Beyond shadows and light: Odyssey of face recognition for social good

Abstract

Face recognition technology, though undeniably transformative in its technical evolution, remains conspicuously underleveraged in humanitarian endeavors. This survey highlights its latent utility in addressing critical societal exigencies, ranging from the expeditious identification of disaster-afflicted individuals to locating missing children. We investigate technical complexities arising from facial feature degradation, aging, occlusions, and low-resolution images. These issues are frequently encountered in real-world scenarios. We provide a comprehensive review of state-of-the-art models and relevant datasets, including a meta-analysis of existing and curated collections such as the newly introduced Web and Generated Injured Faces (WGIF) dataset. Our evaluation encompasses the performance of current face recognition algorithms in real-world scenarios, exemplified by a case study on the Balasore train accident in India. By examining factors such as the impact of aging on facial features and the limitations of traditional models in handling low-quality or occluded images, we showcase the complexities inherent in applying face recognition for societal good. We discuss future research directions, emphasizing the need for interdisciplinary collaborations and innovative methodologies to enhance the adaptability and robustness of face recognition systems in humanitarian contexts. Through detailed case studies, we provide insights into the effectiveness of current methods and identify key areas for improvement. Our goal is to encourage the development of specialized face recognition models for social welfare applications, contributing to timely and accurate identification in critical situations.