Estimation of 2D to 3D dimensions and proportionality indices for facial examination

Martos, Rubén; Valsecchi, Andrea; Ibáñez, Óscar; Aguilera, Inmaculada Alemán

doi:10.1016/j.forsciint.2018.03.037

Cited by 11 publications

(11 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Future research works should be addressed to tackle and/or test automatic approaches on images showing different poses and acquisition conditions. A different interesting future work would be to analyze if the accuracy/dispersion of the current method is enough for other recent automatic methods in forensic anthropology such as facial examination [7], skull-face anatomical/morphological correspondence [39] or skull-face overlay [40].…”

Section: Discussionmentioning

confidence: 99%

Automatic cephalometric landmarks detection on frontal faces: An approach based on supervised learning techniques

Porto

Lima

Flores

et al. 2019

Digital Investigation

Self Cite

View full text Add to dashboard Cite

Facial landmarks are employed in many research areas such as facial recognition, craniofacial identification, age and sex estimation among the most important.In the forensic field, the focus is on the analysis of a particular set of facial landmarks, defined as cephalometric landmarks. Previous works demonstrated that the descriptive adequacy of these anatomical references for an indirect application (photo-anthropometric description) increased the marking precision of these points, contributing to a greater reliability of these analyzes. However, most of them are performed manually and all of them are subjectivity inherent to the expert examiners. In this sense, the purpose of this work is the development and validation of automatic techniques to detect cephalometric landmarks from digital images of frontal faces in forensic field. The presented approach uses a combination of computer vision and image processing techniques within a supervised learning procedures. The proposed methodology obtains similar precision to a group of human manual cephalometric reference markers and result to be more accurate against others state-of-the-art facial landmark detection frameworks. It achieves a normalized mean distance (in pixel) error of 0.014, similar to the mean inter-expert dispersion (0.009) and clearly better than other automatic approaches also analyzed along of this work (0.026 and 0.101).

show abstract

Section: Discussionmentioning

confidence: 99%

Automatic cephalometric landmarks detection on frontal faces: An approach based on supervised learning techniques

Porto

Lima

Flores

et al. 2019

Digital Investigation

Self Cite

View full text Add to dashboard Cite

show abstract

“…The first phase of photo-anthropometry involves the identification and placements of landmarks (or reference points) on the images that are to be measured for comparison (Flores et al, 2019). Once these landmarks have been determined and identified, the measurements between these points are made to help with comparison (Martos et al, 2018). Due to the images not having a scale, the absolute size is not useable, and the measurements then need to be made in ratios and proportions to create indices for comparison (Martos et al, 2018).…”

Section: Facial Photo-anthropometrymentioning

confidence: 99%

“…Once these landmarks have been determined and identified, the measurements between these points are made to help with comparison (Martos et al, 2018). Due to the images not having a scale, the absolute size is not useable, and the measurements then need to be made in ratios and proportions to create indices for comparison (Martos et al, 2018). The only way to use precise measurements for images is to know the exact extrinsic and intrinsic factors at the time the photograph was taken.…”

Section: Facial Photo-anthropometrymentioning

confidence: 99%

“…Photo-anthropometry has the potential to be used for linking of serial killer victims and may be automated with the right expertise. This method is repeatable which can allow it to be used within large data bases (Martos et al, 2018). FISWG do state that photo-anthropometry should not be used as an independent comparison technique for positive identification or exclusion, however, this technique could aid in the filtering a large number to faces within a database and can have the potential to be useful for forensic labs and legal prosecutors in order to reduce the list of possible matches (Martos et al, 2018).…”

Section: Facial Photo-anthropometrymentioning

confidence: 99%

“…This is in contrast to facial recognition whereby an individual's facial traits are compared to a database of facial images in a biometric system (one‐to‐many; FISWG, 2010). The Facial Identification Scientific Working Group (FISWG) details guidelines of four main methods for facial comparison: holistic comparison, morphological analysis, photo‐anthropometry, and superimposition (FISWG, 2012; Martos, Valsecchi, Ibáñez, & Alemán, 2018).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Face similarity linkage: A novel biometric approach to sexually motivated serial killer victims

2020

View full text Add to dashboard Cite

Some sexually motivated serial killers target victims on the basis of appearance. Therefore, multiple victims of a single serial killer are likely to have some facial features and geometries that are similar. The current research was undertaken to propose a technique, termed face similarity linkage, to evaluate whether victims of a serial killer have statistically more similar facial measurements than a randomly chosen person of the same gender. To test this, three of Ted Bundy's victims were randomly selected and anatomical landmarks were located and measured to produce proportionality indices of their faces. A random subject from an online database was used as a comparison. The results showed there were no statistically significant differences between the three of Bundy's victims, however there was significant difference between 11 of the 17 facial measurements of Bundy's victims when compared to a random person. This research serves as a proof of concept that, with more advanced means of data collection, may be a useful tool for law enforcement for linking serial homicides. The current method is relatively novel, and in need of expert systems interfaces to improve speed and application, which is outlined in the current study.

show abstract

Artificial intelligence in forensic anthropology: State of the art and Skeleton-ID project

Martos,

Ibáñez,

Mesejo

2024

Methodological and Technological Advances in Death Investigations

View full text Add to dashboard Cite

Estimation of 2D to 3D dimensions and proportionality indices for facial examination

Cited by 11 publications

References 26 publications

Automatic cephalometric landmarks detection on frontal faces: An approach based on supervised learning techniques

Automatic cephalometric landmarks detection on frontal faces: An approach based on supervised learning techniques

Face similarity linkage: A novel biometric approach to sexually motivated serial killer victims

Artificial intelligence in forensic anthropology: State of the art and Skeleton-ID project

Contact Info

Product

Resources

About