Automated Dental Recognition in MSCT Images for Human Identification

An automated dental identification system (ADIS) for human identification in forensic dentistry requires automatic recognition of teeth in dental images. In this paper, we propose a multi-stage technique to classify teeth in multislice CT (MSCT) images. The proposed algorithm consists of the following three stages: segmentation, feature extraction and classification. We segmented the teeth based on our previous experiences. In the feature extraction stage, we introduced a multi-resolution method using wavelet-Fourier descriptor (WFD). Finally, we utilized WFD coefficients as feature vectors for classification in the third stage. Teeth classification is performed by a conventional supervised classifier for teeth identification. Experimental results reveal the effectiveness of the proposed method.