Subclass Contrastive Loss for Injured Face Recognition

TL;DR

This paper introduces a novel Subclass Contrastive Loss for injured face recognition, addressing a critical challenge in identifying victims with facial injuries, and presents a new database to facilitate research in this area.

Contribution

The paper proposes a new loss function specifically designed for injured face recognition and creates a dedicated database to advance research in this field.

Findings

The proposed loss outperforms existing methods in injured face recognition.

A new Injured Face database is introduced to support research.

Experimental results demonstrate improved recognition accuracy.

Abstract

Deaths and injuries are common in road accidents, violence, and natural disaster. In such cases, one of the main tasks of responders is to retrieve the identity of the victims to reunite families and ensure proper identification of deceased/ injured individuals. Apart from this, identification of unidentified dead bodies due to violence and accidents is crucial for the police investigation. In the absence of identification cards, current practices for this task include DNA profiling and dental profiling. Face is one of the most commonly used and widely accepted biometric modalities for recognition. However, face recognition is challenging in the presence of facial injuries such as swelling, bruises, blood clots, laceration, and avulsion which affect the features used in recognition. In this paper, for the first time, we address the problem of injured face recognition and propose a novel Subclass Contrastive Loss (SCL) for this task. A novel database, termed as Injured Face (IF) database, is also created to instigate research in this direction. Experimental analysis shows that the proposed loss function surpasses existing algorithm for injured face recognition.