An improvement on the Euler number computing algorithm used in MATLAB

Abstract

Computation of the Euler number of a binary image is often necessary in image matching, image database retrieval, image analysis, pattern recognition, and computer vision. This paper proposes an improvement on the Euler number computing algorithm used in the famous image processing tool MATLAB. By use of the information obtained during processing the previous pixel, the number of times of checking the neighbor pixels for processing a pixel decrease from 4 to 2. Our method is very simple in principle, and easily implemented. The experimental results demonstrated that our method outperforms significantly conventional Euler number computing algorithms.