Entropy Coding Based Set Partitioning in Entropy Coding Based Set Partitioning in Hierarchical Trees (SPIHT) Trees (SPIHT)

Abstract

As we know that images are the most important Digital data now a days. Image compression plays vital role in terms of saving storage space and reduction of transmission time. Wavelet transform is considered as landmark in the field of image compression due to the feature that it represents a signal in terms of functions those are localized in both frequency and time domain, as not in case of other Transformation techniques. Set Partitioning in Hierarchical Trees (SPIHT) is based on wavelet transform gives us the better image quality after the compression in a progressive manner. It works on the principal that partitioning of spatial orientation trees in such manner that insignificant and significant coefficients (with respect to some predefined threshold) are kept in the different sets. The output bit stream generated by SPIHT algorithm consists of large number of seriate ‘000’ with probability nearly equal to ¼, and require further compression. This is achieve by the cascading Entropy encoding schemes with SPIHT algorithm. The aim of this research is comparison between cascading of SPIHT algorithm with two entropy encoding schemes (Arithmetic coding and Huffman coding). For the cascading, the output bit stream of SPIHT is divided in sets of three bits to form 23=8 symbols. These symbols are given to entropy encoding schemes (Arithmetic and Huffman). This cascading save lots of bits during transmission of data. Due to which it decreases the transmission time and requires less space on hard disk. This research concludes that the concatenation of SPIHT and Arithmetic coding blocks provides better Bits saving capability as compared to SPIHT and Huffman coding concatenation. On the other hand, SPIHT combined with Huffman performs well in terms of algorithm efficiency, implementation and execution time by preserving PSNR.