Liu Ching Yiu Jessica, Wilkinson Caroline
Face Lab, IC1 Liverpool Science Park, 131 Mount Pleasant, Liverpool, L3 5TF, United Kingdom.
Liverpool School of Art & Design, Duckinfield Street Liverpool, L3 5RD, United Kingdom.
Forensic Sci Int. 2020 Mar;308:110170. doi: 10.1016/j.forsciint.2020.110170. Epub 2020 Jan 28.
Predicting the possible age-related changes to a child's face, age progression methods modify the shape, colour and texture of a facial image while retaining the identity of the individual. However, the techniques vary between different practitioners. This study combines different age progression techniques for juvenile subjects, various researches based on longitudinal radiographic data; physical anthropometric measurements of the head and face; and digital image measurements in pixels. Utilising 12 anthropometric measurements of the face, this study documents a new workflow for digital manual age progression. An inter-observer error study (n = 5) included the comparison of two age progressions of the same individual at different ages. The proposed age progression method recorded satisfactory levels of repeatability based on the 12 anthropometric measurements. Seven measurements achieved an error below 8.60%. Facial anthropometric measurements involving the nasion (n) and trichion (tr) showed the most inconsistency (14-34% difference between the practitioners). Overall, the horizontal measurements were more accurate than the vertical measurements. The age progression images were compared using a manual morphological method and machine-based face recognition. The confidence scores generated by the three different facial recognition APIs suggested the performance of any age progression not only varies between practitioners, but also between the Facial recognition systems. The suggested new workflow was able to guide the positioning of the facial features, but the process of age progression remains dependant on artistic interpretation.
年龄递进方法通过改变面部图像的形状、颜色和纹理来预测儿童面部可能出现的与年龄相关的变化，同时保留个体身份。然而，不同从业者使用的技术有所不同。本研究结合了针对青少年受试者的不同年龄递进技术、基于纵向放射学数据的各种研究、头部和面部的人体测量学测量以及以像素为单位的数字图像测量。本研究利用面部的12项人体测量数据，记录了一种新的数字手动年龄递进工作流程。一项观察者间误差研究（n = 5）包括对同一个体在不同年龄的两种年龄递进结果进行比较。基于这12项人体测量数据，所提出的年龄递进方法显示出令人满意的可重复性水平。七项测量的误差低于8.60%。涉及鼻根点（n）和发缘点（tr）的面部人体测量显示出最大的不一致性（从业者之间的差异为14 - 34%）。总体而言，水平测量比垂直测量更准确。使用手动形态学方法和基于机器的人脸识别对年龄递进图像进行了比较。三种不同面部识别应用程序编程接口生成的置信度分数表明，任何年龄递进的性能不仅在从业者之间存在差异，在面部识别系统之间也存在差异。所建议的新工作流程能够指导面部特征的定位，但年龄递进过程仍然依赖于艺术诠释。
