A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2006; you can also visit the original URL.
The file type is
A coding method for face images by segmenting face regions such as eyes, mouth, etc. is introduced. Each region is removed from the face image, leaving a smoothly interpolated background which is suitable for e cient compression. Extracted region images are coded using vector quantization. The overall method is found to achieve comparable compression ratios with compatible image coding methods. Furthermore, separate encoding of face segments enables us to achieve speed improvements for a facedoi:10.1016/j.sigpro.2004.03.007 fatcat:kiituwi6czh57eqrmumlbpin5u