Cell Cluster Image Segmentation on Form Analysis

Abstract

In this paper, a segmentation algorithm based on form information is proposed for separation of touching and overlapping cells. The method integrating morphological smoothing with holes filling is employed in a pre-processing stage. Then the overlapping cell clusters are identified through a polygon approximation. Later the separation is implemented, which consists of the detecting concave points on the contours and determining the separation lines. The algorithm can split complicated large cell clusters. In addition, this algorithm can be adopted for other applications, where separation between touching and overlapping particles is needed.