On the Feasibility of 3D Model-Based Forensic Height and Weight Estimation

Neerja Thakkar, Hany Farid; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2021, pp. 953-961

Forensic DNA analysis has been critical in prosecuting crimes and overturning wrongful convictions. At the same time, other physical and digital forensic identification techniques---used to link a suspect to a crime scene---are plagued with problems of accuracy, reliability, and reproducibility. Flawed forensic science can have devastating consequences -- the National Registry of Exonerations identified that flawed forensic techniques contribute to almost a quarter of wrongful convictions in the United States. Even some of the most basic, general-purpose forensic techniques for measuring a person's height and weight are unreliable. We propose using recent advances in 3D body-pose estimation to estimate height and weight from a single, unconstrained image. The reliability of this method is assessed using large-scale simulations and an in-the-wild dataset, bounding the expected accuracy with which height and weight can be estimated, and providing a road map for further improvements.