Age-Invariant Face Recognition: A Comprehensive Study of Methods, Datasets, and New Algorithm for Immigration Control

Face recognition has emerged as a prominent field of study, finding diverse applications in domains such as biometrics, human-computer interaction, surveillance, and access control. Despite the considerable accomplishments of face recognition technologies, the challenge of Age-Invariant Face Recognition (AIFR) continues to impede the seamless operation of real-time applications like passport authentication, locating missing children, and identifying wanted individuals. Hence, an in-depth exploration of age-invariant characteristics is paramount in face analysis. This study extensively reviews advancements, obstacles, and prospective research avenues in AIFR. It comprehensively examines conventional methodologies, deep learning-based approaches, and the available datasets catering to AIFR. Furthermore, this study develops an AIFR framework, integrating established algorithms to facilitate real-time passport authentication, supported by a user-friendly graphical user interface (GUI). The research also overcomes the challenges encountered while implementing prevailing techniques and enhances real-time applicability through required preprocessing techniques. In conclusion, the paper underscores a multitude of pertinent and unexplored avenues for future research, charting the course for advancements in the challenging realm of age-invariant face recognition. The project page is available at https://github.com/Mohsin849/AIFR-Face-Maching