Performance analysis of various techniques applied in human identification using dental X-rays.

Area of Science:

• Forensic Science
• Computer Science
• Biomedical Imaging

Background:

• Forensic dentistry relies on dental records, primarily radiographs, for personal identification.
• Manual comparison of ante mortem and postmortem dental records is time-consuming and labor-intensive.
• Automating the identification process can significantly improve efficiency and accuracy in forensic investigations.

Purpose of the Study:

• To develop and evaluate an automated system for identifying individuals using ante mortem and postmortem dental radiographs.
• To leverage image processing and pattern recognition techniques for accurate dental identification.
• To compare the effectiveness of different contour extraction methods in this automated identification process.

Main Methods:

• The proposed approach integrates morphological contour detection, Gaussian filtering, and a semi-automatic contour extraction method.
• The algorithm involves three key stages: radiograph segmentation, pixel classification, and contour matching.
• Tooth contours are extracted from postmortem radiographs and compared against a database of ante mortem radiographs.

Main Results:

• A hit rate of 0.7 was achieved using morphological contour detectors for identification.
• The performance of morphological contour detectors was found to be comparable to other evaluated methods.
• The automated system demonstrates potential for accurate and efficient forensic dental identification.

Conclusions:

• The developed automated system shows promise for enhancing the accuracy and speed of personal identification in forensic dentistry.
• Morphological contour detection is a viable feature for matching ante mortem and postmortem dental radiographs.
• Further research can refine these techniques for broader application in forensic identification.