Finite automata and regularized edge preserving wavelet transform scheme
被引:0
作者:
Hong, Sung-Wai
论文数: 0引用数: 0
h-index: 0
机构:
Hong Kong Polytechnic Univ, Kowloon, Hong KongHong Kong Polytechnic Univ, Kowloon, Hong Kong
Hong, Sung-Wai
[1
]
Bao, Paul
论文数: 0引用数: 0
h-index: 0
机构:
Hong Kong Polytechnic Univ, Kowloon, Hong KongHong Kong Polytechnic Univ, Kowloon, Hong Kong
Bao, Paul
[1
]
机构:
[1] Hong Kong Polytechnic Univ, Kowloon, Hong Kong
来源:
Data Compression Conference Proceedings
|
1999年
关键词:
Feature extraction - Finite automata - Image coding - Image reconstruction - Least squares approximations - Signal to noise ratio - Wavelet transforms;
D O I:
暂无
中图分类号:
学科分类号:
摘要:
An edge preserving image compression technique based on the wavelet transform and iterative constrained least square regularization is introduced. In particular, a scheme based on generalized finite automata (GFA) scheme is used to compromise the rate of edge information and DWT coded image data. GFA is used instead of vector quantization in order to achieve adaptive encoding of the edge image.