TY  - JOUR
T1  - Combined Approach on Cervical Cytology Image Segmentation
AU - Sivaprakasam, S. Anantha AU - Naganathan, E.R. 
JO  - International Journal of Soft Computing
VL  - 10
IS  - 2
SP  - 163
EP  - 168
PY  - 2015
DA  - 2001/08/19
SN  - 1816-9503
DO  - ijscomp.2015.163.168
UR  - https://makhillpublications.co/view-article.php?doi=ijscomp.2015.163.168
KW  - Cytological image segmentation
KW  -cluster
KW  -region growing
KW  -hit ratio region
KW  -k-means
AB  - Medical image segmentation is a complex and challenging task due to the inherent nature of the image. A number of different segmentation algorithms for these images have been developed. The single arithmetic of colour image segmentation has some deficiencies and defects, so we can use combine different algorithms according to the actual situation for segmentation. Here, researchers propose a new and novel approach called colour image segmentation based on JSEG and Robust k-means algorithms applied on cytological image. This algorithm segments the cytological image properly without manual parameter adjustment for each image and simplifies texture and colour. In this, the segmentation consists of two major stages. In the first stage, the cervical colour image is quantized to represent several representing classes which can be used to differentiate regions in the image. In the second stage, hit rate regions with similar Colour Regions Merging algorithm, i.e., Robust k-means algorithm is applied. Experiment results show that this method provides good segmentation results on different cytological images.
ER  -