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{192617,
        author = {Rutuja M. Etankar and Prof. Rakhi S.Lande and Avanti S. Kandalkar and Parth R. Mohod and Rakshita R. Hanwatkar},
        title = {Smart Justice: Artificial Intelligence (AI) -Based FIR Filing & Criminal Identification from Sketches with Secure Police-Citizen Communication},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {2621-2630},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=192617},
        abstract = {Harder crimes mean old ways of tracking offenders fall short, pushing need for smarter online tools everyone can reach. Getting reports filed usually takes too long, ties you to one place, often mixes updates - besides, matching faces from rough witness drawings stays deeply flawed. Our approach, called Smart Justice, weaves together machine learning, hidden logs, and locked messaging channels to upgrade how complaints get stored, criminals tracked.
Submitting complaints happens online via a safe website where users verify identity before filing reports. Because it runs on blockchain, every police report stays unchangeable, tracked, and reliable once recorded. Evidence files, messages, and entries are locked in place so they cannot be altered later. When something gets logged, SHA-2 turns it into a unique fingerprint to catch meddling attempts. Data remains private since AES scrambles information both when saved and sent across systems.
Spotting criminals gets a boost from deep learning, especially through systems that learn faces from hand-drawn sketches. These systems rely on tools called Convolutional Neural Networks to match rough drawings with actual people. Instead of photos alone, investigators now work with fake sketches made from real pictures - crafted using digital tricks and expanded with added variations. Often starting from words, new methods turn witness statements into images automatically, thanks to language-savvy algorithms and smart generators. When no photo exists, these face-like drafts still form clear enough likenesses. Once built, each drawing goes through extra steps so it can be compared to old police files.
A trustworthy platform for officers tracks reports, matches faces through drawings, while allowing safe message exchange between public and agencies. Built-in intelligence quickens access, shortens delays, sharpens case outcomes, keeps private details locked away. When smart pattern spotting meets tamper-proof record storage, the outcome strengthens digital fairness systems fit for today’s policing demands.},
        keywords = {Smart Justice, Blockchain, Machine Learning, Facial Sketch Recognition, Secure Crime Reporting.},
        month = {April},
        }