Martos Rubén, Valsecchi Andrea, Ibáñez Oscar, Alemán Inmaculada
Doctoral Program in Biomedicine, Department of Legal Medicine, Toxicology and Physical Anthropology, University of Granada, Spain.
Department of Computer Science and Artificial Intelligence, University of Granada, Spain.
Forensic Sci Int. 2018 Jun;287:142-152. doi: 10.1016/j.forsciint.2018.03.037. Epub 2018 Apr 3.
Photo-anthropometry is a metric-based facial image comparison technique where measurements of the face are taken from an image using predetermined facial landmarks. In particular, dimensions and proportionality indices (DPIs) are compared to DPIs from another facial image. Different studies concluded that photo-anthropometric facial comparison, as it is currently practiced, is unsuitable for elimination purposes. The major limitation is the need for images acquired under very restrictive, controlled conditions. To overcome this latter issue, we propose a novel methodology to estimate 3D DPIs from 2D ones. It uses computer graphic techniques to simulate thousands of facial photographs under known camera conditions and regression to derive the mathematical relationship between 2D and 3D DPIs automatically. Additionally, we present a methodology that makes use of the estimated 3D DPIs for reducing the number of potential matches of a given unknown facial photograph within a set of known candidates. The error in the estimation of the 3D DPIs can be as large as 35%, but both I and III quartiles are consistently inside the ±5% range. The methodology for filtering cases has demonstrated to be useful in the task of narrowing down the list of possible candidates for a given photograph. It is able to remove on average (validated using cross-validation technique) 57% and 24% of the negative cases, depending on the amounts of DPIs available. Limitations of the work developed together with open research lines are included within the Discussion section.
照片人体测量法是一种基于度量的面部图像比较技术，通过使用预先确定的面部标志点从图像中获取面部测量数据。具体而言，将面部的尺寸和比例指数（DPI）与另一张面部图像的DPI进行比较。不同的研究得出结论，目前所采用的照片人体测量面部比较方法不适用于排除目的。主要限制在于需要在非常严格、可控的条件下获取图像。为克服这一问题，我们提出了一种从二维DPI估计三维DPI的新方法。它利用计算机图形技术在已知相机条件下模拟数千张面部照片，并通过回归自动推导二维和三维DPI之间的数学关系。此外，我们还提出了一种利用估计出的三维DPI来减少给定未知面部照片在一组已知候选照片中潜在匹配数量的方法。三维DPI估计中的误差可能高达35%，但第一和第三四分位数始终在±5%的范围内。过滤案例的方法已证明在缩小给定照片可能候选者列表的任务中很有用。根据可用DPI的数量，它平均能够（使用交叉验证技术验证）去除57%和24%的负面案例。讨论部分包括了所开展工作的局限性以及开放的研究方向。
