Color personal ID photo compression based on object segmentation

Author

Qiuyu, Zhu ; Suozhong, Wang

Author_Institution

Sch. of Commun. & Inf., Shanghai Univ., China

fYear

2005

fDate

24-26 Aug. 2005

Firstpage

566

Lastpage

569

Abstract

The paper studies color personal identification photo compression based on object segmentation. Using an object pattern recognition method, a personal ID photo is divided into three regions - background, head-and-shoulder region and facial region. Different regions have different image qualities. After adopting the Freeman chain code description and its arithmetic coding of background boundary, background adaptive gray padding, bit-plane shift quality graded compression algorithm, and JPEG-2000 based wavelet transform and EBCOT coding scheme, a good result that is better than the standard JPEG-2000 is obtained.

Keywords

data compression; image coding; image colour analysis; image segmentation; object recognition; wavelet transforms; Freeman chain code description; JPEG-2000 based wavelet transform; arithmetic coding; background adaptive gray padding; background boundary; bit-plane shift quality graded compression algorithm; color personal identification photo compression; facial region; head-and-shoulder region; image qualities; object pattern recognition method; object segmentation; Arithmetic; Compression algorithms; Image coding; Image quality; Image storage; Object segmentation; Pattern recognition; Transform coding; Vector quantization; Wavelet coefficients;

fLanguage

English

Publisher

ieee

Conference_Titel

Communications, Computers and signal Processing, 2005. PACRIM. 2005 IEEE Pacific Rim Conference on

Print_ISBN

0-7803-9195-0

Type

conf

DOI

10.1109/PACRIM.2005.1517352

Filename

1517352