Automatic system for counting cells with elliptical shape

TL;DR

This paper introduces an automated approach for counting elliptical cells in images, combining k-means segmentation with contour analysis to accurately detect and split touching cells, outperforming manual methods.

Contribution

The novel method integrates k-means segmentation with contour-based splitting to improve accuracy in counting elliptical cells.

Findings

High detection accuracy compared to manual counting

Effective splitting of touching cells

Robust performance across different image conditions

Abstract

This paper presents a new method for automatic quantification of ellipse-like cells in images, an important and challenging problem that has been studied by the computer vision community. The proposed method can be described by two main steps. Initially, image segmentation based on the k-means algorithm is performed to separate different types of cells from the background. Then, a robust and efficient strategy is performed on the blob contour for touching cells splitting. Due to the contour processing, the method achieves excellent results of detection compared to manual detection performed by specialists.