Journal of Computer Applications (JCA) ISSN: 0974-1925, Volume VI, Issue 1, 2013 15 Abstract - In this paper, a fully automated lesion detection method based on color histogram is proposed to help the adept to make a more robust diagnosis. In the proposed method, a preprocessing is applied to remove the irrelevant information and specular reflection from the colposcopy cervical images before feature extraction. Then the color histogram features are extracted and the features are used as an input to KNN, NaiveBayes, and SVM classifier to detect the Aceto White Region (AWR). Segmentation results are evaluated on 240 images of colposcopy and accuracy of the proposed system is over 85%. Index Terms – colposcopy, color histogram, cervical cancer, aceto white region. I. INTRODUCTION Cervical cancer is one of the most common cancers among women. Cervical cancer kills more than 288,000 women each year worldwide and disproportionately affects the poorest, most vulnerable women. At least 80 percent of cervical cancer deaths occur in developing countries1. Cancer of the cervix is primarily caused by HumanPapilloma Virus (HPV) infection. In developing countries, like India HPV infection is high2. Cancer refers to a class of diseases in which a cell or a group of cells divide and replicate irrepressible, intrude into adjacent cells and tissues (invasion) and ultimately spread to other parts of the body than the location at which they arose (metastasis) (National Cancer Institute 2009). In cervical cancer, (cancer of the uterine cervix), cancer develops in the tissues of the cervix, which is a part of the female reproductive system. The cervix connects the upper body of the uterus to the vagina. The endocervix (the upper part which is close to the uterus) is covered by glandular cells, and the ectocervix (the lower part which is close to the vagina) is covered by squamous cells. The transformation zone refers to the place where these two regions of the cervix meet. There are several types of cervical cancer. These are classified on the basis of location of the cervix where cancer develops. Cancer that develops in the ectocervix is called squamous cell carcinoma, and around 80-90% of cervical cancer cases (more than 90% in India) are of this type2. Manuscript received 25/02/2013 P S Rama Praba, Research scholar ,Department of Electronics and Communication Engineering, Sathyabama University, Chennai, India, E-mail: pazramar@yahoo.co.in Dr H Ranganathan, Principal, Rajiv Gandhi College of Engineering, Chennai, India Cancer that develops in the endocervix is called adenocarcinoma. In addition, a small percentage of cervical cancer cases are mixed versions of the above two, and are called adenosquamous carcinomas or mixed carcinomas. There are also some very rare types of cervical cancer, such as small cell carcinoma, neuroendocrine carcinoma etc. (American Cancer Society). Here we are dealing with squamous cell carcinoma. Although cancer of the cervix can develop in women of all ages, it usually develops in women of age group 35-55 years. In India, the peak age for cervical cancer incidence is 45-54 years, which is similar to the rest of the world2. India has an excessively high burden of cervical cancer and it accounts for nearly one-third of global cervical cancer deaths3. Since early detection predicts better prognosis, one of the most effective ways of preventing and controlling cervical cancer is regular screening and early diagnosis. Despite the fact that more than 80% of cervical cancer cases are in developing countries, only 5% of women there have ever been screened for cervical abnormalities1, 3. To diagnosis the cervical cancer, two prevention programs are available nowadays. They are Papanicolaou (Pap) smear test and colposcopy. Even though cervical cancer prevention programs such as the Pap smear have been effective in reducing the incidence and mortality of cervical cancer in developed countries, developing countries often lack the sophisticate laboratory equipment, highly trained personnel and financial resources necessary to implement these programs4. Pap test can only screen for potential problems, not diagnose them. A Pap test is reported as normal (negative) when all the cells are of a healthy size and shape. An abnormal (positive) test is reported if any cells of different sizes or shapes are found. An abnormal Pap test does not mean the patient has cancer5. Without a cost effective cervical cancer screening solution, cervical cancer has remained a leading cause of cancer-related death among women in developing countries. To address this problem, alternative cost effective cervical cancer screening methods have been investigated. The consistent and accurate diagnoses provided by digital image analysis will allow less experienced physicians to provide a standard of care on par with expert colposcopist. Colposcopic images are characterized by color and texture. Thus, their automatic analysis is difficult. However, the diagnosis of experts about some much debated images is often different, because of the very high specialization Comparing Different Classifiers for Automatic Lesion Detection in Cervix Based On Colour Histogram P.S.Rama Praba a, *, Dr H.Ranganathan b,1