Pattern retrieval using optimized compression transform

Daidi Zhong; Irek Defée

doi:10.1117/12.632732

24 June 2005 Pattern retrieval using optimized compression transform

Daidi Zhong, Irek Defée

Proceedings Volume 5960, Visual Communications and Image Processing 2005; 59604M (2005) https://doi.org/10.1117/12.632732
Event: Visual Communications and Image Processing 2005, 2005, Beijing, China

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.

Citation Download Citation

Daidi Zhong and Irek Defée "Pattern retrieval using optimized compression transform", Proc. SPIE 5960, Visual Communications and Image Processing 2005, 59604M (24 June 2005); https://doi.org/10.1117/12.632732

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available