Deep Palmprint Recognition with Alignment and Augmentation of Limited Training Samples

Abstract

This paper builds upon a previously proposed automatic palmprint alignment and classification system. The proposed system was geared towards palmprints acquired from either contact or contactless sensors. It was robust to finger location and fist shape changes—accurately extracting the palmprints in images without fingers. An extension to this previous work includes comparisons of traditional and deep learning models, both with hyperparameter tuning. The proposed methods are compared with related verification systems and a detailed evaluation of open-set identification. The best results were yielded by a proposed Convolutional Neural Network, based on VGG-16, and outperforming tuned VGG-16 and Xception architectures. All deep learning algorithms are provided with augmented data, included in the tuning process, enabling significant accuracy gains. Highlights include near-zero and zero EER on IITD-Palmprint verification using one training sample and leave-one-out strategy, respectively. Therefore, the proposed palmprint system is practical as it is effective on data containing many and few training examples.

Contactless Palmprint Recognition System: A Survey

“…An ab-initio linear non-supervised approach called principal component analysis (PCA) was applied to extract the holistic vectors. [77], [87], [88], while various unsupervised approaches, such as independent component analysis (ICA) and locality preserving projection (LPP), have been used to recognize palmprints [10], [24], [53]. However, supervised methods are generally more efficient when resolving issues with recognition.…”

Modern Available Palmprint Databases: A Review

“…Palm-related features, as well as major features like ridges, valleys, and minutiae point primary lines, exhibit great accuracy in all biometric features. Where the palmprint has a large ROI, it can be taken at a lesser resolution and from a larger distance with a less costly sensor or DSLR camera, making it less expensive [6]. Palmprint have low distortion, good stability, and high uniqueness when compared to other biometrics.…”