Processing

Please wait...

Settings

Settings

Goto Application

1. WO2012141655 - IN-VIDEO PRODUCT ANNOTATION WITH WEB INFORMATION MINING

Publication Number WO/2012/141655
Publication Date 18.10.2012
International Application No. PCT/SG2012/000127
International Filing Date 11.04.2012
IPC
G06K 9/62 2006.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
62Methods or arrangements for recognition using electronic means
CPC
G06F 16/7847
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
FELECTRIC DIGITAL DATA PROCESSING
16Information retrieval; Database structures therefor; File system structures therefor
70of video data
78Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
783using metadata automatically derived from the content
7847using low-level visual features of the video content
G06K 9/00744
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
00624Recognising scenes, i.e. recognition of a whole field of perception; recognising scene-specific objects
00711Recognising video content, e.g. extracting audiovisual features from movies, extracting representative key-frames, discriminating news vs. sport content
00744Extracting features from the video content, e.g. video "fingerprints", or characteristics, e.g. by automatic extraction of representative shots or key frames
G06K 9/4642
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
36Image preprocessing, i.e. processing the image information without deciding about the identity of the image
46Extraction of features or characteristics of the image
4642by performing operations within image blocks or by using histograms
Applicants
  • NATIONAL UNIVERSITY OF SINGAPORE [SG]/[SG] (AllExceptUS)
  • CHUA, Tat Seng [SG]/[SG] (UsOnly)
  • LI, Guangda [CN]/[SG] (UsOnly)
  • LU, Zheng [CN]/[SG] (UsOnly)
  • WANG, Meng [CN]/[SG] (UsOnly)
Inventors
  • CHUA, Tat Seng
  • LI, Guangda
  • LU, Zheng
  • WANG, Meng
Agents
  • AMICA LAW LLC
Priority Data
61/474,32812.04.2011US
Publication Language English (EN)
Filing Language English (EN)
Designated States
Title
(EN) IN-VIDEO PRODUCT ANNOTATION WITH WEB INFORMATION MINING
(FR) ANNOTATION DE PRODUIT VIDÉO AVEC EXPLORATION D'INFORMATIONS WEB
Abstract
(EN)
A system provides product annotation in a video to one or more users. The system receives a video from a user, where the video includes multiple video frames. The system extracts multiple key frames from the video and generates a visual representation of the key frame. The system compares the visual representation of the key frame with a plurality of product visual signatures, where each visual signature identifies a product. Based on the comparison of the visual representation of the key frame and a product visual signature, the system determines whether the key frame contains the product identified by the visual signature of the product. To generate the plurality of product visual signatures, the system collects multiple training images comprising multiple of expert product images obtained from an expert product repository, each of which is associated with multiple product images obtained from multiple web resources.
(FR)
La présente invention porte sur un système permettant une annotation de produit dans une vidéo destinée à un ou plusieurs utilisateurs. Le système reçoit une vidéo d'un utilisateur, la vidéo comprenant des trames vidéo multiples. Le système extrait des trames clés multiples de la vidéo et génère une représentation visuelle de la trame clé. Le système compare la représentation visuelle de la trame clé à une pluralité de signatures visuelles de produits, chaque signature visuelle identifiant un produit. En fonction de la comparaison de la représentation visuelle de la trame clé et d'une signature visuelle de produit, le système détermine si la trame clé contient le produit identifié par la signature visuelle du produit. Pour générer la pluralité de signatures visuelles de produits, le système collecte des images d'apprentissage multiples contenant de multiples images de produits experts obtenues à partir d'un référentiel de produits experts, chacun d'elles étant associée à des images de produit multiples obtenues à partir de ressources Web multiples.
Also published as
GB1319882.5
Latest bibliographic data on file with the International Bureau