Locally Linear Embedding Clustering Algorithm for Natural Imagery

TL;DR

This paper introduces a new clustering algorithm that combines Locally Linear Embedding and vector quantization to segment and reduce color information in natural images while preserving key visual features.

Contribution

A novel topologically driven clustering method that integrates LLE with vector quantization for effective image color segmentation and resolution reduction.

Findings

Significant reduction in color resolution without losing visual features

Effective segmentation of color regions in natural imagery

Combines LLE with vector quantization for improved clustering

Abstract

The ability to characterize the color content of natural imagery is an important application of image processing. The pixel by pixel coloring of images may be viewed naturally as points in color space, and the inherent structure and distribution of these points affords a quantization, through clustering, of the color information in the image. In this paper, we present a novel topologically driven clustering algorithm that permits segmentation of the color features in a digital image. The algorithm blends Locally Linear Embedding (LLE) and vector quantization by mapping color information to a lower dimensional space, identifying distinct color regions, and classifying pixels together based on both a proximity measure and color content. It is observed that these techniques permit a significant reduction in color resolution while maintaining the visually important features of images.