Optimization of vector quantization in Hybrid Vector Scalar Quantization (HVSQ)
The advancement in fields like multimedia, medical imagery and emergence of high resolution digital cameras has necessitated the acquisition, storage and transmission of high resolution digital images. Storage and transmission of such images are expensive in terms of bytes and bandwidth. There is a need for compressing these images to curtail the storage and transmission budget. A bewildering variety of image compression schemes featuring new concepts and techniques have been proposed to yield superior compression quality.
Hybrid Vector Scalar Quantization (HVSQ) is one such novel compression scheme used for compressing high resolution cervigram image archives of the US National Library of Medicine. It is a lossy compression scheme comprising of two of the well known quantization techniques namely Vector and Scalar Quantization in the wavelet domain. This thesis focuses on implementation and optimization of the Vector Quantization module of HVSQ to yield higher image quality in terms of Peak Signal to Noise Ratio (PSNR) and lower encoding time. The thesis also focuses on evaluating the performance of Vector, Scalar and Hybrid Vector Scalar Quantization. The superior performance HVSQ is then verified by compressing a few high resolution natural images.