Alongside specific elements such as fingerprints (anatomical) and writing (behavioural), the size and geometry of the hand can lead to important demographical indicators such as sex, height, weight and foot size as soft-biometrics.
These capacities could be enhanced by adding predicted soft-biometric traits to the decision. Forensic analysis has proved the capacity to match a hand image from crime scene footage to a constrained image even under conditions that are known to impair performance with other biometrics. Furthermore, hand length measures do not require invasive techniques to collect, and they can even be collected covertly. The human hand offers a rich seam of anatomical characteristics that are easily obtainable and measurable. This work aims to predict a complete set of soft-biometric traits from hand images: sex, height, weight and foot size, thereby providing flexibility within available data. These predicted pieces of information may be critical for supporting decisions within both biometric and forensic domains. a hand image) to predict other previously unknown pieces of information (such as individual’s sex). These results are based on the ability to use known information (i.e.
United kingdom regress to weights verification#
Although soft-biometric traits lack distinctiveness to identify an individual, it has been shown that a combination of multiple soft-biometrics can add a valuable degree of certainty to primary verification decisions. Knowing the sex of the subject enables confirmation of a primary verification decision, or allows a narrowing of a watch-list identification search space, potentially improving the certainty of an assessment, or the time required to reach a decision. Consider an environment in which a facial system is providing primary biometric evidence.
įor automated biometrics, meta-data or soft-biometrics refers to additional characteristics of the subject that can be used to support or sharpen an identification or verification decision. In the forensic domain it is frequently the case that identifications are based on multiple sources of partial evidence, therefore understanding how one characteristic of human identity maps to a further characteristic aids identification. Both disciplines require an accurate assessment of human characteristics thereby allowing confidence in the result. This is similar to the task as it exists in the field of forensics, where forensic verification or identification of subjects is required by human inspection typically for legal purposes. Using individual modalities such as face, iris, hand and voice, numerous deployments have been made in application areas such as border and physical access control, where the task is to verify an identity against a pre-enrolled template or identifying from a dataset of pre-enrolled subjects. The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.Ĭompeting interests: The authors have declared that no competing interests exist.Īutomated Information and Communications Technology (ICT)-based biometric technologies that recognise humans through physiological or behavioural characteristics enable a convenient, accurate and repeatable method for identity assessment. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.ĭata Availability: All data files are available from the Zenodo database (DOI: ).įunding: This work is supported by the UK Engineering and Physical Sciences Research Council as part of the SID: An Exploration of Super-Identity project (EPSRC EP/J004995/1). Received: Accepted: OctoPublished: November 2, 2016Ĭopyright: © 2016 Miguel-Hurtado et al. National University of Defense Technology, CHINA Citation: Miguel-Hurtado O, Guest R, Stevenage SV, Neil GJ, Black S (2016) Comparing Machine Learning Classifiers and Linear/Logistic Regression to Explore the Relationship between Hand Dimensions and Demographic Characteristics.
0 kommentar(er)
