On Detecting Domestic Abuse via Faces

Puspita Majumdar, Saheb Chhabra, Richa Singh, Mayank Vatsa; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2018, pp. 2173-2179

Domestic violence is considered a major social problem worldwide. Different countries have enacted the law to contain and protect the victims of domestic violence. In order to understand the nature of domestic violence, medical professionals and researchers have performed manual analysis of facial injuries. The aim of these studies is to find commonly affected facial regions, to determine the types of maxillofacial trauma associated with domestic violence, and to distinguish the injuries of domestic violence from accidents. Analysis of these injuries assist the service providers in providing proper treatment to the victims as well as facilitate law enforcement investigation. This paper automates the process of analyzing the facial injuries to distinguish the victims of domestic abuse from others. For this purpose, Domestic Violence Face database of 450 subjects with two classes namely, Domestic Violence and Non-Domestic Violence, is prepared. The paper also presents a novel framework using activation maps of deep learning features for determining whether an image belongs to domestic violence class or not. The results on the proposed database show that deep learning based framework is effective in detecting domestic injuries.