Single architecture and multiple task deep neural network for altered fingerprint analysis

TL;DR

This paper presents a deep neural network-based method using Inception-v3 architecture for detecting altered fingerprints, identifying alteration types, and recognizing gender, hand, and fingers with high accuracy, aiding forensic investigations.

Contribution

It introduces a multi-task deep learning approach for altered fingerprint analysis, including detection, classification, and attribute recognition, with activation map visualization.

Findings

Achieves over 98% accuracy in altered fingerprint detection.

Successfully classifies alteration types and biometric attributes.

Provides activation maps for interpretability of neural network focus areas.

Abstract

Fingerprints are one of the most copious evidence in a crime scene and, for this reason, they are frequently used by law enforcement for identification of individuals. But fingerprints can be altered. "Altered fingerprints", refers to intentionally damage of the friction ridge pattern and they are often used by smart criminals in hope to evade law enforcement. We use a deep neural network approach training an Inception-v3 architecture. This paper proposes a method for detection of altered fingerprints, identification of types of alterations and recognition of gender, hand and fingers. We also produce activation maps that show which part of a fingerprint the neural network has focused on, in order to detect where alterations are positioned. The proposed approach achieves an accuracy of 98.21%, 98.46%, 92.52%, 97.53% and 92,18% for the classification of fakeness, alterations, gender, hand and fingers, respectively on the SO.CO.FING. dataset.