Cell counting plays an important role in biomedical research. There are always some phenomena such as indistinct intervals and target adhesion in cell images, which leads to poor segmentation effect and therefore inaccurate counting. In view of this situation, based on image binarization technology, this paper proposed a quick cell count method combining mathematical morphology and connected component labeling in which the cell images can be grayed, USM sharpened,binarized, morphologically processed, and connected component labeled, and ultimately the number of cells could be calculated. The experimental results showed that this method can effectively segment the complete the segmentation of both sparse cell images and intensive cell images, and the counting error is within 5%.
Authors: Junwen Si (Dalian Polytechnic University), Chuanchuan Zhu (Dalian Polytechnic University), Xufen Xie (Dalian Polytechnic University),
Hide Authors & Abstract