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{200761,
        author = {Sanskar Gupta and vishal verma and sourav kundu and vineet kumar and Jasneet kaur},
        title = {Image Forgery Detection System},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {12},
        pages = {2405-2412},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=200761},
        abstract = {The advancement of complex digital image fakes has been greatly encouraged by the fast-growing generative AI models and high-precision image-editing software which requires very sophisticated forensic analysis methods. This project has proposed a state-of-the-art computational Image Forgery Detection System that is capable of identifying structural, statistical and noisy inconsistencies introduced from the operations involving tampering. The system primarily covers copy-move, splicing, and content-removal forgeries by building a multistage pipeline that includes image pre-processing (normalization), feature amplification through manipulation of signal domain features, and extraction of intrinsic fingerprints such as PRNU noise residuals and frequency-domain artifacts. Hybrid detection framework utilizing combination of deep learning based convolutional representations and traditional feature descriptors, makes separation between real and changed regions easier. Experimental evaluation shows strong classification accuracy coupled with reliable pixel-level localization. This system provides a robust forensic measure to validate the authenticity of an image for security, law enforcement and forensic investigation applications.},
        keywords = {Negative Image Recognition, Multimedia Forensic, Copy Move Forgery (CMF), Digital Media Spoofing Detection, Image Forgery Localisation, CNN based feature descriptor extraction; Noise Residual Analysis (NRA); PRNU Fingerprint; Frequency Domain Features.},
        month = {May},
        }