An experimental study on the applicability of evolutionary algorithms to craniofacial superimposition in forensic identification

Ibáñez, Óscar; Ballerini, Lucia; Cordón, Óscar; Santamaría, José

doi:10.1016/j.ins.2008.12.029

Cited by 58 publications

(57 citation statements)

References 46 publications

(53 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Following a 3D-2D IR approach we aim to properly align the 3D skull model and the 2D face photograph in a common coordinate frame. The required perspective transformation to be applied on the skull was modeled in [5] as a set of geometric operations involving twelve parameters/unknowns which are encoded in a real-coded vector to represent a superimposition solution.…”

Section: Skull-face Overlay In Craniofacial Superimpositionmentioning

confidence: 99%

“…S, T , and P are uniform scaling, translation, and perspective projection matrices, respectively. The interested reader is referred to [10] for a detailed description of the matrices in Equation 1 and their relation with the twelve unknowns of the problem, as well as to [5] for a deeper explanation.…”

Section: Skull-face Overlay In Craniofacial Superimpositionmentioning

confidence: 99%

“…This complex landscape leaded us to tackle the problem considering robust evolutionary algorithms (EAs) [11] to search for the optimal values of the twelve registration transformation parameters. In [5], CMA-ES [12] and different real-coded genetic algorithms [13] were applied, achieving very promising results in some problem instances.…”

Section: Skull-face Overlay In Craniofacial Superimpositionmentioning

confidence: 99%

“…As it is explained in [5], we have developed an automatic method that overlays a 3D model of the skull over a 2D photograph of the face of the missing person. With that aim, we studied and experimented with different evolutionary approaches in [5], where CMA-ES demonstrated to be the most accurate and robust approach.…”

Section: Introductionmentioning

confidence: 99%

“…With that aim, we studied and experimented with different evolutionary approaches in [5], where CMA-ES demonstrated to be the most accurate and robust approach.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Two different approaches to handle landmark location uncertainty in skull-face overlay:coevolution vs fuzzy landmarks

Ibáñez

Cordón

Damas

2011

Proceedings of the 7th Conference of the European Society for Fuzzy Logic and Technology (EUSFLAT-2011)

Self Cite

View full text Add to dashboard Cite

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 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. Following this approach we are able to look for both the best transformation parameters and the best landmark locations at the same time. Coevolutionary skull-face overlay results are compared with our previous fuzzy-evolutionary automatic method over six skull-face overlay problem instances corresponding to three real-world cases solved by the Physical Anthropology lab at the University of Granada (Spain). Promising results have been achieved though the robustness of the method should be improved.

show abstract

Section: Skull-face Overlay In Craniofacial Superimpositionmentioning

confidence: 99%

Section: Skull-face Overlay In Craniofacial Superimpositionmentioning

confidence: 99%

Section: Skull-face Overlay In Craniofacial Superimpositionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

“…With that aim, we studied and experimented with different evolutionary approaches in [5], where CMA-ES demonstrated to be the most accurate and robust approach.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Two different approaches to handle landmark location uncertainty in skull-face overlay:coevolution vs fuzzy landmarks

Ibáñez

Cordón

Damas

2011

Proceedings of the 7th Conference of the European Society for Fuzzy Logic and Technology (EUSFLAT-2011)

Self Cite

View full text Add to dashboard Cite

show abstract

BSP‐GA: A new Genetic Algorithm for System Optimization and Excellent Schema Selection

Jin

Wilamowska-Korsak

et al. 2014

Syst. Res.

View full text Add to dashboard Cite

The significance of Internet‐of‐Things to Supply Chain Management has been dramatically increasing. The performance of supply chain based on Internet‐of‐Things is largely dependent on its optimization. Genetic algorithms (GAs) are important intelligent methods for complex system optimization problems, but they have some internal drawbacks such as premature and slow convergence to the global optimum. In this paper, we present a new schema protection based GA (BSP‐GA). First, we propose three principles for selecting excellent schema based on the schema theory; second, we propose the concept of K‐intensive effect synthesis operator, and we give a general five‐intensive effect synthesis operator and its proof; third, we give the selection process of excellent schema through an example, and further we give the implementation steps of BSP‐GA. The performance of BSP‐GA has been compared with simple GA by using two carefully chosen benchmark problems. It has been observed that BSP‐GA can yield the global optimum more efficiently than commonly used simple GA. Furthermore, a theorem is presented to guarantee the convergence of BSP‐GA. Copyright © 2014 John Wiley & Sons, Ltd.

show abstract

Forensic Identification by Craniofacial Superimposition Using Fuzzy Set Theory

Ibáñez

Campomanes-Alvarez

Campomanes-Álvarez

et al. 2020

Fuzzy Approaches for Soft Computing and Approximate Reasoning: Theories and Applications

View full text Add to dashboard Cite

An experimental study on the applicability of evolutionary algorithms to craniofacial superimposition in forensic identification

Cited by 58 publications

References 46 publications

Two different approaches to handle landmark location uncertainty in skull-face overlay:coevolution vs fuzzy landmarks

Two different approaches to handle landmark location uncertainty in skull-face overlay:coevolution vs fuzzy landmarks

BSP‐GA: A new Genetic Algorithm for System Optimization and Excellent Schema Selection

Forensic Identification by Craniofacial Superimposition Using Fuzzy Set Theory

Contact Info

Product

Resources

About