The API processes an occlusal view image, applying image segmentation techniques such as deep learning-based models (e.g., U-Net) to separate each tooth and relevant structures from the background. It generates masks or outlines for each segmented tooth, labeling them appropriately (e.g., by tooth number). The segmented output enables precise analysis of tooth positions, arch symmetry, and occlusal relationships for use in digital dental charts or automated evaluations.