Traditional Chinese Medicine (TCM) extensively uses tongue diagnosis as a key technique to evaluate internal health conditions. Recent advances in artificial intelligence and image processing have enabled the automation and enhancement of such diagnostic methods. This paper presents the development of an intelligent diagnostic system based on tongue image analysis designed to assist TCM practitioners in health assessment. The system incorporates advanced image preprocessing stepsnoise reduction, color normalization, and segmentation to ensure input quality. Visual features including color, texture, and shape are extracted and refined through feature selection. Machine learning models such as Convolutional Neural Networks (CNN), Random Forest (RF), and Support Vector Machines (SVM) were trained and optimized via grid search hyperparameter tuning. The models classify tongue images into TCM diagnostic categories, with performance evaluated using accuracy, precision, recall, F1-score, and Matthews Correlation Coefficient (MCC). Experimental results indicate that the CNN model outperforms others, achieving 96.7% accuracy, 95.2% precision, 94.8% recall, 95.0% F1-score, and 0.92 MCC. This study demonstrates the promising integration of TCM knowledge with intelligent systems, contributing to more consistent, accessible, and efficient health diagnostics.