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{189053,
        author = {Dhiraj Pal and Leena Patil and Ajay Yadav and Rehan Sheikh and Mantasha Khan and Sanika Gedam},
        title = {Sketch Match-Net: A CNN-Based Framework for Sketch-to Photo Suspect Identification},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {7},
        pages = {4790-4795},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=189053},
        abstract = {Traditional criminal identification through facial sketches is manually labor-intensive and subjective, depending entirely on the artistic abilities of forensic artists; therefore, the result is always inconsistent and of low accuracy. This paper presents Sketch Match-Net, an intelligent face identification system that updates the traditional sketch-based face recognition. The proposed framework will make use of the CNN architecture in order to bridge the visual gap between a manually created sketch and real facial images. A user-friendly digital interface is developed which generates composite sketches through a drag-and-drop mechanism using modular facial components. It introduces high precision and efficiency in the process. The generated sketches are then processed through a trained CNN model for feature extraction and matched with a criminal database hosted on the cloud for identifying potential suspects. After a successful identification, it will provide detailed information about the suspect with identity records and associated images. Experimental results indicate improvements in accuracy, scalability, and enhanced processing speed compared to traditional manual methods. Sketch Match-Net thus constitutes a reliable, automated, and technology-driven platform which focuses on enhancing modern investigative practices and improving criminal identification processes.},
        keywords = {Convolutional Neural Networks (CNN), Facial Recognition, Feature Extraction, Sketch-Based Identification, Artificial Intelligence (AI), Deep Learning, Image Processing, Criminal Identification, Cloud Computing.},
        month = {December},
        }