In this thesis, we investigate the potential of machine learning (ML) techniques to enhance the accuracy and efficiency of cervical cancer diagnostics. The work's goal was to develop a machine learning-based application that can classify cervical cell images with good accuracy, providing an accessible and automated alternative to manual inspection.We used publicly available dataset (SIPaKMeD) single cell images. We extract features from the single cell images using different techniques and then filter some feature using filter selection approach to enhance model accuracy. We use different machine learning techniques to evaluate which one work better with our data set and the SVM model gives us the highest accuracy and precision. The trained model then used to predict the image classes percentage, which show the accuracy and confidence of the model on the prediction.