Early detection of cervical cancer is critical for improving patient outcomes, and accurate classification of Pap smear images supports clinical decision-making. This study aimed to improve cervical cancer diagnosis by classifying Pap smear images using texture features. A dataset of 250 images across five classes underwent preprocessing including grayscale conversion and noise removal. Texture features such as contrast, dissimilarity, homogeneity, energy, correlation, and Angular Second Moment (ASM) were extracted using the Gray-Level Co-occurrence Matrix (GLCM). These features were then used to train and evaluate machine learning algorithms: Decision Tree (DT), Random Forest (RF), Gradient Boosting (GB), and Neural Networks (NN). The Decision Tree model achieved the highest accuracy of 95%, outperforming Neural Networks which reached 74%. Ensemble methods like RF and GB showed robust performance across classes. These results demonstrate the effectiveness of GLCM-based feature extraction combined with Decision Tree classification for accurate and reliable Pap smear image analysis. This approach offers valuable insights for enhancing clinical decision support in cervical cancer diagnosis.