Image segmentation with improved watershed algorithm and its FPGA implementation

This paper is concerned with image segmentation based on watershed transform techniques. It introduces a fast, improved watershed algorithm which processes 3×3 pixels in one process. Simulation results show that the improved watershed algorithm has a better throughput and yields comparable results to those of Vincent´s immersion watershed algorithm. The improved algorithm is modified and formulated such that it is amenable to computing architecture implementation. An FPGA-based architecture that is developed to implement the proposed algorithm is presented. This architecture improves the applicability of this algorithm in real time applications. A description of the improved watershed algorithm, its extension to N×N pixels, and the architecture implementation is presented