Teeth feature extraction and matching for human identification using morphological skeleton transform

The morphological skeleton transform (MST) is a leading morphological shape representation scheme. In the MST, a given shape is represented as the union of all the maximal disks contained in the shape. The concept of external skeleton points and external maximal disks has been used for shape description and characterization purposes. Dental biometrics has emerged as vital biometric information of human being due to its stability, invariant nature and uniqueness. The proposed work using SIFT algorithm for human identification and we work with canny detection algorithm for the analysis and comparison with the proposed SIFT algorithm. This system has six main stages as pre-processing, feature extraction, feature matching and finalized recognized person. Then we go for canny edge detection and comparison with database images. At the final step we compare SIFT and canny algorithm detected values using the Euclidian distance between the query image and database. Here the Euclidian distance between detected points and matching points determines the accuracy of the algorithm for human identification. The system is work for both types of dental images i.e. photograph and radiograph in which two different datasets are required. The required database contains 50 images of dental photographs and 50 images of dental radiographs so experimentation has done on total 100 images and that are taken from dental clinic* and internet. While comparing proposed SIFT algorithm with canny detection algorithm we can conclude that our SIFT algorithm can provide more accurate result.