Automatic Classification of Cervical Cancer Using Support Vector Machine

R. Rajpriya and Dr.M.S. Saravanan

Cervical cancer has become one of the major causes of cancer death among women worldwide. Accurate classification of Pap smear images becomes the challenging task in medical image processing. This paper proposed feature selection and classification of Pap smear slide images and present an automated method for classifying cancerous and non-cancerous cells are present in the original image. There are four stages for classifying the cervical cancer for getting better results. Feature enhancement processes used for reduce noise and segment the regions by filtering and threshold method. Feature extraction method is to extract the features by Fuzzy logic, threshold, and Fuzzy C-means clustering. Feature selection and classification method is to select the optimal features for classifying the normal and abnormal cells by support vector machine. There is 228 slides of different 7 classes are classifying the selected optimal features. Based on optimal features, the support vector machine method classifies the abnormal and normal cells. Support vector machine provide accuracy results for classification of cancerous and non-cancerous cells with 93.0% for 7-class problem and 99.1% for 2-class problem.

Volume 11 | 04-Special Issue

Pages: 744-752