Real-time K-Means Clustering for Color Images on Reconfigurable Hardware

Abstract

K-means clustering is a very popular clustering technique, which is used in numerous applications. However, clustering is a time consuming task, particularly for large dataset, and large number of clusters. In this paper, we show that real-time k-means clustering can be realized for large size color images (24-bit full color RGB) and large number of clusters (up to 256) using an off-the-shelf FPGA (field programmable gate arrays) board. In our current implementation with one FPGA, the performance for 512 times 512 and 640 times 480 pixel images is more than 30fps, and 20-30 fps for 756 times 512 pixel images in average when dividing to 256 clusters