23 be used for by it is known comprising floating the scraps of paper picture and/or it is known not comprising floating
The picture of the scraps of paper is as training sample；According to whether being labeled comprising the floating scraps of paper to training sample；Using deep learning point
Class algorithm is trained study to the training sample after mark, obtains Image Classifier；
Floating scraps of paper detection module 21 be specifically used for: will at least frame picture input picture classifier to be detected, according to figure
The testing result at least frame picture to be detected is determined as the classification results of classifier.
Specifically, Image Classifier training module 23 is before training, to distinguish the picture comprising the floating scraps of paper and not wrapping
The picture of the scraps of paper containing floating, needs to be labeled each picture.For example, the picture mark 1 comprising floating the scraps of paper will not wrapped
The picture mark 0 of the scraps of paper containing floating.
Wherein, adoptable deep learning sorting algorithm include but is not limited to it is following any one: NB Algorithm,
Artificial neural network algorithm, genetic algorithm, K arest neighbors (K-NearestNeighbor, KNN) sorting algorithm, clustering algorithm etc..
The present embodiment by 23 training image classifier of Image Classifier training module, will at least frame picture to be detected it is defeated
Enter Image Classifier, determines the testing result at least frame picture to be detected according to the classification results of Image Classifier, thus
Floating scraps of paper determining module 22 according to the testing result at least frame picture to be detected determine in video to be detected whether include
The scraps of paper are floated, visual classification accuracy rate can be improved.
The detailed descriptions such as working principle, the technical effect of realization of related video floating scraps of paper detection device embodiment can be with
With reference to the related description in aforementioned video floating scraps of paper detection method embodiment, details are not described herein.
Fig. 3 is the hardware block diagram of diagram video floating scraps of paper detection hardware device according to an embodiment of the present disclosure.Such as Fig. 3
Shown, floating scraps of paper detection hardware device 30 according to the video of the embodiment of the present disclosure includes memory 31 and processor 32.
The memory 31 is for storing non-transitory computer-readable instruction.Specifically, memory 31 may include one
Or multiple computer program products, the computer program product may include various forms of computer readable storage mediums, example
Such as volatile memory and/or nonvolatile memory.The volatile memory for example may include random access memory
(RAM) and/or cache memory (cache) etc..The nonvolatile memory for example may include read-only memory
(ROM), hard disk, flash memory etc..
The processor 32 can be central processing unit (CPU) or have data-handling capacity and/or instruction execution energy
The processing unit of the other forms of power, and can control other components in video floating scraps of paper detection hardware device 30 to hold
The desired function of row.In one embodiment of the present disclosure, the processor 32 is by running based on this stored in the memory 31
Calculation machine readable instruction, so that video floating scraps of paper detection hardware device 30 executes the video drift of each embodiment of the disclosure above-mentioned
The all or part of the steps of floating scraps of paper detection method.
Those skilled in the art will be understood that solve the technical issues of how obtaining good user experience effect, this
It also may include structure well known to communication bus, interface etc. in embodiment, these well known structures should also be included in this public affairs
Within the protection scope opened.
Being described in detail in relation to the present embodiment can be with reference to the respective description in foregoing embodiments, and details are not described herein.
Fig. 4 is the schematic diagram for illustrating computer readable storage medium according to an embodiment of the present disclosure.As shown in figure 4, root
According to the computer readable storage medium 40 of the embodiment of the present disclosure, it is stored thereon with non-transitory computer-readable instruction 41.When this
When non-transitory computer-readable instruction 41 is run by processor, the ratio of the video features of each embodiment of the disclosure above-mentioned is executed
To all or part of the steps of method.
Above-mentioned computer readable storage medium 40 includes but is not limited to: and optical storage media (such as: CD-ROM and DVD), magnetic
Optical storage media (such as: MO), magnetic storage medium (such as: tape or mobile hard disk), with built-in rewritable nonvolatile
The media (such as: storage card) of memory and media (such as: ROM box) with built-in ROM.
Being described in detail in relation to the present embodiment can be with reference to the respective description in foregoing embodiments, and details are not described herein.
Fig. 5 is the hardware structural diagram for illustrating the terminal according to the embodiment of the present disclosure.As shown in figure 5, the video floats
It includes that above-mentioned video floats scraps of paper detection device embodiment that the scraps of paper, which detect terminal 50,.
The terminal can be implemented in a variety of manners, and the terminal in the disclosure can include but is not limited to such as move electricity
Words, smart phone, laptop, digit broadcasting receiver, PDA (personal digital assistant), PAD (tablet computer), PMP are (just
Take formula multimedia player), navigation device, car-mounted terminal, vehicle-mounted display terminal, vehicle electronics rearview mirror etc. mobile terminal
And the fixed terminal of such as number TV, desktop computer etc..
As the embodiment of equivalent replacement, which can also include other assemblies.As shown in figure 5, the video floats
It may include power supply unit 51, wireless communication unit 52, A/V (audio/video) input unit 53, user that the scraps of paper, which detect terminal 50,
Input unit 54, sensing unit 55, interface unit 56, controller 57, output unit 58 and memory 59 etc..Fig. 5 is shown
Terminal with various assemblies can also alternatively be implemented it should be understood that being not required for implementing all components shown
More or fewer components.
Wherein, wireless communication unit 52 allows the radio communication between terminal 50 and wireless communication system or network.A/V
Input unit 53 is for receiving audio or video signal.It is defeated that the order that user input unit 54 can be inputted according to user generates key
Enter data with the various operations of controlling terminal.Sensing unit 55 detects the current state of terminal 50, the position of terminal 50, user couple
In the presence or absence of touch input of terminal 50, the orientation of terminal 50, the acceleration or deceleration movement of terminal 50 and direction etc., and give birth to
Order or signal at the operation for controlling terminal 50.Interface unit 56 is used as at least one external device (ED) and connect with terminal 50
Can by interface.Output unit 58 is configured to provide output signal with vision, audio and/or tactile manner.Memory
59 can store the software program etc. of the processing and control operation that are executed by controller 55, or can temporarily store
Output or the data that will be exported.Memory 59 may include the storage medium of at least one type.Moreover, terminal 50 can be with
The network storage device cooperation of the store function of memory 59 is executed by network connection.The usual controlling terminal of controller 57 it is total
Gymnastics is made.In addition, controller 57 may include for reproducing or the multi-media module of multimedia playback data.Controller 57 can be with
The handwriting input executed on the touchscreen or picture are drawn input and are identified as character or figure by execution pattern identifying processing
Picture.Power supply unit 51 receives external power or internal power under the control of controller 57 and provides each element of operation and component
Required electric power appropriate.
The disclosure propose video features comparison method various embodiments can with use such as computer software,
The computer-readable medium of hardware or any combination thereof is implemented.Hardware is implemented, the ratio for the video features that the disclosure proposes
It can be by using application-specific IC (ASIC), digital signal processor (DSP), number to the various embodiments of method
Word signal processing apparatus (DSPD), programmable logic device (PLD), field programmable gate array (FPGA), processor, control
Device, microcontroller, microprocessor are designed to execute at least one of electronic unit of function described herein to implement,
In some cases, the various embodiments of the comparison method for the video features that the disclosure proposes can be real in controller 57
It applies.For software implementation, the disclosure propose video features comparison method various embodiments can with allow execute extremely
Lack a kind of individual software module of functions or operations to implement.Software code can be by being write with any programming language appropriate
Software application (or program) implement, software code can store in memory 59 and executed by controller 57.
Being described in detail in relation to the present embodiment can be with reference to the respective description in foregoing embodiments, and details are not described herein.
The basic principle of the disclosure is described in conjunction with specific embodiments above, however, it is desirable to, it is noted that in the disclosure
The advantages of referring to, advantage, effect etc. are only exemplary rather than limitation, must not believe that these advantages, advantage, effect etc. are the disclosure
Each embodiment is prerequisite.In addition, detail disclosed above is merely to exemplary effect and the work being easy to understand
With, rather than limit, it is that must be realized using above-mentioned concrete details that above-mentioned details, which is not intended to limit the disclosure,.
Device involved in the disclosure, device, equipment, system block diagram only as illustrative example and be not intended to
It is required that or hint must be attached in such a way that box illustrates, arrange, configure.As those skilled in the art will appreciate that
, it can be connected by any way, arrange, configure these devices, device, equipment, system.Such as "include", "comprise", " tool
" etc. word be open vocabulary, refer to " including but not limited to ", and can be used interchangeably with it.Vocabulary used herein above
"or" and "and" refer to vocabulary "and/or", and can be used interchangeably with it, unless it is not such that context, which is explicitly indicated,.Here made
Vocabulary " such as " refers to phrase " such as, but not limited to ", and can be used interchangeably with it.
In addition, as used herein, the "or" instruction separation used in the enumerating of the item started with "at least one"
It enumerates, so that enumerating for such as " at least one of A, B or C " means A or B or C or AB or AC or BC or ABC (i.e. A and B
And C).In addition, wording " exemplary " does not mean that the example of description is preferred or more preferable than other examples.
It may also be noted that in the system and method for the disclosure, each component or each step are can to decompose and/or again
Combination nova.These decompose and/or reconfigure the equivalent scheme that should be regarded as the disclosure.
The technology instructed defined by the appended claims can not departed from and carried out to the various of technology described herein
Change, replace and changes.In addition, the scope of the claims of the disclosure is not limited to process described above, machine, manufacture, thing
Composition, means, method and the specific aspect of movement of part.Can use carried out to corresponding aspect described herein it is essentially identical
Function or realize essentially identical result there is currently or later to be developed processing, machine, manufacture, event group
At, means, method or movement.Thus, appended claims include such processing, machine, manufacture, event within its scope
Composition, means, method or movement.
The above description of disclosed aspect is provided so that any person skilled in the art can make or use this
It is open.Various modifications in terms of these are readily apparent to those skilled in the art, and are defined herein
General Principle can be applied to other aspect without departing from the scope of the present disclosure.Therefore, the disclosure is not intended to be limited to
Aspect shown in this, but according to principle disclosed herein and the consistent widest range of novel feature.
In order to which purpose of illustration and description has been presented for above description.In addition, this description is not intended to the reality of the disclosure
It applies example and is restricted to form disclosed herein.Although already discussed above multiple exemplary aspects and embodiment, this field skill
Its certain modifications, modification, change, addition and sub-portfolio will be recognized in art personnel.
Claims (12)
1. a kind of video floats scraps of paper detection method characterized by comprising
Floating scraps of paper detection is carried out at least frame picture to be detected extracted from video to be detected, the floating scraps of paper are slotting
Enter sub- display window in the video to be detected and unrelated with the video content to be detected；
It whether is determined in the video to be detected according to the testing result at least frame picture to be detected comprising floating paper
Piece.
2. the method according to claim 1, wherein inspection of the basis at least frame picture to be detected
It surveys result and determines in the video to be detected whether include the step of floating the scraps of paper, comprising:
If it is detected that including the floating scraps of paper at least frame picture to be detected, it is determined that include floating paper in the video to be detected
Piece.
3. the method according to claim 1, wherein described wait for at least frame extracted from video to be detected
Detection picture carries out the step of floating scraps of paper detection, comprising:
For multiframe picture to be detected, the characteristics of image of each frame picture to be detected is extracted；
Compare the characteristics of image of each frame picture to be detected, if it exists includes the picture to be detected of identical image feature, then really
At least two frames picture to be detected includes the floating scraps of paper in the fixed picture to be detected.
4. the method according to claim 1, wherein described wait for at least frame extracted from video to be detected
Detection picture carries out the step of floating scraps of paper detection, comprising:
For single frames picture to be detected, the characteristic point of the picture to be detected and the adjacent features point of the characteristic point are extracted；
Characteristic area is determined according to the similarity of the characteristic point and the adjacent features point；
If detecting in the picture to be detected and containing at least two characteristic area, it is determined that include drift in the picture to be detected
The floating scraps of paper.
5. the method according to claim 1, wherein the method also includes:
Using the known picture comprising the floating scraps of paper and/or the known picture not comprising the floating scraps of paper as training sample；
According to whether being labeled comprising the floating scraps of paper to the training sample；
Study is trained to the training sample after the mark using deep learning sorting algorithm, obtains Image Classifier；
Described the step of floating scraps of paper detection is carried out at least frame picture to be detected extracted from video to be detected, comprising:
At least frame picture to be detected is inputted into described image classifier, the classification results according to described image classifier are true
Testing result in fixed at least frame picture to be detected.
6. a kind of video floats scraps of paper detection device characterized by comprising
Scraps of paper detection module is floated, for carrying out the floating scraps of paper at least frame picture to be detected extracted from video to be detected
Detection, the floating scraps of paper are in the insertion video to be detected and unrelated with the video content to be detected sub- display window
Mouthful；
Scraps of paper determining module is floated, for described to be detected according to determining to the testing result of at least frame picture to be detected
Whether include the floating scraps of paper in video.
7. device according to claim 6, which is characterized in that the floating scraps of paper determining module is specifically used for: if detection
Include the floating scraps of paper at least frame picture to be detected out, it is determined that include the floating scraps of paper in the video to be detected.
8. device according to claim 6, which is characterized in that the floating scraps of paper detection module is specifically used for: for more
Frame picture to be detected, extracts the characteristics of image of each frame picture to be detected；Compare the characteristics of image of each frame picture to be detected, if
In the presence of the picture to be detected comprising identical image feature, it is determined that at least two frames picture packet to be detected in the picture to be detected
The scraps of paper containing floating.
9. device according to claim 6, which is characterized in that the floating scraps of paper detection module is specifically used for: for single
Frame picture to be detected extracts the characteristic point of the picture to be detected and the adjacent features point of the characteristic point；According to the feature
The similarity of point and the adjacent features point determines characteristic area；If detecting in the picture to be detected and containing at least two spy
Levy region, it is determined that include the floating scraps of paper in the picture to be detected.
10. device according to claim 6, which is characterized in that described device further include:
Image Classifier training module, for by the known picture comprising the floating scraps of paper and/or known comprising the floating scraps of paper
Picture is as training sample；According to whether being labeled comprising the floating scraps of paper to the training sample；Classified using deep learning
Algorithm is trained study to the training sample after the mark, obtains Image Classifier；
The floating scraps of paper detection module is specifically used for: at least frame picture to be detected is inputted into described image classifier,
The testing result at least frame picture to be detected is determined according to the classification results of described image classifier.
11. a kind of video floating scraps of paper detect hardware device, comprising:
Memory, for storing non-transitory computer-readable instruction；And
Processor, for running the computer-readable instruction, so that realizing according to claim 1-5 when the processor executes
Any one of described in video float scraps of paper detection method.
12. a kind of computer readable storage medium, for storing non-transitory computer-readable instruction, when the non-transitory meter
When calculation machine readable instruction is executed by computer, so that the computer perform claim requires video described in any one of 1-5
Float scraps of paper detection method.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811068698.5A CN109064494B (en) | 2018-09-13 | 2018-09-13 | Video floating paper detection method and device and computer readable storage medium |
| PCT/CN2018/117711 WO2020052082A1 (en) | 2018-09-13 | 2018-11-27 | Video floating paperdetection method and device, and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811068698.5A CN109064494B (en) | 2018-09-13 | 2018-09-13 | Video floating paper detection method and device and computer readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109064494A true CN109064494A (en) | 2018-12-21 |
| CN109064494B CN109064494B (en) | 2021-09-21 |
Family
ID=64761493
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811068698.5A Active CN109064494B (en) | 2018-09-13 | 2018-09-13 | Video floating paper detection method and device and computer readable storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN109064494B (en) |
| WO (1) | WO2020052082A1 (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111738173B (en) * | 2020-06-24 | 2023-07-25 | 北京奇艺世纪科技有限公司 | Video clip detection method and device, electronic equipment and storage medium |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101183430A (en) * | 2007-12-13 | 2008-05-21 | 中国科学院合肥物质科学研究院 | Handwriting digital automatic identification method based on module neural network SN9701 rectangular array |
| CN101448100A (en) * | 2008-12-26 | 2009-06-03 | 西安交通大学 | Method for extracting video captions quickly and accurately |
| CN101453575A (en) * | 2007-12-05 | 2009-06-10 | 中国科学院计算技术研究所 | Video subtitle information extracting method |
| CN101853398A (en) * | 2010-05-11 | 2010-10-06 | 浙江大学 | Chinese paper cutting identification method based on space constraint characteristic selection and combination thereof |
| CN103186780A (en) * | 2011-12-30 | 2013-07-03 | 乐金电子(中国)研究开发中心有限公司 | Video caption identifying method and device |
| US20150169989A1 (en) * | 2008-11-13 | 2015-06-18 | Google Inc. | Foreground object detection from multiple images |
| CN104966097A (en) * | 2015-06-12 | 2015-10-07 | 成都数联铭品科技有限公司 | Complex character recognition method based on deep learning |
| CN105184226A (en) * | 2015-08-11 | 2015-12-23 | 北京新晨阳光科技有限公司 | Digital identification method, digital identification device, neural network training method and neural network training device |
| CN105718861A (en) * | 2016-01-15 | 2016-06-29 | 北京市博汇科技股份有限公司 | Method and device for identifying video streaming data category |
| CN107679552A (en) * | 2017-09-11 | 2018-02-09 | 北京飞搜科技有限公司 | A kind of scene classification method and system based on multiple-limb training |
| CN108288077A (en) * | 2018-04-17 | 2018-07-17 | 天津和或节能科技有限公司 | Grading of old paper device establishes device and method, grading of old paper system and method |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9996772B2 (en) * | 2016-04-28 | 2018-06-12 | International Business Machines Corporation | Detection of objects in images using region-based convolutional neural networks |
| CN108038850A (en) * | 2017-12-08 | 2018-05-15 | 天津大学 | A kind of drainage pipeline Exception Type automatic testing method based on deep learning |
| CN107948640B (en) * | 2017-12-19 | 2020-09-25 | 百度在线网络技术（北京）有限公司 | Video playing test method and device, electronic equipment and storage medium |
-
2018
- 2018-09-13 CN CN201811068698.5A patent/CN109064494B/en active Active
- 2018-11-27 WO PCT/CN2018/117711 patent/WO2020052082A1/en active Application Filing
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101453575A (en) * | 2007-12-05 | 2009-06-10 | 中国科学院计算技术研究所 | Video subtitle information extracting method |
| CN101183430A (en) * | 2007-12-13 | 2008-05-21 | 中国科学院合肥物质科学研究院 | Handwriting digital automatic identification method based on module neural network SN9701 rectangular array |
| US20150169989A1 (en) * | 2008-11-13 | 2015-06-18 | Google Inc. | Foreground object detection from multiple images |
| CN101448100A (en) * | 2008-12-26 | 2009-06-03 | 西安交通大学 | Method for extracting video captions quickly and accurately |
| CN101853398A (en) * | 2010-05-11 | 2010-10-06 | 浙江大学 | Chinese paper cutting identification method based on space constraint characteristic selection and combination thereof |
| CN103186780A (en) * | 2011-12-30 | 2013-07-03 | 乐金电子(中国)研究开发中心有限公司 | Video caption identifying method and device |
| CN104966097A (en) * | 2015-06-12 | 2015-10-07 | 成都数联铭品科技有限公司 | Complex character recognition method based on deep learning |
| CN105184226A (en) * | 2015-08-11 | 2015-12-23 | 北京新晨阳光科技有限公司 | Digital identification method, digital identification device, neural network training method and neural network training device |
| CN105718861A (en) * | 2016-01-15 | 2016-06-29 | 北京市博汇科技股份有限公司 | Method and device for identifying video streaming data category |
| CN107679552A (en) * | 2017-09-11 | 2018-02-09 | 北京飞搜科技有限公司 | A kind of scene classification method and system based on multiple-limb training |
| CN108288077A (en) * | 2018-04-17 | 2018-07-17 | 天津和或节能科技有限公司 | Grading of old paper device establishes device and method, grading of old paper system and method |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2020052082A1 (en) | 2020-03-19 |
| CN109064494B (en) | 2021-09-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR101768521B1 (en) | Method and system providing informational data of object included in image | |
| JP5134628B2 (en) | Media material analysis of consecutive articles | |
| CN109299734A (en) | Recognition methods, device and the computer readable storage medium of infringement picture | |
| US10528649B2 (en) | Recognizing unseen fonts based on visual similarity | |
| US20140368689A1 (en) | Image similarity determining device and method, and an image feature acquiring device and method | |
| CN103995889A (en) | Method and device for classifying pictures | |
| Elpeltagy et al. | Multi‐modality‐based Arabic sign language recognition | |
| TW201546636A (en) | Annotation display assistance device and method of assisting annotation display | |
| CN111598012B (en) | Picture clustering management method, system, device and medium | |
| CN104915673A (en) | Object classification method and system based on bag of visual word model | |
| CN109766885A (en) | A kind of character detecting method, device, electronic equipment and storage medium | |
| CN111209827A (en) | OCR (optical character recognition) bill problem recognition method and system based on feature detection | |
| WO2022252822A1 (en) | Information presentation method and apparatus, and device and medium | |
| CN110363206B (en) | Clustering of data objects, data processing and data identification method | |
| US20160062637A1 (en) | Method, apparatus and non-transitory storage medium for processing punctuation mark | |
| CN110874534B (en) | Data processing method and data processing device | |
| CN109376764B (en) | Data collection method and device based on clustering and computer readable storage medium | |
| CN109299682A (en) | Video text detection method, device and computer readable storage medium | |
| CN105740879B (en) | The zero sample image classification method based on multi-modal discriminant analysis | |
| CN110347841A (en) | A kind of method, apparatus, storage medium and the electronic equipment of document content classification | |
| CN109064494A (en) | Video floats scraps of paper detection method, device and computer readable storage medium | |
| CN110929647B (en) | Text detection method, device, equipment and storage medium | |
| US20160283520A1 (en) | Search device, search method, and computer program product | |
| CN101582118A (en) | Dictionary creating apparatus, recognizing apparatus, and recognizing method | |
| CN110413823A (en) | Garment image method for pushing and relevant apparatus |
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 | ||
| CP01 | Change in the name or title of a patent holder | ||
| CP01 | Change in the name or title of a patent holder |
Address after: 100041 B-0035, 2 floor, 3 building, 30 Shixing street, Shijingshan District, Beijing. Patentee after: Douyin Vision Co.,Ltd. Address before: 100041 B-0035, 2 floor, 3 building, 30 Shixing street, Shijingshan District, Beijing. Patentee before: Tiktok vision (Beijing) Co.,Ltd. Address after: 100041 B-0035, 2 floor, 3 building, 30 Shixing street, Shijingshan District, Beijing. Patentee after: Tiktok vision (Beijing) Co.,Ltd. Address before: 100041 B-0035, 2 floor, 3 building, 30 Shixing street, Shijingshan District, Beijing. Patentee before: BEIJING BYTEDANCE NETWORK TECHNOLOGY Co.,Ltd. |