Peer group filtering and perceptual color image quantization

Abstract

In the first part of this work, peer group filtering (PGF), a nonlinear algorithm for image smoothing and impulse noise removal in color images is presented. The algorithm replaces each image pixel with the weighted average of its peer group members, which are classified based on the color similarity of the neighboring pixels. Results show that it effectively removes the noise and smooths the color images without blurring edges and details. In the second part of the work, PGF is used as a preprocessing step for color quantization. Local statistics obtained after PGF are used as weights in the quantization to suppress color clusters in detailed regions, since human perception is less sensitive to the differences in these areas. As a result, very coarse quantization can be obtained while preserving the color information in the original images. This can be useful in color image segmentation and color image retrieval applications.