This paper describes an examination of the potential for knuckle and fingernail bed biometrics to provide digital evidence in online child sexual abuse and exploitation cases, using the algorithms and software used for identifying hands and cropping the region of interest; the paper plays out the pre-processing of the extracted region of interest, the models used for biometric verification, and the fusion criteria.
The grooming process involves sexually explicit images or videos sent by the offender to the minor. Although offenders may try to conceal their identity, these sexts often include hand, knuckle, and nail bed imagery. The authors present a novel biometric hand verification tool designed to identify online child sexual exploitation offenders from images or videos based on biometric/forensic features extracted from hand regions. The system can match and authenticate hand component imagery against a constrained custody suite reference of a known subject by employing advanced image processing and machine learning techniques. The authors conducted experiments on two hand datasets: Purdue University and Hong Kong. In particular, the Purdue dataset collected for this study allowed them to evaluate the system performance on various parameters, with specific emphasis on camera distance and orientation. To explore the performance and reliability of the biometric verification models, the authors considered several parameters, including hand orientation, distance from the camera, single or multiple fingers, architecture of the models, and performance loss functions. Results showed the best performance for pictures sampled from the same database and with the same image capture conditions. They conclude the biometric hand verification tool offers a robust solution that will operationally impact law enforcement by allowing agencies to investigate and identify online child sexual exploitation offenders more effectively. They also highlight the strength of the system and the current limitations. (Published Abstract Provided)