CN102103686A - Video identification system using symmetric information of graded image block and method thereof - Google Patents
Video identification system using symmetric information of graded image block and method thereof Download PDFInfo
- Publication number
- CN102103686A CN102103686A CN2010102466703A CN201010246670A CN102103686A CN 102103686 A CN102103686 A CN 102103686A CN 2010102466703 A CN2010102466703 A CN 2010102466703A CN 201010246670 A CN201010246670 A CN 201010246670A CN 102103686 A CN102103686 A CN 102103686A
- Authority
- CN
- China
- Prior art keywords
- video
- frame
- piece
- search
- symmetric information
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/907—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/78—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/783—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformation in the plane of the image
- G06T3/40—Scaling the whole image or part thereof
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N1/00—Scanning, transmission or reproduction of documents or the like, e.g. facsimile transmission; Details thereof
- H04N1/40—Picture signal circuits
- H04N1/40012—Conversion of colour to monochrome
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
- H04N19/10—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding
- H04N19/102—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the element, parameter or selection affected or controlled by the adaptive coding
- H04N19/119—Adaptive subdivision aspects, e.g. subdivision of a picture into rectangular or non-rectangular coding blocks
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
- H04N19/10—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding
- H04N19/102—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the element, parameter or selection affected or controlled by the adaptive coding
- H04N19/12—Selection from among a plurality of transforms or standards, e.g. selection between discrete cosine transform [DCT] and sub-band transform or selection between H.263 and H.264
- H04N19/122—Selection of transform size, e.g. 8x8 or 2x4x8 DCT; Selection of sub-band transforms of varying structure or type
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
- H04N19/10—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding
- H04N19/102—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the element, parameter or selection affected or controlled by the adaptive coding
- H04N19/124—Quantisation
- H04N19/126—Details of normalisation or weighting functions, e.g. normalisation matrices or variable uniform quantisers
Abstract
The present invention discloses a video identification system which uses symmetric information of graded image block and a method thereof. When video clips are input, a frame rate of a video signal is converted to a preset value so the video signal is robust relatively to the conversion in a time axis. Afterwards, a gray grade conversion is performed for only using the brightness information of the video signal. Then, a frame size of the video signal is standardized to a preset size so the video is robust relatively to the size conversion. The frame size is divided to graded blocks by the standardized video, and furthermore symmetric information is extracted from each block thereby generating a specific vector. The graded blocks can be defined along a time axis or along a symmetric structure at a random position in the space for obtaining a graded structure on time or on time-space.
Description
The cross reference of related application
The application advocates that according to 35U.S.C. § 119 enjoying in the application number of submitting to Korea S Department of Intellectual Property on Dec 21st, 2009 is the right of priority of the korean patent application of 10-2009-0127713, and whole disclosures of described application case are incorporated herein by reference.
Technical field
Following discloses relate to a kind of video recognition system and method, and are particularly related to a kind of video recognition system and method for using the symmetric information of classification image block.
Background technology
The variation of terminal, the realization of large-capacity storage media and high-speed communication environment make that digitized content is easy to be played, and are transmitted fast and share.In addition, because digitized characteristics be easy to transmit and share the illegal content that has with the original contents same quality, so the infringement of copyright increase.
Therefore, carrying out copyright protection increases with the illegal needs of sharing that prevent high capacity and high-quality video content.For copyright protection, the demand of video monitoring and filtering system is increased.This video monitoring and filtering system are extracted unique video features information (being also referred to as " content DNA ") from the original video that needs copyright protection; this characteristic information is stored in the database (DB); when transmission or shared video content, from video content, extract video features information; information of being extracted and the information that is stored among the DB are compared, and the result carries out monitoring and filters based on the comparison.
For this video monitoring and filtering system, importantly extract video features at operation robusts (robust) such as transmission or contingent compression during shared video, size conversion, frame-rate conversion.Especially, there are the needs of handling following content recently, promptly owing to the content of supporting as the option of video player to change with 90 ° of rotations or reverse mode.
Under this background, carried out many researchs, and proposed following prior art video identification.
Exercise question is that the Korean Patent No.10-0644016 of " moving image search system and method " (" moving image search system and method ") has proposed a kind of use image section that wherein occurrence scene (or camera lens (shot)) changes in moving image and note, color, shape and the texture information of image comes the system of search video.But, for this system applies in filter, the operation that need analyze and explain video, and therefore for large-capacity video, will take a long time and dispose DB.In addition, be difficult to guarantee the objectivity of note.In addition, because the image of scene change part may be owing to factors such as frame-rate conversion be easy to change, so the reliability of search may worsen.
Exercise question has proposed a kind of scheme of detecting the scene change of vision signal and utilizing the length between scene change to come identification video of being used to for the Korean Patent No.10-0729660 of the digital video recognition system and the method for length " use scene change " (" digital video identification system and method using scene change length ").When coming identification video based on scene change, scene change quantity, and thereby may go wrong during DB when configuration or search for very big or very little according to video to be searched.
The exercise question of Job Oosteven, Ton Kalker and Japp Haitsma has proposed a kind of video frequency identifying method of the brightness value based on image block for the paper of " feature extraction and the database policies (Feature Extraction and a Database Strategy for Video Fingerprinting) (Proceeding of International Conference on Recent Advances in Visual Information Systems, 2002) that are used for video fingerprint recognition ".In this piece paper, obtain the average brightness value of image block, use time and spatial diversity between the brightness value to extract feature.In this case, because feature is by binarization, so can improve search efficiency.But,,, on the efficient that relates to high capacity DB application, search time etc., go wrong so can not discern rotation, image counter-rotating and distortion because used the difference of continuous blocks with unified size.
In the low computational load of needs, be used to monitor with the video identification technology of filtering system for must being robust when operations such as the size conversion of transmitting or take place during shared video, compression, frame-rate conversion, rotation, counter-rotatings.In addition, feature can not depend on the characteristics based on style (genre-based characteristics) of video.For example, between action movie and feature film, can not there be the difference on the discrimination, wherein has a large amount of motions and scene change to take place in the action movie, and have only the scene change of relatively small amount or motion to take place in the feature film.
Summary of the invention
Correspondingly, consider the problems referred to above that occur in the prior art and make the present invention, and the object of the invention provides a kind of video recognition system and method, this system and method is when extracting video features with low computational load, for being robust, be robust promptly for distortion owing to size conversion, compression, frame-rate conversion, rotation and counter-rotating in the transmission or the various distortions that may occur during shared video.
To achieve these goals, the invention provides a kind of video recognition system, comprise: feature and metamessage database (DB) unit, be used for storing extract from a plurality of video clippings and many video informations and be needed feature of video identification and video element information; Feature extraction unit is used for extracting feature from the input video montage; The database search unit is used for using the feature of extracting to come search characteristics and metamessage database; And the characteristic matching unit, be used for the Search Results of extraction feature and described feature and metamessage database is complementary; Wherein feature extraction unit comprises: the frame-rate conversion unit is used for the frame-rate conversion of the vision signal of input video montage is become a preset value; The grey level transition unit, the vision signal that is used for frame rate has been converted is carried out grey level transition; The frame sign standardized unit is used for the frame sign specification of the vision signal of executed grey level transition is turned to default size; And the blocking characteristic extraction unit, being used for Video Segmentation is the classification piece, extracts symmetric information from each piece, and generating feature vector then.
Preferably, the blocking characteristic extraction unit can become the classification piece with Video Segmentation based on the piece pattern with time or space symmetrical structure.More specifically, the blocking characteristic extraction unit is the classification piece based on the time-space classification piece pattern that is defined as having the space symmetrical structure, has simultaneously time hierarchy in successive frame, has in the simultaneously different in time frame time hierarchy with Video Segmentation.The blocking characteristic extraction unit can generate the eigenvector that comprises N dimension symmetric information eigenwert based on the piece pattern.
Preferably, the database search unit can be tieed up the positional value of symmetric information eigenwert or come search characteristics and metamessage database by the inverse characteristic value by changing N, to determine distortion video because of quadrature rotates or the horizontal/vertical counter-rotating causes, and that can only use N dimension symmetric information eigenwert comes tentatively search characteristics and metamessage database than the upper strata bit, and secondly uses the remaining bits of N dimension symmetric information eigenwert only to search for preliminary Search Results.
To achieve these goals, the invention provides a kind of method of extracting feature from video, comprising: by the frame-rate conversion with incoming video signal is that preset value is carried out frame-rate conversion; The vision signal that frame rate has been converted is carried out grey level transition; Turn to by frame sign specification and to specify size to carry out the frame sign normalization the vision signal of executed grey level transition; And by be the classification piece with Video Segmentation, by from each piece, extracting symmetric information and carrying out blocking characteristic by the generating feature vector and extract.
In addition, the invention provides a kind of video frequency identifying method, comprising: by the frame-rate conversion with incoming video signal is that preset value is carried out frame-rate conversion; The vision signal that frame rate has been converted is carried out grey level transition; Turn to by frame sign specification and to specify size to carry out the frame sign normalization the vision signal of executed grey level transition; By being the classification piece with Video Segmentation, from each piece, extracting symmetric information and generating feature vector and carry out blocking characteristic and extract; And mate by the property data base (DB) of search use characteristic vector configuration in advance and with the Search Results of eigenvector and property data base, carry out characteristic matching.
According to following detailed description book, accompanying drawing, claims, other features and aspect are with apparition.
Description of drawings
Fig. 1 shows the block diagram according to the structure of the video recognition system of the symmetric information of the use classification image block of the embodiment of the invention.
Fig. 2 shows the block diagram according to the structure of the feature extraction unit of the video recognition system of the embodiment of the invention.
Fig. 3 shows the figure of the example of the characteristic extraction procedure of being carried out by the feature extraction unit of Fig. 2.
Fig. 4 a and Fig. 4 b are the figure that shows the example of the image block with time-space hierarchy respectively.
Fig. 5 shows the figure of the example of the N dimensional feature value of extracting based on the piece pattern among Fig. 4 a and Fig. 4 b.
Fig. 6 shows the figure of the example of the bit operating that is used to calculate similarity.
Embodiment
Hereinafter, detailed description exemplary embodiment with reference to the accompanying drawings.Run through accompanying drawing and detailed description, unless describe in addition, identical Reference numeral will be understood that to refer to components identical, feature and structure.For clear, explanation and convenient for the purpose of, the relative size of these elements and narration may be by exaggerative.Following detailed description is with helping the complete understanding of reader's acquisition to method described herein, equipment and/or system.Thereby various variations, modification and the equivalent of method described herein, equipment and/or system will be that those of ordinary skills institute is thinkable.And for further clear and concise and to the point, the description of known function and structure may be omitted." comprise (include) ", implication specified properties, zone, fixed number, step, technology, element and/or the composition of " comprising (comprise) ", " comprising (including) " or " comprising (comprising) ", but do not get rid of other character, zone, fixed number, step, technology, element and/or composition.
Hereinafter, detailed description exemplary embodiment with reference to the accompanying drawings.
According to the present invention, from vision signal, extract the identifying information (that is, the feature of content) of content by the symmetric information that uses the classification image block, discern content.For this operation, from any classification piece of vision signal, obtain symmetric information, any classification piece value of being subdivided into, these values are configured to the form of matrix, and the entry of a matrix element is used as eigenwert, thus video is identified.
Fig. 1 shows the block diagram according to the structure of the video recognition system of the symmetric information of the use classification image block of the embodiment of the invention.
As shown in Figure 1, the video recognition system 100 according to the symmetric information of the use classification image block of the embodiment of the invention comprises feature and metamessage database (DB) 110, feature extraction unit 120, DB search unit 130 and characteristic matching unit 140.
The feature (content DNA) and the video element information that are used for video identification by using a plurality of video clippings and multi-disc video information to extract are come pre-configured feature and metamessage DB 110.
In video recognition system, use based on the feature of the symmetric information of classification image block eigenwert as video according to the symmetric information of the use classification image block of the embodiment of the invention.The structure that is used for extracting the feature extraction unit of these features is illustrated in Fig. 2.Fig. 3 illustrates the example of the characteristic extraction procedure of being carried out by feature extraction unit.
As shown in Figure 2, comprise frame-rate conversion unit 121, grey level transition unit 123, frame sign standardized unit 125 and piecemeal (block-wise) feature extraction unit 127 according to the feature extraction unit 120 in the video recognition system 100 of the present invention.
As shown in Figure 3, when input comprised the video clipping 320 of multiframe, frame-rate conversion unit 121 became a preset value with the vision signal frame-rate conversion of input video montage, thereby and to make vision signal be robust for the conversion that may occur on the time shaft.For example, no matter the frame rate of incoming video signal how, frame-rate conversion unit 121 is all carried out the frame-rate conversion of the incoming video signal conversion operations for default same frame rate.Result as conversion has generated the vision signal 321 with default same frame rate.
Carry out grey level transition by the 123 pairs of vision signals in grey level transition unit.Grey level transition unit 123 is carried out and is used for vision signal is converted to the process of grayscale image, thereby has only the monochrome information of vision signal to be used, and the colouring information of vision signal can be left in the basket.Result as conversion has generated gray scale video signal 323.
Next, frame sign standardized unit 125 turns to default size with the frame sign specification of vision signal, so that this video is a robust for size conversion.Therefore, generate its frame sign and turned to default big or small vision signal 324 by specification.
At last, blocking characteristic extraction unit 127 is cut apart frame so that video is divided into classification piece 325, extracts symmetric information from each piece, and generating feature vector afterwards.
The image block of each video can be by being defined along time shaft or along the symmetrical structure of optional position, space.Example with image block of this symmetrical structure is illustrated among Fig. 4 a and Fig. 4 b.Fig. 4 a illustrates time hierarchy, and Fig. 4 b illustrates the spatial scalability structure.The structure of these pieces will be described in the back.
From four pieces of constructing as shown in the figure, obtain symmetric information.In this situation, shown in Fig. 4 b, four pieces can selecting to have symmetrical structure perhaps obtain time-space (temporal-spatial) hierarchy by the time hierarchy among Fig. 4 a is applied to obtain the spatial scalability structure on the spatial scalability structure.When the piece with time-space hierarchy was selected, the one or more time hierarchies among Fig. 4 a can be applied in the spatial scalability structure.
The process of the symmetric information that is used to extract four pieces is described below.At first, when 2 * 2 matrix A that exist shown in equation (1), can obtain the symmetric information of matrix A by following equation (2).
Even video is rotated with 90 ° of angles or is inverted, the value of this symmetric information still is held.For example, when video is rotated 90 ° of angles, by following equation (3) provide matrix A ' situation under, matrix A ' symmetric information can obtain by following equation (4).
By the method identical, even for the matrix A shown in equation (5) along Z-axis counter-rotating with top method ", can obtain the result of equation (6).
S
1(A″)＝S
1(A)，S
2(A″)＝～S
2(A)，S
3(A″)＝～S
3(A) (6)
That is to say,, also only changed the position of the feature of each piece, (for example, S and eigenwert remains unchanged even video is rotated 90 ° of angles
1(A ')=～S
2(A)).In addition, though by 180 ° or 270 ° of rotations together with 90 ° of angles rotations and level or vertically reverse and cause under the situation of distortion that eigenwert still remains unchanged.
Because these characteristics, according to the symmetric information eigenwert of the embodiment of the invention for being robust by the horizontal or vertical counter-rotating of video or with the distortion that 90 °, 180 ° or 270 ° of angle rotating videos cause.Particularly, in the situation of 90 ° and 270 ° rotations, the position change of eigenwert, but video is with 90 ° or the rotation of 270 ° of angles is based on recently determining in length and breadth of video, so the position can be accurate on the position that has changed in the N dimensional feature position.
According to the embodiment of the invention, the subordinate's piece by repeating to have time-space classification characteristics but not arbitrarily piece make up with generating four required pieces of eigenvector of forming by blocking characteristic.That is to say, as as shown in Fig. 4 a and Fig. 4 b, and definition time-spatial scalability piece pattern (Block Patterns, BP), this piece pattern has the spatial scalability structure and also have time hierarchy simultaneously in successive frame, and thereby definable N dimension symmetric information eigenwert.Here, time hierarchy also not necessarily is defined in the successive frame, and four pieces that the time that also can be defined as goes up in the different frame have symmetrical structure.
Equation (1) can be applied to the piece pattern that defines in Fig. 4 a and Fig. 4 b and extract N dimensional feature value, its example as shown in Figure 5.
In the example depicted in fig. 5, BP1 has three-dimensional feature, and S1 (BP1), S2 (BP1) and S3 (BP1) extract from same frame, perhaps goes up the different frames from the time and extracts, to obtain the time hierarchy as shown in the example of Fig. 4 a.That is to say, when from same number of frames, extracting piece pattern (BP), usage space hierarchy only.When extracting the piece pattern the frame upward different from the time, service time-the spatial scalability structure.
Usually, be robust from the symmetric information eigenwert of extracting as wide pattern for video distortion, but be fragile (that is to say, have the image that much has the same characteristic features value) in identification than the upper strata.In addition, the symmetric information eigenwert of extracting from narrow pattern as lower level has high sense (that is to say, have the image that seldom has the same characteristic features value), but is fragile for video distortion.Consistent with the characteristics of these eigenwerts, the advantage than the residue character identification video of characteristic classification candidate's video group on upper strata and use lower level is used in acquisition.
That is to say, in reference to figure 1 described characteristic matching process, be not the mutual relatively feature of all dimensions, but in using the feature group of classifying than the feature (or attribute) on upper strata, compare the feature of lower level mutually, therefore improved search speed.
In embodiments of the present invention, use the characteristic information of classification symmetric information value, and from the prescribed fractionated piece of normalization frame, extract the symmetric information value as video.For example, when the hypothesis frame rate is 10fps, the size of normalized images is 8*8, and the quantity of spatial scalability piece pattern is 18 o'clock, and about 10 seconds video clipping has the eigenwert (the 18 every frame of * 3 symmetry=54 dimension/frames) of 5400 bits that are used for 10 seconds * 10fps=100 frames.In addition, when the quantity of spatial scalability piece pattern is confirmed as 18, and temporal scalability piece patterning only is applied to present frame and proper that frame before present frame, can be further with the quantity of temporal scalability piece pattern pro rata, each frame from 99 frames of 100 frames altogether extracts 18 patterns.
Use above-mentioned eigenwert to dispose the feature DB that search system will be used in advance, and this feature DB is used from search with input metamessage DB one.In search system, use following equation (7) to come distance between the comparative feature.For example, the eigenwert of the i frame in the N dimensional feature that hypothesis receives as search input (query excerpt) is Q (i), and the eigenwert of the i frame of the k video among the DB is that (k, in the time of i), following providing is used for algorithm that query excerpt and DB are compared to DB.
Fig. 6 shows the figure of the example of the bit operating that is used to calculate similarity.As shown in Figure 6, after N dimensional feature value is carried out the computing of XNOR bit, when counting 1, the similarity value of measurement (similarity distance D just) can be calculated by following equation (7).
The determining to adopt in such a way and carry out of similarity (S) with query excerpt of frame length m promptly when the similarity value of the successive frame of measuring during greater than predetermined threshold, determines that query excerpt is the video that is stored among the DB, shown in equation (8).
In addition, in order to distinguish the distortion video that causes because of quadrature rotation (90 °, 180 ° and 270 °), horizontal/vertical counter-rotating etc., only need to carry out aforesaid operations by the position or the inverse characteristic value that change the N dimensional feature.
In addition, only use than the upper strata bit DB preliminary classification to be become similar group in the N dimensional feature, and only in sorted group, carry out search, thereby improved search performance.
In search system, as recognition result, the position of the i frame of output similarity k video that be maximized, among the DB.
Therebetween, in an embodiment of the present invention, describe difference between the classification symmetrical structure that adopts video and extracted the method and system that feature and use characteristic are come identification video, but it is apparent that, also can be applicable to field except that video identification according to the Feature Extraction System of the embodiment of the invention and method.
Can be embodied as computer-readable code on the computer readable recording medium storing program for performing according to the video frequency identifying method of the symmetric information of the use classification image block of the embodiment of the invention.Computer-readable recording medium is that stored on it can be by the pen recorder of the data of computer system reads, and for example can be ROM (read-only memory) (ROM), random-access memory (ram), cache memory, hard disk, flexible plastic disc, flash memory or light data storage device.In addition, described medium can provide with carrier format, and for example can be included in situation about providing on the Internet.In addition, computer-readable recording medium can be distributed in the computer system connected to one another on the network, and can store and carry out as computer readable code with distributed way.
As mentioned above, advantage of the present invention is: use the time-space hierarchy of digital video to simplify the recognition property (or feature) of digital video, thereby improved search performance.In addition, based on according to video and the fact that contingent various block size local wrong and hierarchical nature causes has only the attribute on upper strata can be used to index and classification inversely proportionally.In addition, by only changing the position of the attribute dimension of the attribute that depends on video recognition system, just can search for discernible distortion environment (rotation, counter-rotating etc.).In addition, can control recognition speed and search time by the amplitude that changes attribute dimension.
Though for illustration purpose discloses according to the video recognition system of the symmetric information of use classification image block of the present invention and the preferred embodiment of method, but those skilled in the art can understand, under situation about not deviating from, may carry out various modifications, increase and replacement in scope and spirit of the present invention disclosed in the accompanying claims.
Claims (20)
1. video recognition system comprises:
Feature and metamessage database (DB) unit, be used for storing extract from a plurality of video clippings and many video informations and be needed feature of video identification and video element both information;
Feature extraction unit is used for extracting feature from the input video montage;
The database search unit, be used for using the feature of extracting come search characteristics and metamessage database and
The characteristic matching unit is used for the Search Results of extraction feature and described feature and metamessage database is complementary;
Wherein feature extraction unit comprises:
The frame-rate conversion unit is used for the frame-rate conversion of the vision signal of input video montage is become a preset value;
The grey level transition unit, the vision signal that is used for frame rate has been converted is carried out grey level transition;
The frame sign standardized unit is used for the frame sign specification of the vision signal of executed grey level transition is turned to default size; And
The blocking characteristic extraction unit, being used for Video Segmentation is the classification piece, extracts symmetric information from each piece, and generating feature vector then.
2. video recognition system according to claim 1, wherein said blocking characteristic extraction unit becomes the classification piece based on the piece pattern with space symmetrical structure with Video Segmentation.
3. video recognition system according to claim 2, wherein said blocking characteristic extraction unit generate the eigenvector that comprises N dimension symmetric information eigenwert based on the piece pattern.
4. video recognition system according to claim 3, wherein said database search unit is tieed up the positional value of symmetric information eigenwert or is come search characteristics and metamessage database by the inverse characteristic value by changing N, to determine the distortion video because of quadrature rotates or the horizontal/vertical counter-rotating causes.
5. video recognition system according to claim 3, what wherein said database search unit only used N dimension symmetric information eigenwert comes tentatively search characteristics and metamessage database than the upper strata bit, and secondly uses the remaining bits of N dimension symmetric information eigenwert only to search for preliminary Search Results.
6. video recognition system according to claim 1, wherein said blocking characteristic extraction unit is the classification piece based on having the piece pattern that has time hierarchy in the simultaneously different in time frame of space symmetrical structure with Video Segmentation.
7. video recognition system according to claim 6, wherein said blocking characteristic extraction unit generate the eigenvector that comprises N dimension symmetric information eigenwert based on the piece pattern.
8. video recognition system according to claim 7, wherein said database search unit is tieed up the positional value of symmetric information eigenwert or is come search characteristics and metamessage database by the inverse characteristic value by changing N, in order to determine the distortion video because of quadrature rotates or the horizontal/vertical counter-rotating causes.
9. video recognition system according to claim 7, what wherein said database search unit only used N dimension symmetric information eigenwert comes tentatively search characteristics and metamessage database than the upper strata bit, and secondly uses the remaining bits of N dimension symmetric information eigenwert and only search for preliminary Search Results.
10. method of extracting feature from video comprises:
By the frame-rate conversion with incoming video signal is that preset value is carried out frame-rate conversion;
The vision signal that frame rate has been converted is carried out grey level transition;
Turn to by frame sign specification and to specify size to carry out the frame sign normalization the vision signal of executed grey level transition; And
By be the classification piece with Video Segmentation, by from each piece, extracting symmetric information and carrying out blocking characteristic by the generating feature vector and extract.
11. method according to claim 10, the step that wherein said execution blocking characteristic extracts is configured to based on the piece pattern with space symmetrical structure Video Segmentation be become the classification piece.
12. method according to claim 11, the step that wherein said execution blocking characteristic extracts are configured to generate the eigenvector that comprises N dimension symmetric information eigenwert based on described pattern.
13. method according to claim 10, the step that wherein said execution blocking characteristic extracts are configured to based on having the piece pattern that has time hierarchy in the simultaneously different in time frame of space symmetrical structure Video Segmentation be become the classification piece.
14. method according to claim 13, the step that wherein said execution blocking characteristic extracts are configured to generate the eigenvector that comprises N dimension symmetric information eigenwert based on described pattern.
15. a video frequency identifying method comprises:
By the frame-rate conversion with incoming video signal is that preset value is carried out frame-rate conversion;
The vision signal that frame rate has been converted is carried out grey level transition;
Turn to by frame sign specification and to specify size to carry out the frame sign normalization the vision signal of executed grey level transition;
By being the classification piece with Video Segmentation, from each piece, extracting symmetric information and generating feature vector and carry out blocking characteristic and extract; And
Mate by the property data base (DB) of search use characteristic vector configuration in advance and with the Search Results of eigenvector and property data base, carry out characteristic matching.
16. video frequency identifying method according to claim 15, it is the classification piece with Video Segmentation that the step that wherein said execution blocking characteristic extracts is configured to based on the piece pattern with space symmetrical structure.
17. video frequency identifying method according to claim 15, the step that wherein said execution blocking characteristic extracts are configured to based on having the piece pattern that has time hierarchy in the simultaneously different in time frame of space symmetrical structure Video Segmentation be become the classification piece.
18. video frequency identifying method according to claim 17, the step that wherein said execution blocking characteristic extracts are configured to generate the eigenvector that comprises N dimension symmetric information eigenwert based on described pattern.
19. video frequency identifying method according to claim 18, the step of wherein said execution characteristic matching is configured to: tie up the positional value of symmetric information eigenwert or come the search characteristics database by the inverse characteristic value by changing N, with the distortion video of determining to be caused by quadrature rotation or horizontal/vertical counter-rotating.
20. video frequency identifying method according to claim 18, the step of wherein said execution characteristic matching is configured to: only use N dimension symmetric information eigenwert than preliminary the search characteristics database of upper strata bit, and secondly use the remaining bits of N dimension symmetric information eigenwert and only search for preliminary Search Results.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| KR1020090127713A KR101367821B1 (en) | 2009-12-21 | 2009-12-21 | video identification method and apparatus using symmetric information of hierachical image blocks |
| KR127713/09 | 2009-12-21 |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102103686A true CN102103686A (en) | 2011-06-22 |
| CN102103686B CN102103686B (en) | 2014-10-01 |
Family
ID=44156442
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201010246670.3A Expired - Fee Related CN102103686B (en) | 2009-12-21 | 2010-06-30 | Video identification system using symmetric information of graded image block and method thereof |
Country Status (2)
| Country | Link |
|---|---|
| KR (1) | KR101367821B1 (en) |
| CN (1) | CN102103686B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101537032B1 (en) * | 2014-05-15 | 2015-07-15 | 심해청 | Method for generating feature information for image filtering and recording-medium recorded program thereof |
| CN104219423B (en) * | 2014-09-25 | 2017-09-29 | 联想(北京)有限公司 | A kind of information processing method and device |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1893676A (en) * | 2005-06-29 | 2007-01-10 | 株式会社Ntt都科摩 | Video evaluation apparatus, spatio-temporal frequency analyzing apparatus, video evaluation method, spatio-temporal frequency analyzing method, video evaluation program, and spatio-temporal frequency |
| US20070253594A1 (en) * | 2006-04-28 | 2007-11-01 | Vobile, Inc. | Method and system for fingerprinting digital video object based on multiresolution, multirate spatial and temporal signatures |
| CN101170672A (en) * | 2006-10-24 | 2008-04-30 | 索尼株式会社 | Contents character information acquisition method, contents character information acquisition program, contents character information acquisition apparatus, and video content recording apparatus |
| CN101369281A (en) * | 2008-10-09 | 2009-02-18 | 湖北科创高新网络视频股份有限公司 | Retrieval method based on video abstract metadata |
| US20090141805A1 (en) * | 2007-12-03 | 2009-06-04 | Vobile, Inc. | Method and system for fingerprinting digital video object based on multiersolution, multirate spatial and temporal signatures |
| US20090238465A1 (en) * | 2008-03-18 | 2009-09-24 | Electronics And Telecommunications Research Institute | Apparatus and method for extracting features of video, and system and method for identifying videos using same |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001506820A (en) | 1996-11-27 | 2001-05-22 | プリンストン ビデオ イメージ，インコーポレイテッド | Motion tracking using image texture templates |
| US6462754B1 (en) | 1999-02-22 | 2002-10-08 | Siemens Corporate Research, Inc. | Method and apparatus for authoring and linking video documents |
| US6879731B2 (en) | 2003-04-29 | 2005-04-12 | Microsoft Corporation | System and process for generating high dynamic range video |
-
2009
- 2009-12-21 KR KR1020090127713A patent/KR101367821B1/en active IP Right Grant
-
2010
- 2010-06-30 CN CN201010246670.3A patent/CN102103686B/en not_active Expired - Fee Related
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1893676A (en) * | 2005-06-29 | 2007-01-10 | 株式会社Ntt都科摩 | Video evaluation apparatus, spatio-temporal frequency analyzing apparatus, video evaluation method, spatio-temporal frequency analyzing method, video evaluation program, and spatio-temporal frequency |
| US20070253594A1 (en) * | 2006-04-28 | 2007-11-01 | Vobile, Inc. | Method and system for fingerprinting digital video object based on multiresolution, multirate spatial and temporal signatures |
| CN101170672A (en) * | 2006-10-24 | 2008-04-30 | 索尼株式会社 | Contents character information acquisition method, contents character information acquisition program, contents character information acquisition apparatus, and video content recording apparatus |
| US20090141805A1 (en) * | 2007-12-03 | 2009-06-04 | Vobile, Inc. | Method and system for fingerprinting digital video object based on multiersolution, multirate spatial and temporal signatures |
| US20090238465A1 (en) * | 2008-03-18 | 2009-09-24 | Electronics And Telecommunications Research Institute | Apparatus and method for extracting features of video, and system and method for identifying videos using same |
| CN101369281A (en) * | 2008-10-09 | 2009-02-18 | 湖北科创高新网络视频股份有限公司 | Retrieval method based on video abstract metadata |
Also Published As
| Publication number | Publication date |
|---|---|
| KR20110071209A (en) | 2011-06-29 |
| KR101367821B1 (en) | 2014-02-26 |
| CN102103686B (en) | 2014-10-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US6470094B1 (en) | Generalized text localization in images | |
| US6473522B1 (en) | Estimating text color and segmentation of images | |
| CN103281473B (en) | General video steganalysis method based on video pixel space-time relevance | |
| Sowmya et al. | A survey on video forgery detection | |
| CN102124489A (en) | Signature derivation for images | |
| CN110659333B (en) | Multi-level visual feature description method and visual retrieval system | |
| CN103927767A (en) | Image processing method and device | |
| Li et al. | Copyright protection for holographic video using spatiotemporal consistent embedding strategy | |
| Gupta et al. | Video authentication in digital forensic | |
| Khodabakhshi et al. | Spider: A system for finding 3D video copies | |
| Verde et al. | Focal: A forgery localization framework based on video coding self-consistency | |
| CN102103686B (en) | Video identification system using symmetric information of graded image block and method thereof | |
| Lu et al. | Revealing digital fakery using multiresolution decomposition and higher order statistics | |
| CN103854249A (en) | Digital image watermarking method based on local index torque characteristic | |
| Sharma et al. | A review of passive forensic techniques for detection of copy-move attacks on digital videos | |
| Kumar et al. | Robust approach of video steganography using combined keypoints detection algorithm against geometrical and signal processing attacks | |
| US20170103285A1 (en) | Method and device for detecting copies in a stream of visual data | |
| Ho et al. | Effective images splicing detection based on decision fusion | |
| Lian et al. | Multimedia forensics for detecting forgeries | |
| Mercier et al. | Detecting manipulations in video | |
| Kumari et al. | Video Object Forgery Detection using Image Processing Techniques | |
| Gan et al. | Video Surveillance Object Forgery Detection using PDCL Network with Residual-based Steganalysis Feature | |
| US20180293461A1 (en) | Method and device for detecting copies in a stream of visual data | |
| Jegaveerapandian et al. | A survey on passive digital video forgery detection techniques. | |
| Hu | Big Data Analytics and Processing for Urban Surveillance Systems |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20141001 Termination date: 20210630 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |