PCA image coding with iterative clustering

Abstract

Cluster analysis divides the data into groups of individuals that are homogeneous and separated from other groups. In consideration of the homogeneity, principal component analysis is usually used to reduce the redundancy of storages inside each cluster through the projection of data based on the principal components. Such data reduction is applied in this paper to images to achieve image compression. Moreover, genetic algorithm is employed in this study to determine the optimal number of components that preserve most of the information of the original data. Based on this mechanism, we develop an iterative clustering method for image coding. The proposed method effectively removes the coding redundancy and increases the number of principal components in some clusters in order to improve the reconstructed effect of certain clusters with complex structures. Consequently, the retrieved image has high quality and good visual effect.