3D-2D silhouette-based image registration for comparative radiography-based forensic identification. (November 2018)

• Record Type: Journal Article
• Authors: Gómez, Oscar; Ibáñez, Oscar; Valsecchi, Andrea; Cordón, Oscar; Kahana, Tzipi
• Is Part Of: Pattern recognition. Volume 83(2018:Nov.)
• Page Start: 469
• Page End: 480
• Publication Date: 2018-11
• Subjects: Forensic identification -- Comparative radiography -- 3D-2D image registration -- Computer vision -- Evolutionary computation; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2018.06.011
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: 2D radiographs and 3D scans of any bone or cavity are automatically superimposed. The method considers up to 7 degrees of freedom and occlusions. The method has been validated with synthetic and real data. The mean overlapping error on synthetic cases is lower than the 2% of the pixels. Real frontal sinuses cases are correctly identified in the 58% of the experiments. Abstract: Comparative radiography is a forensic identification technique traditionally involving the manual comparison of ante-mortem and post-mortem radiographs, thus being time consuming and error prone. The main objective is to propose and validate a computer-aided comparative radiography paradigm based on the 3D bone scan-2D radiograph superimposition process of any bone or cavity. The proposal follows an image registration methodology to automatically search for the ante-mortem radiograph acquisition parameters from the forensic object's silhouette considering occlusions. The underlying optimization problem is complex since a close initialization cannot be assumed and the image intensities are not reliable or not captured. Several experiments were performed to validate the method. First, we study its accuracy and robustness with synthetic images of clavicles, patellae and frontal sinuses. Second, we study how optimization performance and both variability and differences in the segmentation performed by human operators affect the identification using synthetic and real images of frontal sinuses.