ANALYZING IMAGES FOR FORENSIC EVIDENCE SUCH AS FINGERPRINTS, FOOTPRINTS AND BLOOD STAINS USING CNN

Abstract

Forensic science plays a crucial role in criminal investigations by analyzing evidence to identify suspects and solve crimes. With advancements in digital imaging technology, deep learning techniques, particularly Convolutional Neural Networks (CNNs), have revolutionized forensic evidence analysis by enabling automated and precise identification of patterns in forensic images. This project focuses on developing a CNN-based forensic evidence analysis system that processes images of fingerprints, footprints, and bloodstains to assist in criminal investigations. Traditional forensic examination methods are often manual, time-consuming, and prone to human error. To overcome these challenges, our system leverages deep learning models trained on three different datasets containing fingerprints, footprints, and bloodstains. The system works by analyzing an input forensic image and comparing it with an existing database. If a match is found, the system identifies the individual as a potential suspect; otherwise, the person is classified as not registered in the database. This approach enhances the efficiency, accuracy, and scalability of forensic investigations by reducing dependency on manual examination. Our results demonstrate the effectiveness of CNN-based forensic analysis in crime detection, highlighting its potential in law enforcement applications. However, challenges such as dataset quality, model interpretability, and variations in forensic evidence remain areas for future improvement.