Title :
Compression of color facial images using feature correction two-stage vector quantization
Author :
Jincheng Huang ; Wang, Yao
Author_Institution :
Dept. of Electr. Eng., Polytech. Univ., Brooklyn, NY, USA
Abstract :
A Feature Correction Two Stage Vector Quantization (FC2VQ) algorithm was previously developed to compress gray-scale photo ID pictures. This algorithm is extended to color images in this paper. Two options are compared, which apply the FC2VQ algorithm in RGB and YCbCr color spaces, respectively. The RGBFC2VQ algorithm is found to yield better image quality than YCbCr-FC2VQ at similar bitrate. With the RGB-FC2VQ algorithm, a 128×128 24-bit color ID image (49,152 bytes) can be compressed down to 500 bytes with satisfactory quality
Keywords :
face recognition; feature extraction; image coding; vector quantisation; 24 bit; FC2VQ; RGB color space; YCbCr color space; bitrate; color facial images; feature correction; image compression; image quality; two-stage vector quantization; Color; Eyes; Facial features; Gray-scale; Image coding; Image quality; Knowledge based systems; Mouth; Transform coding; Vector quantization;
Conference_Titel :
Circuits and Systems, 1997. ISCAS '97., Proceedings of 1997 IEEE International Symposium on
Print_ISBN :
0-7803-3583-X
DOI :
10.1109/ISCAS.1997.622059
