Book Title: Computational Criminology: AI Applications in Forensic Science and Criminal Justice
Editors: Dr. Xavier Louis, Dr. Surbhi Girdhar, Ms. Aswathi Chandran Nair, Mr. Ravi Kumar, and Ms. Nandini Katare
Chapter: 18
DOI: https://doi.org/10.59646/704/18
Author: S Mahammad Asif
Abstract
The identification of individuals from the distinctive characteristics of their movement particularly their walking gait represents an emerging frontier in forensic biometrics with significant implications for criminal investigations. Unlike facial recognition or fingerprint comparison, gait-based identification operates at distances and under conditions where conventional biometric capture is impossible: through crowds, at night, from low-resolution surveillance cameras, and with subjects wearing head coverings or masks. This chapter examines the neurophysiological and biomechanical foundations of gait individuality, surveys the computational methods from model-based kinematic analysis through deep convolutional-recurrent architectures trained on large-scale gait databases that enable automated gait recognition, and evaluates the forensic validation status and courtroom admissibility of gait evidence. The chapter also considers the broader category of behavioural biometrics including keystroke dynamics, mouse movement patterns, and touchscreen behaviour and their emerging role in digital identity attribution.