Cervical Precancerous Classification System based on Texture Features and Support Vector Machine
Abstract
Cervical cancer is one of the female reproductive health diseases being a significant issue globally because of the large number of new cases and deaths, particularly among women in developing countries. Cervical cancer can be avoided if detected early. The Pap smear screening procedure is used in industrialized nations to detect cervical cancer early. However, limited human resources, a significant time commitment, high prices, and insufficient infrastructure make it less successful in developing countries. With three types of cervical cell images: Normal, Low-grade Squamous Intraepithelial Lesion (LSIL), and High-grade Squamous Intraepithelial Lesion (HSIL), this study offers a classification system for cervical cell images using an image processing technique called Gray Level Co-occurrence Matrix (GLCM) and a Support Vector Machine (SVM) classification method (HSIL). With HSIL class as positive data and LSIL and Normal as negative data, the classification system used three SVM models: Cubic, Quadratic, and Fine Gaussian. SVM classification accuracy was 97.5 percent for 3.54s using the GLCM feature extraction approach.