No abstract

Around the world, millions of women are diagnosed with cervical cancer each year. Early detection is very important to produce a better overall quality of life for those diagnosed with the disease and reduce the burden on the healthcare system. In recent years, the field of machine learning (ML) has been developing methods that can improve the accuracy of detecting cervical cancer. This paper presents a new approach to this problem by using a combination of image segmentation and feature extraction techniques. The proposed approach is divided into three phases. The first stage involves image segmentation, which is performed to extract the regions of interest from the input image. The second stage is comprised of extracting the features from the ROI with the help of the Histogram and Hu Moments techniques. The techniques used in this approach, namely the Hu Moments and Histogram techniques, respectively, can capture the shape information in the ROI. In the third stage of the project, we use a hybrid approach to classify the image. The proposed model is composed of several base classifiers, which are trained on varying subsets of the features that were extracted. These resulting classifiers then make a classification decision. We tested the proposed model against a large dataset of images for cervical cancer. The results of the experiments revealed that it performed better than the existing methods in detecting the disease. It was able to achieve an accuracy of 96.5%, an F1 score of 96.9%, and a recall of 96.7%. The proposed model was successful in accomplishing a remarkable accuracy of 96.5%, making it an ideal candidate for use in the detection of cervical cancer. It was also able to perform feature extraction using the Histogram techniques and image segmentation. The proposed method could help medical professionals improve the diagnosis and reduce the burden of this disease on women worldwide.