This experiment focuses on employing machine learning techniques to create an automated system for classifying palm leaf manuscripts into three distinct categories based on their degradation levels: good, bad, and medium. The study collects a wide range of palm leaf samples at different degradation levels. Using advanced machine learning algorithms and an efficient feature extraction method, a model is created that accurately classifies palm leaves by level of degradation. The research incorporates Gabor feature extraction and statistical classifiers to train the extracted features. The classifiers used are k-Nearest Neighbor (k-NN), Support Vector Machine (SVM), Multi-Layer Perceptron (MLP), Logistic Regression (LR), Random Forest (RF), Decision Tree (DT), Naive Bayes (NB), XG Boost (XGB), and Ada Boost (AB). After employing SMOTE, normalization, and feature selection, RF obtained the highest mean accuracy of 87.25% and a standard deviation of 0.08 in comparison with the other classifiers.