Using microscopy technology to analysis human cells is an important method for pathological study, diagnostic etc. As a pioneering imaging technology, the microscopy has many advantages: reduced photo toxicity and photo bleaching as well as enhanced imaging penetration depth. There are many center location methods for cells microscopic image. However, location results of these methods cannot meet the requirements of precision analysis. In this paper, We present a novel algorithm to locate cell nucleus in microscopic image. Our method consists of the following components: Firstly, to improve robustness of the algorithm the initial segmented regions are obtained by using Otsu method. Secondly, in order to improve accuracy of location results, the random sample consensus (RANSAC) method is used to eliminate exterior point after find the minimum bounding circle of cells. Finally, an ellipse fitting method is introduced to get the location of cell nucleus. Experiments on challenging microscopic images show that the proposed algorithm performs favorably against several state-of-the-art methods.
[1]
W. Gander,et al.
Least-squares fitting of circles and ellipses
,
1994
.
[2]
Xing De-kui.
Algorithm of centre location of ellipse in optical measurement
,
2008
.
[3]
Yeung Sam Hung,et al.
A Hierarchical Approach for Fast and Robust Ellipse Extraction
,
2007,
ICIP.
[4]
Jianxin Chen,et al.
A New Center Location Algorithm Used in Cell Segmentation
,
2008,
2008 Congress on Image and Signal Processing.
[5]
Shen Xiao-jun,et al.
Automatic Segmentation of Cell Image
,
2004
.
[6]
Yao Liu,et al.
Center location and segmentation of cell two-photon microscopic images based on random sample consensus
,
2013,
2013 6th International Congress on Image and Signal Processing (CISP).
[7]
Nicolas Pérez de la Blanca,et al.
Applying deformable templates for cell image segmentation
,
2000,
Pattern Recognit..