Few‐shot palmprint recognition via graph neural networks

Abstract

At present, palmprint recognition based on deep learning has been more and more widely used in identity recognition due to its many advantages. However, these algorithms often require a large amount of labelled data for training. In fact, it is difficult and expensive to get enough data that meets the requirements. In this Letter, based on a small amount of labelled images, the authors proposed a method for few-shot palmprint recognition using Graph Neural Networks (GNNs). The palmprint features extracted by the convolutional neural network are processed into nodes in the GNN. The edges in the GNN are used to represent similarities between image nodes. The parameters in the network are continuously optimised, and finally, the category to which each image belongs is obtained. Further, they adopted a mobile phone to create a palmprint database in an unconstrained way. Adequate experiments were performed on the benchmark database and the authors' self-built database. The experimental results show that their proposed GNN-based few-shot palmprint recognition can obtain state-of-the-art performance, where the accuracy is over 99.90%.

Towards open-set touchless palmprint recognition via weight-based meta metric learning

“…Zhao and Zhang [29] proposed Deep Discriminative Representation (DDR) to learn discriminative features with limited palmprint training data using deep convolutional networks. Shao and Zhong [30] proposed a few-shot palmprint recognition framework based on graph neural networks using only a few of training samples. Izadpanahkakhk et al .…”

Residual connection-based graph convolutional neural networks for gait recognition

“…Over the last few years, Graph Convolutional Neural Network has been applied in palmprint recognition [35], object segmentation [36], image denoising [37], hand gesture recognition [38], and person re-identification [39]. Zhang et al [40] worked on human activity recognition from skeleton sequence by combining spatial and temporal feature maps extracted by the two-stream GCNN architecture.…”

Toward Unconstrained Palmprint Recognition on Consumer Devices: A Literature Review

“…Du et al [144] used a similar architecture trained using the few-shot strategy. Shao et al [152] used the output of a 3-layer Siamese network, and matched the palmprints from two datasets (HKPU-Multispectral and a dataset collected with a smartphone camera) with a Graph Neural Network (GNN). Unfortunately, the training details of the Siamese network are not clear.…”