WO2008082188A1 - Cognitive method for object of moving picture - Google Patents

Cognitive method for object of moving picture Download PDF

Info

Publication number
WO2008082188A1
WO2008082188A1 PCT/KR2007/006947 KR2007006947W WO2008082188A1 WO 2008082188 A1 WO2008082188 A1 WO 2008082188A1 KR 2007006947 W KR2007006947 W KR 2007006947W WO 2008082188 A1 WO2008082188 A1 WO 2008082188A1
Authority
WO
WIPO (PCT)
Prior art keywords
moving picture
recognizing
frame
picture
recognized
Prior art date
Application number
PCT/KR2007/006947
Other languages
French (fr)
Inventor
In-Yong Lee
Original Assignee
Lime Bt Solution Co., Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Lime Bt Solution Co., Ltd filed Critical Lime Bt Solution Co., Ltd
Publication of WO2008082188A1 publication Critical patent/WO2008082188A1/en

Links

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N5/00—Details of television systems
    • H04N5/76—Television signal recording
    • H04N5/91—Television signal processing therefor
    • 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
    • G06F16/7837—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using objects detected or recognised in the video content
    • G06F16/784—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using objects detected or recognised in the video content the detected or recognised objects being people
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/40—Scenes; Scene-specific elements in video content
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/172—Classification, e.g. identification
    • G06V40/173—Classification, e.g. identification face re-identification, e.g. recognising unknown faces across different face tracks
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N5/00—Details of television systems
    • H04N5/76—Television signal recording
    • H04N5/91—Television signal processing therefor
    • H04N5/93—Regeneration of the television signal or of selected parts thereof
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N5/00—Details of television systems
    • H04N5/76—Television signal recording
    • H04N5/78—Television signal recording using magnetic recording
    • H04N5/782—Television signal recording using magnetic recording on tape
    • H04N5/783—Adaptations for reproducing at a rate different from the recording rate

Definitions

  • the present invention relates to a method for recognizing an object of a moving picture, and more particularly, to a method for recognizing an object by checking frames before and after a reference frame in order to accurately recognize a frame located at a selected position if desired contents of successive pictures are desired to be received.
  • a desired video a moving picture such as movie, drama, a documentary program
  • a fundamental technology for non-linear video browsing and searching includes a shot segmentation method and a shot clustering method, both of which are major technologies for analyzing a video.
  • the shot indicates a sequence of video frames obtained from a single camera without interruption and is the basic unit for analyzing or constructing a video.
  • the video is composed of a large number of shots.
  • a desired image can be searched for and received at a desired point of time using the shot.
  • the present invention has been made in view of the above problems, and it is an object of the present invention to provide a method for recognizing an object by checking frames before and after a reference frame in order to accurately recognize a frame located at a selected position if desired contents of successive pictures are desired to be received.
  • the above and other objects can be accomplished by the provision of a method for recognizing an object of a moving picture, the method including: (1) at a moving picture object recognizing system, providing the moving picture according to a request of a user; (2) at the moving picture object recognizing system, determining whether the user selects a predetermined object from the provided moving picture; (3) at the moving picture object recognizing system, recognizing the selected object; (4) at the moving picture object recognizing system, determining whether the recognition of the selected object fails; (5) at the moving picture object recognizing system, recognizing the object by checking a frame before a frame, in which the selected object exists, the recognition of the object being performed while skipping the frame at an interval of n frames (n is an integer) on the basis of a reference picture; (6) at the moving picture object recognizing system, determining whether the object is recognized; and (7) at the moving picture object recognizing system, providing contents which are stored in correspondence with the object, if the object is recognized.
  • the step (5) may include comparing the reference picture and a picture before the reference picture so as to check whether a change portion exists and recognizing the change portion as the object.
  • the step (7) may include, at the moving picture object recognizing system, estimating that the same object exists even in a frame in which the object is not recognized and which is interposed between the reference picture and a frame in which the object is recognized.
  • the moving picture object recognizing system may recognize that the same object exists even in a frame, which is not checked, when the object is recognized from a predetermined frame.
  • the moving picture object recognizing system may finish a recognizing process when a picture change between two compared frames is remarkably increased while the object of the moving picture is recognized with respect to a predetermined frame.
  • FIG. 1 is a block diagram showing a system for recognizing an object of a moving picture according to the present invention
  • FIG. 2 is a flowchart illustrating a method for recognizing an object of a moving picture according to the present invention
  • FIG. 3 is a view explaining the method for recognizing the object of the moving picture according to the present invention while skipping a frame;
  • FIG. 4 is a view explaining a frame flow according to rollback;
  • FIG. 5 is a view explaining a frame flow according to a scene change
  • FIG. 6 is a graph showing the scene change according to the frame flow shown in FIG. 5.
  • a system which implements the method for recognizing the object of the moving picture according to the present invention includes user terminals 100 in which a communication environment is established, such as a personal computer (PC) , a personal digital assistant (PDA) or a mobile telephone, a moving picture provision system 200 for providing the moving picture to a moving picture object recognizing system 300 through a data communication network 400, the moving picture object recognizing system 300 for providing the moving picture received from the moving picture provision system 200 to the user terminal 100, recognizing an object of a selected area when a portion of the moving picture provided to each of the user terminals 100 is selected, and providing contents corresponding thereto, and the data communication network 400 which is a wired/wireless data communication network including the Internet and a wireless application protocol (WAP) , that allows a plurality of unspecified users who possess the user terminals 100 to accomplish a communication environment with the moving picture object recognizing system 300, and accomplishes a communication environment between the moving picture object recognizing system 300 and the moving picture provision system 200.
  • WAP wireless application
  • the moving picture object recognizing system 300 compares a reference picture and a picture before the reference picture so as to check whether a change portion exists and recognizes the change portion as the object.
  • the moving picture object recognizing system 300 estimates that the same object exists even in a frame in which the object is not recognized and which is interposed between the reference picture and the frame in which the object is recognized.
  • the moving picture object recognizing system 300 recognizes the object while skipping the frame at an interval of n frames on the basis of the reference picture, when recognizing the object.
  • n is an integer.
  • the moving picture object recognizing system 300 recognizes that the same object exists in a frame, which is not checked, when the object is recognized from a predetermined frame .
  • the moving picture object recognizing system 300 finishes the recognizing process if the picture change between two compared frames is remarkably increased while the object of the moving picture is recognized with respect to the predetermined frame .
  • the method for recognizing the object of the moving picture will be described with reference to FIGS. 2 to 4.
  • the moving picture object recognizing system 300 allows the user terminal 10 to search and request for the moving picture provided by the moving picture provision system 200 and provides the moving picture according to the request of the user (SIlO) .
  • the moving picture object recognizing system 300 determines whether a user selects a specific object from the moving picture (S120) . If it is determined that the user selects the predetermined object, then the moving picture object recognizing system 300 recognizes the selected object
  • the moving picture object recognizing system 300 checks the recognition of the selected object and determines whether the recognition of the object fails (S140) . If it is determined that the recognition of the moving picture fails, then the moving picture object recognizing system 300 checks a frame before a frame, in which the selected object exists, and recognizes the object (S150) . That is, when the object is recognized, as shown in FIG.
  • the moving picture object recognizing system 300 employs a rollback method for recognizing the object while skipping the frame at an interval of n frames on the basis of the reference picture.
  • n is an integer and is preferably 2.
  • the moving picture object recognizing system 300 determines whether the object recognized (S160) . If the object is recognized, the moving picture object recognizing system 300 provides contents which are stored in correspondence with the object (S170) .
  • the moving picture object recognizing system 300 estimates that the same object exists even in the frame in which the object is not recognized and which is interposed between the reference picture and the frame in which the object is recognized.
  • the moving picture object recognizing system 300 recognizes that the same object exists even in the frame, which is not checked, when the object is recognized from the predetermined frame . Finally, the moving picture object recognizing system 300 finishes the recognizing process if the picture change between two compared frames is remarkably increased while the object of the moving picture is recognized with respect to the predetermined frame, as shown in FIGS. 5 and 6.

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Signal Processing (AREA)
  • Databases & Information Systems (AREA)
  • Library & Information Science (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Human Computer Interaction (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Image Analysis (AREA)

Abstract

A method for recognizing an object by checking frames before and after a reference frame in order to accurately recognize a frame located at a selected position if desired contents of successive pictures are desired to be received is disclosed. A moving picture object recognizing system provides a moving picture according to a request of a user, determines whether the user selects a predetermined object from the provided moving picture, recognizes the selected object, recognizes the object by checking a frame before a frame, in which the selected object exists, if the recognition of the selected object fails, and provides contents which are stored in correspondence with the object if the object is recognized.

Description

[DESCRIPTION]
[invention Title]
COGNITIVE METHOD FOR OBJECT OF MOVING PICTURE [Technical Field] The present invention relates to a method for recognizing an object of a moving picture, and more particularly, to a method for recognizing an object by checking frames before and after a reference frame in order to accurately recognize a frame located at a selected position if desired contents of successive pictures are desired to be received.
[Background Art]
As digital video technologies and image/video recognition technologies have been developed, users can search for/filter and browse only a desired portion of a desired video (a moving picture such as movie, drama, a documentary program) at a desired point of time.
A fundamental technology for non-linear video browsing and searching includes a shot segmentation method and a shot clustering method, both of which are major technologies for analyzing a video.
Accordingly, until now, many researches have been concentrated on the shot segmentation technology and researches into the shot clustering technology are being started.
The shot indicates a sequence of video frames obtained from a single camera without interruption and is the basic unit for analyzing or constructing a video.
In general, the video is composed of a large number of shots. As described above, a desired image can be searched for and received at a desired point of time using the shot. In the present invention, there is a need for accurate recognition of an object when contents included in the object of a moving picture are desired to be received. [Disclosure] [Technical Problem] Therefore, the present invention has been made in view of the above problems, and it is an object of the present invention to provide a method for recognizing an object by checking frames before and after a reference frame in order to accurately recognize a frame located at a selected position if desired contents of successive pictures are desired to be received. [Technical Solution]
In accordance with an aspect of the present invention, the above and other objects can be accomplished by the provision of a method for recognizing an object of a moving picture, the method including: (1) at a moving picture object recognizing system, providing the moving picture according to a request of a user; (2) at the moving picture object recognizing system, determining whether the user selects a predetermined object from the provided moving picture; (3) at the moving picture object recognizing system, recognizing the selected object; (4) at the moving picture object recognizing system, determining whether the recognition of the selected object fails; (5) at the moving picture object recognizing system, recognizing the object by checking a frame before a frame, in which the selected object exists, the recognition of the object being performed while skipping the frame at an interval of n frames (n is an integer) on the basis of a reference picture; (6) at the moving picture object recognizing system, determining whether the object is recognized; and (7) at the moving picture object recognizing system, providing contents which are stored in correspondence with the object, if the object is recognized.
The step (5) may include comparing the reference picture and a picture before the reference picture so as to check whether a change portion exists and recognizing the change portion as the object.
The step (7) may include, at the moving picture object recognizing system, estimating that the same object exists even in a frame in which the object is not recognized and which is interposed between the reference picture and a frame in which the object is recognized.
In the step (5) , the moving picture object recognizing system may recognize that the same object exists even in a frame, which is not checked, when the object is recognized from a predetermined frame.
The moving picture object recognizing system may finish a recognizing process when a picture change between two compared frames is remarkably increased while the object of the moving picture is recognized with respect to a predetermined frame.
[Advantageous Effects]
According to the present invention, when desired contents of successive pictures are desired to be received, it is possible to accurately recognize an object by checking frames before and after a reference frame in order to accurately recognize a frame which exists at a selected position. [Description of Drawings]
The above and other objects, features and other advantages of the present invention will be more clearly understood from the following detailed description taken in conjunction with the accompanying drawings, in which:
FIG. 1 is a block diagram showing a system for recognizing an object of a moving picture according to the present invention; FIG. 2 is a flowchart illustrating a method for recognizing an object of a moving picture according to the present invention;
FIG. 3 is a view explaining the method for recognizing the object of the moving picture according to the present invention while skipping a frame; FIG. 4 is a view explaining a frame flow according to rollback;
FIG. 5 is a view explaining a frame flow according to a scene change; and FIG. 6 is a graph showing the scene change according to the frame flow shown in FIG. 5. [Best Mode]
Hereinafter, a method for recognizing an object of a moving picture according to the present invention will be described in detail with reference to the accompanying drawings.
As shown in FIG. 1, a system which implements the method for recognizing the object of the moving picture according to the present invention includes user terminals 100 in which a communication environment is established, such as a personal computer (PC) , a personal digital assistant (PDA) or a mobile telephone, a moving picture provision system 200 for providing the moving picture to a moving picture object recognizing system 300 through a data communication network 400, the moving picture object recognizing system 300 for providing the moving picture received from the moving picture provision system 200 to the user terminal 100, recognizing an object of a selected area when a portion of the moving picture provided to each of the user terminals 100 is selected, and providing contents corresponding thereto, and the data communication network 400 which is a wired/wireless data communication network including the Internet and a wireless application protocol (WAP) , that allows a plurality of unspecified users who possess the user terminals 100 to accomplish a communication environment with the moving picture object recognizing system 300, and accomplishes a communication environment between the moving picture object recognizing system 300 and the moving picture provision system 200.
The moving picture object recognizing system 300 compares a reference picture and a picture before the reference picture so as to check whether a change portion exists and recognizes the change portion as the object.
When the object is recognized, the moving picture object recognizing system 300 estimates that the same object exists even in a frame in which the object is not recognized and which is interposed between the reference picture and the frame in which the object is recognized.
The moving picture object recognizing system 300 recognizes the object while skipping the frame at an interval of n frames on the basis of the reference picture, when recognizing the object. Here, n is an integer.
The moving picture object recognizing system 300 recognizes that the same object exists in a frame, which is not checked, when the object is recognized from a predetermined frame . The moving picture object recognizing system 300 finishes the recognizing process if the picture change between two compared frames is remarkably increased while the object of the moving picture is recognized with respect to the predetermined frame . Now, the method for recognizing the object of the moving picture will be described with reference to FIGS. 2 to 4.
As shown in FIG. 2, in the method for recognizing object of the moving picture, the moving picture object recognizing system 300 allows the user terminal 10 to search and request for the moving picture provided by the moving picture provision system 200 and provides the moving picture according to the request of the user (SIlO) .
The moving picture object recognizing system 300 determines whether a user selects a specific object from the moving picture (S120) . If it is determined that the user selects the predetermined object, then the moving picture object recognizing system 300 recognizes the selected object
(S130) . At this time, in the method for object of the moving picture, as shown in FIG. 3, the reference picture and the picture before the reference picture are compared so as to check whether a change portion exists and the change portion is recognized as the object.
The moving picture object recognizing system 300 checks the recognition of the selected object and determines whether the recognition of the object fails (S140) . If it is determined that the recognition of the moving picture fails, then the moving picture object recognizing system 300 checks a frame before a frame, in which the selected object exists, and recognizes the object (S150) . That is, when the object is recognized, as shown in FIG.
4, the moving picture object recognizing system 300 employs a rollback method for recognizing the object while skipping the frame at an interval of n frames on the basis of the reference picture. Here, n is an integer and is preferably 2. At this time, in the step S150 of recognizing the object, the moving picture object recognizing system 300 determines whether the object recognized (S160) . If the object is recognized, the moving picture object recognizing system 300 provides contents which are stored in correspondence with the object (S170) .
If the object is recognized in the step S160, the moving picture object recognizing system 300 estimates that the same object exists even in the frame in which the object is not recognized and which is interposed between the reference picture and the frame in which the object is recognized.
That is, the moving picture object recognizing system 300 recognizes that the same object exists even in the frame, which is not checked, when the object is recognized from the predetermined frame . Finally, the moving picture object recognizing system 300 finishes the recognizing process if the picture change between two compared frames is remarkably increased while the object of the moving picture is recognized with respect to the predetermined frame, as shown in FIGS. 5 and 6. Although the preferred embodiments of the present invention have been disclosed for illustrative purposes, those skilled in the art will appreciate that various modifications, additions and substitutions are possible, without departing from the scope and spirit of the invention as disclosed in the accompanying claims.
[industrial Applicability]
As described above, according to the present invention, when desired contents of successive pictures are desired to be received, it is possible to accurately recognize an object by checking frames before and after a reference frame in order to accurately recognize a frame which exists at a selected position.

Claims

[CLAIMS]
[Claim l]
A method for recognizing an object of a moving picture, the method comprising: (1) at a moving picture object recognizing system, providing the moving picture according to a request of a user;
(2) at the moving picture object recognizing system, determining whether the user selects a predetermined object from the provided moving picture;
(3) at the moving picture object recognizing system, recognizing the selected object;
(4) at the moving picture object recognizing system, determining whether the recognition of the selected object fails;
(5) at the moving picture object recognizing system, recognizing the object by checking a frame before a frame, in which the selected object exists, the recognition of the object being performed while skipping the frame at an interval of n frames (n is an integer) on the basis of a reference picture;
(6) at the moving picture object recognizing system, determining whether the object is recognized; and
(7) at the moving picture object recognizing system, providing contents which are stored in correspondence with the object, if the object is recognized. [Claim 2]
The method according to claim 1, wherein the ste comprises comparing the reference picture and a picture k the reference picture so as to check whether a change pc exists and recognizing the change portion as the object. [Claim 3]
The method according to claim 1, wherein the ste comprises, at the moving picture object recognizing s} estimating that the same object exists even in a frame in the object is not recognized and which is interposed be the reference picture and a frame in which the obje< recognized. [Claim 4]
The method according to claim 1, wherein, in the st the moving picture object recognizing system recognizes the same object exists even in a frame, which is not ch« when the object is recognized from a predetermined frame. [Claim 5]
The method according to claim 1, wherein the r picture object recognizing system finishes a recogi process when a picture change between two compared frarr remarkably increased while the object of the moving picti recognized with respect to a predetermined frame.
PCT/KR2007/006947 2006-12-29 2007-12-28 Cognitive method for object of moving picture WO2008082188A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
KR1020060137754A KR100771220B1 (en) 2006-12-29 2006-12-29 Cognitive method for object of moving picture
KR10-2006-0137754 2006-12-29

Publications (1)

Publication Number Publication Date
WO2008082188A1 true WO2008082188A1 (en) 2008-07-10

Family

ID=38816220

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/KR2007/006947 WO2008082188A1 (en) 2006-12-29 2007-12-28 Cognitive method for object of moving picture

Country Status (2)

Country Link
KR (1) KR100771220B1 (en)
WO (1) WO2008082188A1 (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR101945487B1 (en) * 2017-08-02 2019-02-07 에스케이텔레콤 주식회사 Apparatus and method for recognizing object included in video data

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH08139995A (en) * 1994-11-11 1996-05-31 Canon Inc Method for detecting scene change point of moving image
JPH09130732A (en) * 1995-11-01 1997-05-16 Matsushita Electric Ind Co Ltd Scene change detection method and dynamic image edit device
JP2000324499A (en) * 1999-05-14 2000-11-24 Fujitsu Ltd Picture processor and method for detecting scene change
WO2003098549A1 (en) * 2001-03-26 2003-11-27 Konan Technology Inc. Scene change detector algorithm in image sequence

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR100441963B1 (en) * 2001-03-26 2004-07-27 주식회사 코난테크놀로지 Scene Change Detector Algorithm in Image Sequence

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH08139995A (en) * 1994-11-11 1996-05-31 Canon Inc Method for detecting scene change point of moving image
JPH09130732A (en) * 1995-11-01 1997-05-16 Matsushita Electric Ind Co Ltd Scene change detection method and dynamic image edit device
JP2000324499A (en) * 1999-05-14 2000-11-24 Fujitsu Ltd Picture processor and method for detecting scene change
WO2003098549A1 (en) * 2001-03-26 2003-11-27 Konan Technology Inc. Scene change detector algorithm in image sequence

Also Published As

Publication number Publication date
KR100771220B1 (en) 2007-10-29

Similar Documents

Publication Publication Date Title
JP7171884B2 (en) Pedestrian recognition method and device
US11120078B2 (en) Method and device for video processing, electronic device, and storage medium
US9977989B2 (en) Systems and methods for identifying objects and providing information related to identified objects
JP5457434B2 (en) Data access based on image content recorded by mobile devices
CN111046235B (en) Method, system, equipment and medium for searching acoustic image archive based on face recognition
US20080267521A1 (en) Motion and image quality monitor
US20110243449A1 (en) Method and apparatus for object identification within a media file using device identification
JP2010514023A (en) How to automatically prefetch words while entering multimedia message text
EP2460117A1 (en) System and method of using facial recognition to update a personal contact list
WO2008155686A1 (en) Method, apparatus and computer program product for providing association of objects using metadata
CN105100513B (en) Method for processing message of incoming call and device, incoming call service server
CN110321863A (en) Age recognition methods and device, storage medium
US20070239457A1 (en) Method, apparatus, mobile terminal and computer program product for utilizing speaker recognition in content management
CN109992176A (en) A kind of scan method and device of message identification code
CN109634913A (en) Storage method, device and the electronic equipment of document
CN103959305B (en) Method for performing face recognition in radio access network
CN110110207A (en) A kind of information recommendation method, device and electronic equipment
CN105897570A (en) Pushing method and device
WO2008082188A1 (en) Cognitive method for object of moving picture
CN110020309A (en) A kind of page processing method and device
CN112559852A (en) Information recommendation method and device
CN105786986A (en) Picture finding method and device
CN110147426B (en) Method for determining classification label of query text and related device
CN114117058A (en) Account information determination method and device, electronic equipment and storage medium
Liu et al. Video key-frame extraction for smart phones

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 07860732

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC, EPO FORM 1205A SENT ON 09/10/09

122 Ep: pct application non-entry in european phase

Ref document number: 07860732

Country of ref document: EP

Kind code of ref document: A1