A near-lossless image compression algorithm using vector quantization
Emil Marin Popa, Alina Pitic, Antoniu Gabriel Pitic · 2006
Abstract: Lossy image compression methods are based on error measuring at entire image level only. In some areas there is an obvious need for getting an upper bound for the error at pixel level. In the paper we propose a near-lossless compression algorithm based on DPCM simple scheme, followed by a vector quantization. The exit will have a non uniform distribution, so it will be further compressed using an entropy based method. Experimental results obtained and presented in the paper prove that the vector quantization method gives us better results than the scalar quantization and the classic LBG algorithm, in the near-lossless context.