Residual Feature Pyramid Network for Enhancement of Vascular Patterns

TL;DR

This paper introduces ResFPN, a residual feature pyramid network that enhances finger vein images by detecting veins of various widths, leading to improved recognition accuracy across multiple datasets.

Contribution

The paper presents a novel ResFPN architecture with SDBlock and FAM modules for robust vein detection, independent of recognition pipelines.

Findings

Up to 5% reduction in recognition errors

Effective across different datasets

Improves vein pattern detection accuracy

Abstract

The accuracy of finger vein recognition systems gets degraded due to low and uneven contrast between veins and surroundings, often resulting in poor detection of vein patterns. We propose a finger-vein enhancement technique, ResFPN (Residual Feature Pyramid Network), as a generic preprocessing method agnostic to the recognition pipeline. A bottom-up pyramidal architecture using the novel Structure Detection block (SDBlock) facilitates extraction of veins of varied widths. Using a feature aggregation module (FAM), we combine these vein-structures, and train the proposed ResFPN for detection of veins across scales. With enhanced presentations, our experiments indicate a reduction upto 5% in the average recognition errors for commonly used recognition pipeline over two publicly available datasets. These improvements are persistent even in cross-dataset scenario where the dataset used to train the ResFPN is different from the one used for recognition.