Fast image compression using over-complete ICAMM
Chih-Cheng Peng, Chih‐Hong Kao, Sheng‐Ping Hsieh · 2010
This paper presents a new over complete ICAMM to make decomposition the basis for low-bit high-speed image compression on image sub-blocks. Although the over complete independent component analysis basic number is much larger than the original data dimension, most of the coefficients will be zero after performing the basis transform so that this algorithm reaches the low bit-rate compression goal. The over complete independent component effect approximates the wavelet basis functions. This is different from the discrete cosine function and wavelet function in that the independent component is relevant to the data itself. When using the over complete independent component analysis to decompose the image sub-blocks, it can divide self-adaptive learning into several subgroups based on the different characteristics of the text images. Each subgroup has a set of corresponding over complete independent components. In this way, it can be more efficient to reduce the bit rate use. At the same time the information in the subgroup can also be used in image transmission based on the different encodings. The experimental results show that our proposed approach achieves low bit-rate image compression.