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{198785,
        author = {Mrs. Amruta V. Naik and Trupti Mahendra Patil and Poonam Sudarshan Barai and Shivani Anil Rathod and Shamal Dharmendra Satpute and Afraz Ismail Sheikh},
        title = {AI FRAMEWORK FOR MASKED FACE AND BODY-METRIC RECOGNITION},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {13315-13321},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=198785},
        abstract = {CrimAi is an open-source prototype designed to support criminal detection through the use of facial recognition and object detection technologies. Built with Python, OpenCV, and database management systems, the project enables real-time identification of individuals from surveillance feeds. By automating the recognition process, CrimAi aims to assist law enforcement agencies in improving the speed, accuracy, and efficiency of criminal identification. This paper provides a structured analysis of the system’s design and architecture, highlights its practical applications, and discusses its current limitations. Finally, we explore promising future directions such as federated learning for privacy-preserving model training, explainable AI for trans- parent decision-making, and multimodal surveillance integration to create more robust and intelligent security solutions. While the system shows promise in improving safety and efficiency, it also raises important considerations regarding privacy and ethical use. This paper discusses the design, implementation, results, applications, and future directions of CrimAi, emphasizing its potential role in transforming modern surveillance and criminal detection.},
        keywords = {Criminal Detection, Face Recognition, Object Detection, Computer Vision, Artificial Intelligence, Machine Learning, OpenCV, Surveillance Systems, Public Safety, Smart Cities},
        month = {April},
        }