Content-based image retrieval using H.264 intra coding features

NCUIR > College of Electrical Engineering & Computer Science > Department of Communication Engineering > journal & Dissertation > Item 987654321/105897

Please use this identifier to cite or link to this item: https://ir.lib.ncu.edu.tw/handle/987654321/105897

Title:	Content-based image retrieval using H.264 intra coding features
Authors:	張寶基;Wang, Ren-Jie;Yang, Ya-Ting;Chang, Pao-Chi
Contributors:	資訊電機學院通訊工程學系
Keywords:	Applied sciences;Artificial intelligence;Coding;Coding, codes;Compression domain;Computer science;control theory;systems;Content-based image/video retrieval;Exact sciences and technology;Geometrical verification;H.264;Image compression;Image search;Information systems. Data bases;Information, signal and communications theory;Intra prediction;Memory and file management (including protection and security);Memory organisation. Data processing;Multimedia;Pattern recognition. Digital image processing. Computational geometry;Retrieval;Signal and communications theory;Software;Surface layer;Telecommunications and information theory;Texture;Texture features;Video coding;Visual
Date:	2014-01-01
Issue Date:	2026-04-23 13:00:18 (UTC+8)
Publisher:	Academic Press Inc.;Amsterdam: Elsevier Inc
Abstract:	摘要： •This paper focuses on content-based image retrieval in the H.264 compression domain.•Intra prediction mode and residual coefficient are extracted as the texture feature to match images.•The proposed method substantially reduce computational and memory consumption, compared with the pixel domain approach. Efficient multimedia retrieval has become a vital issue because more audio and video data are now available. This paper focuses on content-based image retrieval (CBIR) in the compression domain (CPD). The retrieval features are extracted based on I-frame coding information in H.264. This paper proposes using a local mode histogram as the texture feature to match images and applying the residual coefficients to filter non-confident modes. The geometrical correspondence between two images is also considered. The experimental results show that the proposed method can substantially reduce computational and memory resource consumption, and provides similar performance compared with methods that extract features from decompressed images. 出版者： Amsterdam: Elsevier Inc 出版日期： 2014-07-01 出處： Journal of visual communication and image representation, 2014-07, Vol.25 (5), p.963-969 資源來源： Elsevier ScienceDirect Journals Complete 版權： 2014 Elsevier Inc. 版權： 2015 INIST-CNRS 識別號： ISSN: 1047-3203 識別號： EISSN: 1095-9076 識別號： DOI: 10.1016/j.jvcir.2014.02.016
Appears in Collections:	[Department of Communication Engineering] journal & Dissertation

Files in This Item:

File	Description	Size	Format
index.html		0Kb	HTML	13	View/Open

社群 sharing

Loading...