Biological Cell Image Segmentation Using Novel Hybrid Morphology-Based Method

In this paper, we propose a novel hybrid method for the segmentation and automatic counting of biological cell image. The method is based on techniques of morphology, thresholding and watershed. It performs well in low contrast image where gradient-based method may fail. Experimental results on practical cell images are shown in the paper with the emphasis on the comparisons between the novel hybrid method and the gradient-based methods: Sobel [1], Canny [2] and GAC [3] of level-set.

[1]  Rafael C. González,et al.  Digital image processing using MATLAB , 2006 .

[2]  Gunilla Borgefors,et al.  Distance transformations in digital images , 1986, Comput. Vis. Graph. Image Process..

[3]  Luc Vincent,et al.  Morphological grayscale reconstruction in image analysis: applications and efficient algorithms , 1993, IEEE Trans. Image Process..

[4]  Guillermo Sapiro,et al.  Geodesic Active Contours , 1995, International Journal of Computer Vision.

[5]  Justin W.L. Wan,et al.  A spectral k-means approach to bright-field cell image segmentation , 2010, 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology.

[6]  Pierre Soille,et al.  Morphological Image Analysis: Principles and Applications , 2003 .

[7]  N. Otsu.  A threshold selection method from gray level histograms , 1979 .

[8]  Xiaobo Zhou,et al.  High content cellular imaging for drug development , 2006 .

[9]  J. Canny.  A Computational Approach to Edge Detection , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.