Adaptive vector quantization technique for retinal image compression

This paper presents a new image compression technique for the coding of retinal images. Retinal images are used to detect diseases like diabetes or hypertension. In this work, the contourlet transform of the retinal image is taken first. The coefficients of the contourlet transform are quantized using adaptive multistage vector quantization scheme. The number of code vectors in the adaptive vector quantization scheme depends on the dynamic range of the input image. The result of the proposed scheme is compared with wavelet based adaptive multistage vector quantization. The experimental results show that contourlet based adaptive vector quantization scheme gives better reconstruction when compared to wavelet based technique.