Directional Connected Components Algorithm Based on Gradient Information

Abstract

This paper presents a directional connected components algorithm that overcomes the problem of overlapping components by gradient information. The proposed algorithm replaces the binary matrix with the directional matrix that contains the gradient information. The directional matrix contains both the gradient magnitude and angle and provides the merge decisions of neighboring pixels for solving the problem of overlapping edges. The proposed algorithm improves the performance of the connected components algorithm in the classification of features and candidates using edge information. Experimental results demonstrate that the proposed algorithm can resolve the problem of overlapping components, and prevent false connections between components and background under various circumstances.