Automatic Dental Superimposition of 3D Intraorals and 2D Photographs for Human Identification
Summary: arXiv:2604.05877v1 Announce Type: cross
Abstract
Dental comparison is considered a primary identification method, at the level of fingerprints and DNA profiling. One crucial but time-consuming step of this method is the morphological comparison. One of the main challenges to apply this method is the lack of ante-mortem medical records, especially in scenarios such as migrant death at the border and/or in countries where there is no universal healthcare. The availability of photos on social media where teeth are visible has led many odontologists to consider morphological comparison using them. However, state-of-the-art proposals have significant limitations, including the lack of proper modeling of perspective distortion and the absence of objective approaches that quantify morphological differences.
Proposed Methodology
Our proposal involves a 3D (post-mortem scan) – 2D (ante-mortem photos) approach. Using computer vision and optimization techniques, we replicate the ante-mortem image with the 3D model to perform the morphological comparison. Two automatic approaches have been developed:
- Paired Landmarks: This method utilizes paired landmarks on both the 3D model and the 2D photograph to facilitate accurate alignment and comparison.
- Segmentation of the Teeth Region: This approach estimates camera parameters by segmenting the region of the teeth in the 2D image, which allows for a more refined analysis of morphological characteristics.
Results
Both methods have proven to be capable of obtaining very promising results over 20,164 cross comparisons from 142 samples, yielding mean ranking values of 1.6 and 1.5, respectively. These results clearly outperform the filtering capabilities of traditional automatic dental chart comparison approaches.
Advantages of the Proposed Methods
The main advantages of our proposed methodologies include:
- Automatic Processing: The methodologies are fully automated, significantly reducing the time required for morphological comparison.
- Objective Measurement: The approaches provide an objective and quantitative score of the morphological correspondence, allowing for clearer interpretations.
- Visual Analysis: The superimposed images can be easily visualized, making the analysis more intuitive for forensic experts.
Conclusion
In summary, the integration of 3D intraoral scans with 2D photographs represents a significant advancement in the field of dental identification. This innovative approach addresses the critical challenges posed by the lack of ante-mortem records and provides a robust, efficient, and objective method for morphological comparison. As forensic science continues to evolve, methodologies like these promise to enhance the accuracy and reliability of human identification efforts, especially in challenging scenarios where traditional methods fall short.