Title :
Image Features Extraction for Multimedia Database Content Description
Author_Institution :
Dept. of Electr. Eng., Nat. Defense Univ.
Abstract :
The new multimedia content description standard MPEG-7 and its related framework standard MPEG-21 have been gained lots of interests by the academic and multimedia industry recently. One of the key issues that need to be determined is how to correctly extract and measure the similarity of content features. In this paper, we focus on how to effectively extract the image features and select the similar images from database. We adopt the principle component analysis (PCA), wavelet decomposition (WD) and moment invariants (MI) methods to extract image features. The head-and-shoulder images (standard test images and AR database) are the main interests. The simulation results shown that our proposed algorithms can successfully select the closest images from database according to the query image
Keywords :
database indexing; feature extraction; multimedia databases; principal component analysis; standards; video coding; visual databases; wavelet transforms; MI methods; MPEG-21 standard; MPEG-7 standard; PCA; head-and-shoulder images; image feature extraction; moment invariants; multimedia database content description; multimedia database indexing; principle component analysis; query image; wavelet decomposition; Data security; Face detection; Feature extraction; Fingerprint recognition; Humans; Image databases; Multimedia databases; Principal component analysis; Spatial databases; Wavelet analysis; Decomposition (WD); Feature Extraction; Moment Invariants (MI); Multimedia Database Indexing; Principle Component Analysis (PCA); Wavelet;
Conference_Titel :
Computer and Information Science, 2006 and 2006 1st IEEE/ACIS International Workshop on Component-Based Software Engineering, Software Architecture and Reuse. ICIS-COMSAR 2006. 5th IEEE/ACIS International Conference on
Conference_Location :
Honolulu, HI
Print_ISBN :
0-7695-2613-6
DOI :
10.1109/ICIS-COMSAR.2006.45
