Cervical cancer is one of the leading causes of cancer-related deaths in women worldwide. Early detection and diagnosis play a crucial role in improving treatment outcomes. This project aims to develop a deep learning model for detecting cervical cancer from medical images, classifying them into two categories: cervical negative (healthy) and cervical positive (cancerous). Using Convolutional Neural Networks (CNN) and MobileNet, this study focuses on leveraging image classification techniques to automate the identification of cancerous cells in cervical images. The dataset used for training consists of labeled images, and the models are trained and tested to ensure high classification accuracy. The CNN model is designed to extract relevant features from the images, while MobileNet, a lightweight architecture, ensures efficiency and suitability for devices with limited computational power. The goal is to provide a tool that can assist healthcare professionals in diagnosing cervical cancer at an early stage, reducing the time required for diagnosis and enabling timely treatment. Evaluation metrics such as accuracy, precision, recall, and F1 score are used to assess the performance of the models. The project demonstrates the potential of deep learning in medical image analysis and its applications in cancer detection.

Keywords: cervical cancer, deep learning, image classification, convolutional neural networks, MobileNet, medical images, detection, early diagnosis, machine learning, healthcare.