Multilevel Compression Scheme using Vector Quantization for Image Compression

Abstract

Abstract-In this paper, we have proposed a multi level compression scheme, in which the initial codebook and the Index Map that are generated using the normal Vector Quantization are compressed in three levels. The Minimum Mean Square method that is adopted in Block Truncation Coding is used to compress the codebook in first level with some improvements. The interpolative method is used to perform second level of compression to the codebook. Finally the Search Order Coding method is used to compress the Index Map without loss of image data. The experimental results show that there is a significant improvement in bit reduction without loosing much of image data.