Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{196278,
        author = {Chetan Mahendra Patil and Bhimeshree suresh  kapse and Pavan kumar Arjun Pawar and Yash Anil Chavhan and Mrunal Dinesh Kapse and Dr.Sushama Telerande},
        title = {Missing Person Identification System: Architecture, Experiments, and Results},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {2711-2714},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=196278},
        abstract = {The identification of long-term missing persons is a critical challenge for law enforcement worldwide, primarily due to the natural aging of facial features over time. Conventional facial recognition systems rely on static reference photographs that quickly become outdated, leading to significant drops in identification accuracy after periods as short as two years. This paper presents an extended and experimentally validated system that integrates a Generative Adversarial Network (GAN)-based age-progression module with a Convolutional Neural Network (CNN)-based facial recognition pipeline. Our system generates a portfolio of photorealistic, age-progressed facial images from a single input photograph and uses these to augment the search database for real-time surveillance matching. Experimental results on the UTKFace and MORPH Album 2 datasets demonstrate that the proposed system achieves a Rank-1 identification accuracy of 84.6% for cases involving a four-year time gap—a 22.9 percentage point improvement over a baseline system using no age progression. The GAN component achieves a FID score of 31.4 and an SSIM of 0.81, confirming high-fidelity, identity-preserving image synthesis.},
        keywords = {Missing Persons Identification, Age Progression, Generative Adversarial Networks (GAN), Facial Recognition, Convolutional Neural Networks (CNN), FaceNet, UTKFace, MORPH Dataset, Surveillance Systems, Computer Vision.},
        month = {April},
        }