Classifies a given aadhaar image to real or fake by doing two levels of analysis.

A Python-based desktop tool for detecting digital image forgeries. It applies forensic techniques—Error Level Analysis, Metadata Extraction, Histogram, Noise Map, JPEG Ghost, and Copy-Move Detection—to reveal inconsistencies and visual clues, helping experts assess image authenticity without automation.

Edited Images Analyser

Developed an intelligent solution using OCR, QR code detection, and computer vision to extract and validate Aadhaar details from images. Applied preprocessing for rotated/skewed inputs, ensured fraud detection via pattern checks, and improved accuracy for secure, automated identity verification.

A multi-layered AI forensic system combining ELA, CLIP, and Qwen2-VL to detect digital forgeries, deepfakes, and AI-generated synthetic media.

🎩 A comprehensive document authenticity verification tool with advanced image forensics and LLM-based text analysis.

Python implementation of the Error Level Analysis algorithm in scikit-image with a GUI made in TKinter

Separates real and fake images

Official implementation of "A Triple-Stream Forensic Framework for Image Forgery Detection and Retrieval".

Create a gif of an image as it is increasingly compressed using error analysis to show where abnormal degradation can be observed.

DocGuard Sentinel is an enterprise-grade, real-time banking underwriting forensics and automated compliance platform. It bridges Computer Vision (Error Level Analysis), Client-Side Behavioral Telemetry, and Multi-Modal Agentic Intelligence (Gemini 1.5 Flash) to instantly detect document tampering, verify financial alignment across distinct files, t

A web-based image forgery detection system using classical computer vision algorithms (SIFT, BRISK, AKAZE, ORB) and deep learning models (ResNet18, CNN+LSTM) with Error Level Analysis. Built with FastAPI, React, and PyTorch.

A browser-based forensic image analysis tool for detecting digital manipulation and re-compression artifacts

Python CLI tool to visually detect photoshopped pictures using Error Level Analysis