Share Email Print
cover

Proceedings Paper

Pattern retrieval using optimized compression transform
Author(s): Daidi Zhong; Irek Defée
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Images and video are currently predominantly handled in compressed form. Block-based compression standards are by far the most widespread. It is thus important to devise information processing methods operating directly in compressed domain. In this paper we investigate this possibility on the example of simple face information processing method based on the H.264 AC Transformed blocks. We use patterns of quantized 4x4 transformed blocks for representing local picture information. These patterns at different quantization levels provide very flexible representation of picture information. By combining both the AC and DC information, we represent global information in pictures by histograms of quantized block pattern distributions. The approach is tested on FERET database of face images and it is shown that despite its simplicity provides good results in the face recognition problem.

Paper Details

Date Published: 24 June 2005
PDF: 8 pages
Proc. SPIE 5960, Visual Communications and Image Processing 2005, 59604M (24 June 2005); doi: 10.1117/12.632732
Show Author Affiliations
Daidi Zhong, Tampere Univ. of Technology (Finland)
Irek Defée, Tampere Univ. of Technology (Finland)


Published in SPIE Proceedings Vol. 5960:
Visual Communications and Image Processing 2005

© SPIE. Terms of Use
Back to Top