PROJECT TITLE :

Color Image Coding Based On Linear Combination Of Adaptive Colorspaces - 2017

ABSTRACT:

This paper improves a colorization-primarily based image coding using Image Segmentation and adaptive colorspaces. Recently, various approaches for color image coding based mostly on colorization have been presented. These strategies utilize a YCbCr colorspace and transfer the luminance component by a standard compression methodology. Then, the chrominance components are approximated from the luminance element employing a colorization methodology. Our technique segments a luminance component into little segments called superpixels, and reconstructs the chrominance of each superpixel as a linear combination of its luminance. For chrominance parts, we tend to introduce an adaptive color area transform optimized for liner combination. This is as a result of YCbCr colorspace cannot continuously become a good approximation of the chrominance. In addition, we have a tendency to introduce an automatic selection for the amount of superpixel segments from a given quality issue. The simulation with normal pictures shows that our methodology performs better result than conventional coding schemes.