Improved CNN-Segmentation-Based Finger Vein Recognition Using Automatically Generated and Fused Training Labels

Abstract

We utilise segmentation-oriented CNNs to extract vein patterns from nearinfrared finger imagery and use them as the actual vein features in biometric finger vein recognition. As the process to manually generate ground-truth labels required to train the networks is extremely time-consuming and error prone, we propose several models to automatically generate training data, eliminating the needs for manually annotated labels. Furthermore, we investigate label fusion between such labels and manually generated labels. Based on our experiments, the proposed methods are also able to improve the recognition performance of CNN-network-based feature extraction up to different extents.

Feature extraction of finger-vein patterns based on boosting evolutionary algorithm and its application for loT identity and access management

“…In recent years, deep learning has been received much attention from researchers [5,19,32]. For instance, in the article [5], the authors suggested a convolutional-neural-networkbased finger vein recognition framework and analyse the strengths of the network over four publicly accessible databases.…”

Finger Vein Verification Algorithm Based on Fully Convolutional Neural Network and Conditional Random Field

“…As an extension of this work, [40] was engaged with an novel method to extract the depth feature of vein based on both short-term and long-term memory recurrent neural network, while Yang et al [41] introduced a finger vein segmentation model in light of the generative adversarial networks, which stands astonishing robustness to outliers and vessel breaks. Referring to [42]- [44], semantic segmentation convolutional neural network was optimized to directly abstract the actual finger-vein patterns from NIR finger images while Jalilian and Uhl [43] investigated the effects of fusion and combination training with different labels on finger vein recognition.…”

“…Following the pattern in [39], [43], we begin with image enhancement for each input finger vein image to detect vein patterns more precisely. Then six baselines, such as Repeated line tracking [27] (REP), Wide line detector [12] (WLD), Gabor filter [25] (Gabor), Maximum curvature points [14] (MC), Mean curvature [13] (MMC), Enhanced maximum curvature [32] (EMC) are employed to divide vein pattern into segments, resulting in six binary images.…”

State of the Art in Vascular Biometrics

“…Techniques for RoI determination are typically described in the context of descriptions of the entire recognition toolchain. There are hardly papers dedicated to this [76,94,163,203,209,299] Binary vascular structure using semantic segmentation CNNs [91,[100][101][102] Minutiae [84,148,293] issue separately. A typical example is [287], where an inter-phalangeal joint prior is used for finger vein RoI localisation and haze removal methods with the subsequent application of Gabor filters are used for improving visibility of the vascular structure.…”

“…The first documented approach uses a combination of vein pixel classifier and a shallow segmentation network [91], while subsequent approaches rely on fully fledged deep segmentation networks and deal with the issue of training data generation regarding the impact of training data quality [100] and a joint training [30,40,60,98,144,228] Deep learning (entire toolchain) learning sample similarity [89,284] with manually labelled and automatically generated training data [101]. This book contains a chapter extending the latter two approaches [102].…”