A cooperative coevolutionary approach dealing with the skull–face overlay uncertainty in forensic identification by craniofacial superimposition

Abstract

Craniofacial superimposition is a forensic process where photographs or video shots of a missing person are compared with the skull that is found. By projecting both photographs on top of each other (or, even better, matching a scanned three-dimensional skull model against the face photo/video shot), the forensic anthropologist can try to establish whether that is the same person. The whole process is influenced by inherent uncertainty mainly because two objects of different nature (a skull and a face) are involved. In previous work, we categorized the different sources of uncertainty and introduced the use of imprecise landmarks to tackle most of them. In this paper, we propose a novel approach, a cooperative coevolutionary algorithm, to deal with the use of imprecise cephalometric landmarks in the skull-face overlay process, the main task in craniofacial superimposition. Following this approach we are able to look for both the best projection parameters and the best landmark locations at the same time. Coevolutionary skull-face overlay results are compared with our previous fuzzy-evolutionary automatic method. Six skullface overlay problem instances corresponding to three realworld cases solved by the Physical Anthropology Lab at the University of Granada (Spain) are considered. Promising results have been achieved, dramatically reducing the run time while improving the accuracy and robustness.

Modeling the consistency between the bony and facial chin outline in craniofacial superimposition

“…In fact, several successful applications of these techniques in forensic anthropology have been developed so far, such as age estimation [24,25], skull 3D modeling [26], facial soft thickness prediction [27], facial identification [28], and skull 3D model simplification [29]. Within CFS, Evolutionary Algorithms (EAs) and fuzzy sets have being used to tackle SFO in an automatic way using EAs and fuzzy sets [12,11,13,14]. The following section 2.2 summarizes the latter SFO system since the SFO images analyzed in this work have been obtained using it.…”

“…In our automatic SFO procedure [11,12,13,14], this approach is guided by a set of cranial and facial landmarks previously located by a forensic expert. An EA iteratively searches for the best geometric transformation, corresponding to 12 real-coded parameters in our model [11].…”

“…The works developed by authors such as [10,11,12,13,14] serve as examples of how computer algorithms can automate SFO and accommodate the uncertainty/fuzziness of some facial landmarks [15] and of the soft tissues [16,17]. These methods represent a clear step forward since they have managed to reduce time and subjectivity inherent to manual approaches.…”

Vibration-Based Damage Detection in Beams by Cooperative Coevolutionary Genetic Algorithm

“…Many researches effectively applied the CCGA to the particular optimization problems [27][28][29][30][31]. In the CCGA, a population contains a number of species or subpopulations.…”

Computer-aided craniofacial superimposition using a quasi-Newton iterative closest point approach

“…The first type is a set of computer assisted processes that use commercial software such as PHOTOSHOP, CORAL DRAW or 3D STUDIO MAX to complete the skull-face overlay manually in digital form 1,2 . The second type is a set of computational intelligence techniques such as genetic algorithms (GA) [3][4][5] , multimodal GA 6 , covariance matrix adaptation evolution strategy 7 , cooperative co-evolutionary approach 8 , and realcoded GA 9,10 that are used to automate the overlay process. These intelligent techniques aid to mitigate the uncertainty elements such as fuzzy landmarks and thickness of soft tissues that are encountered during the process of mapping the 3D-skull model onto the 2D face.…”