An Adaptive Image Compression Method Based on Vector Quantization
Jau-Ji Shen, Hsiu-Chuan Huang · 2010
With the growth of Internet, Image compression has become a popular issue. Since the traditional Vector Quantization (VQ) produces compressed images with a quality at about 27 to 30 dB or so, the techniques of quality improvement is limited. Thus in this paper, we proposed an adaptive image compression method based on VQ, which can adjust the encoding of the difference map between the original image and its restored VQ compressed version. Experimental results show that although our scheme needs to provide extra data, it can substantially improve the quality of VQ compressed images, and further be adjusted depending on the difference map from the lossy compression to lossless compression.