Font Size: a A A

Retrieval Based On Mpeg-7 Standard Animation Lens

Posted on:2007-04-17Degree:MasterType:Thesis
Country:ChinaCandidate:W LiFull Text:PDF
GTID:2208360185491371Subject:Pattern Recognition and Intelligent Systems
Abstract/Summary:PDF Full Text Request
Along with the CG cartoon be popular in the world, how can make the CG films better and more quickly become the cartoon producers' desire. If they can find the already existed proper material scenes and have the further production, it can be surely to enhance their works efficiently and will reduce much investment for producing cartoon films.Content-based image retrieval technology has been a research hot spot in the recent year, On the other hand, due to the complexity of the information, the lack of standard for the description of information content induces low interoperability among retrieval methods and retrieval systems. To meet this challenge, MPEG-7 was started as a solution to the normative description of audiovisual content. MPEG-7 relates the description with its content, and enables the effective and efficient query and access to multimedia content.In this paper, we use the MPEG-7 to retrieve the key frames of the cartoon's scenes, the main contents are:(1) Expatiate the color descriptors of the MPEG-7 standard. The color layout and domain color descriptor are used in retrieval test and the performance is discussed.(2) Expatiate the texture descriptors of the MPEG-7 standard. The homogeneous texture descriptor and is used in retrieval test and the performance is discussed.(3) A method for extracting the key frames from the cartoon scenes using the domain color descriptor is presented and we do the same experiment.(4) Since the domain color descriptor and the homogeneous texture descriptor have the different effect scope, combine the two descriptors to retrieve the key frames.Based on the survey, some open issues, which need to be researched further, are presented, and the future research trends are also given.
Keywords/Search Tags:MPEG-7, Color Descriptor, Texture Descriptor, Image retrieval
PDF Full Text Request
Related items