3D Facial Reconstruction from 2D Portrait Imagery

Publication Type:

Journal article preview


Information & Security: An International Journal, Volume 46 (2020)


digital forensics, Forensic Facial Reconstruction, Landmark Alignment



A 3D facial reconstruction from a single 2D portrait image system is presented here. This implementation uses regression trees for facial landmark alignment and 3D morphable models for the reconstruction of the 3D model from an input 2D facial impression. Two generic regression trees were adopted, one being based on the widely adopted 68-landmark structure and the other is based on a 74-landmark structure. The FaceWarehouse dataset was used to create a novel 74-landmark regression tree and during the system’s evaluation.

The accuracy of the models generated was computed through the Root Mean Square, 75th Percentile and Arithmetic Mean comparison metrics. Two different datasets of 2D images were reconstructed in 3D using the 68 and 74 landmark based regression tree landmark structures. The results acquired throughout the evaluation process have shown that a higher level of accuracy and precision was attained from the models reconstructed using 68-landmark regression tree when compared to the 74 developed here. The accuracy produced by the 68-landmark regression tree applied to two sets was that of 85% and 90% as opposed to the 82% and 83% produced by the 74-landmark regression tree on the same model subsets; thus justifying its wide adoption