Classify a path on tire by using Logistic Regression and Support Vector Machine (SVM)Based on VGG-16, VGG-19, and INCEPTION V3 Modes

This study focuses on the classification of tire tread patterns using machine learning and deep learning approaches, emphasizing Logistic Regression (LR) and Support Vector Machine (SVM) combined with feature extraction methods like Inception V3, VGG-16, and VGG-19. Results indicate that Inception V3 outperformed other feature extraction methods, yielding the highest classification accuracy (CA) of 93.2% when used with SVM. SVM demonstrated superior robustness and adaptability, especially in handling complex data, as evidenced by its high AUC values (up to 0.987) across multiple configurations. Logistic Regression, while slightly less robust, performed consistently well with simpler features, achieving stable metrics with VGG-16 (AUC: 0.976, CA: 90.7%). These findings highlight the importance of selecting appropriate feature extraction and classification combinations to optimize performance. The study recommends using Inception V3 with SVM for high-accuracy applications and Logistic Regression for scenarios prioritizing computational efficiency. These insights contribute to developing adaptive and efficient tire classification systems suitable for diverse road and environmental conditions.