Metric Identification of the Same People from Images: How Reliable Is It?

Abstract

Ratios have been applied to humans to identify individuals from images. These attempts have been proven unsuccessful, as camera angle, height, and distortions of the image affected the results. The anharmonic ratio is a ratio of ratios; it has proved successful in the identification of objects from images, as it is not affected by any distortions. The anharmonic ratio was applied to the human body and face to identify individuals from their images. Faces and bodies of twenty South Australian males aged 16-65 years were measured using standard anthropometric techniques. Participants were photographed in high quality images and recorded by standard surveillance camera (low quality images). Ten ratios were calculated from manual measurements and from all images. An Euclidean distance showed ratios incorrectly identified individuals 64.3% of the time between images of different quality. Variation of ratios between individuals is low so that standard deviations of ratios are of the magnitude similar to technical errors of measurements. Therefore participants cannot be isolated based on ratios. Ratios are an unreliable method for identification.

Comparative Assessment of a Novel Photo‐Anthropometric Landmark‐Positioning Approach for the Analysis of Facial Structures on Two‐Dimensional Images

“…In particular, no studies have ever proposed conceptual adaptations to the definition of landmarks for image‐based applications, while those that have addressed FPA‐positioning variability used non‐specific landmark‐positioning approaches (i.e., cephalometric definitions). As a consequence, doubts can be raised concerning the proper and reliable attribution of the investigated landmarks . Recently, an alternative nomenclature (i.e., capulometric landmarks) has been tentatively proposed for the analysis of 2D images .…”

“…Traditional cephalometric definitions, however, merely describe a series of purely anatomical structures lying on the skin surface and/or the underlying bones and were primarily established for the purpose of directly mapping actual living subjects or their lateral‐view X‐ray image for medical purposes . Consequently, their adoption in FPA applications usually leads to a high positioning variability within and between examiners . The main reason for this arises from the fact that different examiners may have different interpretations of where a specific cephalometric landmark should be placed on a two‐dimensional, frontal view, facial image, without any three‐dimensional reference and/or the possibility to touch the subject's actual facial surface.…”

“…The main reason for this arises from the fact that different examiners may have different interpretations of where a specific cephalometric landmark should be placed on a two‐dimensional, frontal view, facial image, without any three‐dimensional reference and/or the possibility to touch the subject's actual facial surface. As a result of this, the general reliability of FPA has been recently challenged by the scientific community . One significant aftermath, in particular, has been the recommendation from the Facial Identification Scientific Working Group (FISWG) to avoid using FPA‐based methodologies as proof of evidence in FFI .…”

“…scientific community (17)(18)(19)23). One significant aftermath, in particular, has been the recommendation from the Facial Identification Scientific Working Group (FISWG) to avoid using FPAbased methodologies as proof of evidence in FFI (21).…”

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

“…The use of facial landmarks have been considered in diverse forensic areas such as identification of living individuals [1,2], age and sex estimation [3,4,5] or craniofacial identification [6] for the dead. All these areas, landmarks are mainly employed to measure distances, proportions [7] and to guide image superimposition processes [8].…”