A Novel Low Space Image Storing and Reconstruction Method by K-Means Clustering Algorithm

This paper presents a lossy image compression technique that proposes a novel approach for storing RGB color images which save 33% memory space compared to memory space requirement of conventional method of storing RGB images. The proposed method, first finds the most and least dominating color components among three Red, Green and Blue color channels for each RGB image and then for each pixel of the image, it finds the absolute difference between the most and least dominating color values and expresses the difference as a fraction of the most dominating color value of the pixel. All the fraction values are clustered into sixteen groups using K-Means Clustering algorithm and all centroids are stored as Header. The less significant two bits of each the other two color channels are modified according to the cluster information. These two modified color channels along with one Header are stored for each image. Thus 33% of the memory space requirement to store the original image could be saved using the proposed method. At the time of reconstruction of the image, according to the cluster information third color component is retrieved with the help of the header. The experimental result shows that the reconstructed images retain around 98.5±0.5% of the original image information. The method has been implemented using Matlab 7 and tested on one standard FRAV2D database and hundred natural images and this method could be applied to compress any RGB image.