Automated ROI detection for histological image using fuzzy c-means and K-means algorithm
Rupesh Mandal, Mousumi Gupta, Chinmoy Kar · 2016
This paper deals with the automatic detection of the region of interest (ROI) in Histopathologoical images by means of advanced segmentation techniques. The clustering techniques like fuzzy C-means (FCM) and K-means algorithms for the color image segmentation are implemented on a dataset which consisted of skin images. Euclidian distance is used as a distance metric in both the algorithms. The resultant segmented regions which were obtained from these two techniques were compared and found to be of similar features. The entire experiment is implemented in the L*a*b* color space and a concise discussion regarding the color space conversion is carried out. This paper presents a detailed discussion on the various steps of the two clustering techniques and its requirements and shows how the result obtained from them could be used for diagnosis purpose by the human experts in medical treatment.