One of the most prevalent cancers in the world and one of the most harmful to human life is cervical cancer (CC). This procedure was created to increase the diagnostic accuracy of CC in such dataset pictures in order to better detect and forecast illness. Therefore, we attempted to demonstrate a convolution neural network-based classification framework for CC that is intelligent and effective and has a comparatively basic architecture in comparison to others. Additionally, we offered a simple and useful technique for CC classification from cytological pictures using effective feature extraction or accurate cell image segmentation effort. The outcomes of automatic cell detection are contrasted with those of other cutting-edge cell detection methods as well as hand annotation of the underlying data. Many of the procedures for cell detection and categorization are still being worked on. This procedure's primary goals are to pinpoint the cell area and increase segmentation precision. With an F1 score of 0.96, the suggested approach has the highest cell detection accuracy.