Optimal transform in perceptually uniform color space and its application in image retrieval

To find an appropriate color transform is necessary and helpful for the applications of color images to extract color features or to reduce the data redundancy. In this paper, we proposed a new scheme to find color transforms close to the optimal transform and agree with human vision system for comparison. We first apply the perceptually uniform color space transform to all the hundreds color test images to convert RGB values into uniform CIE LAB components and then use principal component analysis (PCA) in the uniform space to find the image-dependent optimal color transforms (KLT). In our experiments, we have obtained a new color space: an approximate but fixed transform in CIE LAB space, namely LAR space, which is just the LAB rotated and has an elegant and simple form. The proposed LAR transform performs better than RGB, YCbCr, YUV, HSV and LAB in color-based image retrieval.