Visually Improved Image Compression by Combining EZW Encoding with Texture Modeling using Huffman Encoder
This paper proposes a technique for image compression which uses the Wavelet-based Image/Texture Coding Hybrid (WITCH) scheme [1] in combination with Huffman encoder. It implements a hybrid coding approach, while nevertheless preserving the features of progressive and lossless coding. The hybrid scheme was designed to encode the structural image information by Embedded Zerotree Wavelet (EZW) encoding algorithm [2] and the stochastic texture in a model-based manner & this encoded data is then compressed using Huffman encoder. The scheme proposed here achieves superior subjective quality while increasing the compression ratio by more than a factor of three or even four. With this technique, it is possible to achieve compression ratios as high as 10 to 12 but with some minor distortions in the encoded image.
Keywords: Image compression, Huffman encoder, Zero tree Wavelet
Download Full-Text
