At present, the fusion of different unimodal biometrics has attracted increasing attention from researchers, who are dedicated to the practical application of biometrics. In this paper, we explored a multi-biometric algorithm that integrates palmprints and dorsal hand veins (DHV). Palmprint recognition has a rather high accuracy and reliability, and the most significant advantage of DHV recognition is the biopsy (Liveness detection). In order to combine the advantages of both and implement the fusion method, deep learning and graph matching were, respectively, introduced to identify palmprint and DHV. Upon using the deep hashing network (DHN), biometric images can be encoded as 128-bit codes. Then, the Hamming distances were used to represent the similarity of two codes. Biometric graph matching (BGM) can obtain three discriminative features for classification. In order to improve the accuracy of open-set recognition, in multi-modal fusion, the score-level fusion of DHN and BGM was performed and authentication was provided by support vector machine (SVM). Furthermore, based on DHN, all four levels of fusion strategies were used for multi-modal recognition of palmprint and DHV. Evaluation experiments and comprehensive comparisons were conducted on various commonly used datasets, and the promising results were obtained in this case where the equal error rates (EERs) of both palmprint recognition and multi-biometrics equal 0, demonstrating the great superiority of DHN in biometric verification.

Research on palmprint recognition has been progressing toward a contactless and unconstrained direction, where the imaging quality is easily disturbed by various factors. Determining the trustworthiness of palmprint image input to the system is crucial for stable and reliable recognition. However, there are few studies on Palmprint Image Quality Assessment (PIQA) for practical scenarios due to the lack of labeled image quality data. In this paper, we propose a Pseudo-label Generation and Ranking Guidance (PGRG) framework for label-free PIQA. Two-stage preparation is performed before the training of quality model. 1) Estimate the recognizability of palmprint images to generate quality pseudo-labels. 2) Generate pseudo-images and guide their quality ranking to pre-train the model. In the final training phase, we propose a label-based ranking loss. It guides the model to determine quality relative relationships by emphasizing the ranking between pseudo-labels. This allows our framework to be applied to a variety of palmprint recognition models. Adequate experiments are conducted on three benchmark unconstrained palmprint databases. The results show that our PGRG framework can effectively improve the performance of existing advanced palmprint recognition models. The Equal Error Rate (EER) can be reduced by up to 2.41% by discarding a small amount of low-quality images compared to the baseline.

Palmprint is one of the discriminant biometric modalities of humans. Recently, deep learning-based palmprint recognition algorithms have improved the accuracy and robustness of recognition results to a new level. Most of them require a large amount of labeled training samples to guarantee satisfactory performance. However, getting enough labeled data is difficult due to time consumption and privacy issues. Therefore, in this article, a novel meta-Siamese network (MSN) is proposed to exploit few-shot learning for small-sample palmprint recognition. During each episode-based training iteration, a few images are selected as sample and query sets to simulate the support and testing sets in the test set. Specifically, the model is trained episodically with a flexible framework to learn both the feature embedding and deep similarity metric function. In addition, two distance-based losses are introduced to assist the optimization. After training, the model can learn the ability to get similarity scores between two images for few-shot testing. Adequate experiments conducted on several constrained and unconstrained benchmark palmprint databases show that MSN can obtain competitive improvements compared with baseline methods, where the best accuracy can be up to 100%.

Deep palmprint recognition has become an emerging issue with great potential for personal authentication on handheld and wearable consumer devices. Previous studies of palmprint recognition are mainly based on constrained data sets collected by dedicated devices in controlled environments, which has to reduce the flexibility and convenience. In addition, general deep palmprint recognition algorithms are often too heavy to meet the real-time requirements of embedded system. In this article, a new palmprint benchmark is established, which consists of more than 20 000 images collected by five brands of smartphones in an unconstrained manner. Each image has been manually labeled with 14 key points for the region of interest (ROI) extraction. Furthermore, a novel deep distillation hashing (DDH) algorithm is proposed as a benchmark for efficient deep palmprint recognition. Palmprint images are converted to binary codes to improve the efficiency of feature matching. Derived from knowledge distillation, new distillation loss functions are constructed to compress the deep model to further improve the efficiency of feature extraction on the light network. Comprehensive experiments are conducted on both constrained and unconstrained palmprint databases. Using DDH, the accuracy of palmprint identification can be increased by up to 11.37%, and the equal error rate (EER) of palmprint verification can be reduced by up to 3.11%. The results indicate the potential of our database, and DDH can outperform other baselines to achieve the state-of-the-art performance. The collected data set is publicly available at http://gr.xjtu.edu.cn/web/bell/resource.

As an effective method of biometrics, palmprint recognition allows the safe identity recognition of humans without spatial and temporal limitations. To build a more robust palmprint recognition system, recent promising Convolutional Neural Networks (CNN) has been incorporated for better palmprint feature extraction and representation. However, the increasing number of palmprint datasets presents us with a cross-domain recognition problem where the upcoming images may come from different imaging conditions compared to the registered palmprints, which will undermine the recognition accuracy significantly. As a supervised approach, the performance of CNN-based model depends on the availability of data and labels from the same domain, which is hard for transferring recognition. To keep the outperforming recognition result of CNN-based models, we propose a novel Regularized Adversarial Domain Adaptative Hashing method (R-ADAH) for cross-domain palmprint recognition based on Deep Hashing Network (DHN). During training, the Maximum Mean Discrepancy (MMD) is incorporated for better adaptive performance. In this scenario, we only train a DHN on the source domain. With the adversarial training, the target network is becoming adaptive to the unlabeled palmprint images with more stable training, unbiased sample gradient and less sensitivity to the hyper-parameter tuning when only domain-specific label is provided. Extensive validation experiments are conducted on benchmark datasets and our self-collected palmprint datasets by mobile phones to test the performance of our model. The results show a promising increase of the recognition performance.

Deep learning-based palmprint recognition algorithms have shown great potential. Most of them are mainly focused on identifying samples from the same dataset. However, they may be not suitable for a more convenient case that the images for training and test are from different datasets, such as collected by embedded terminals and smartphones. Therefore, we propose a novel Joint Pixel and Feature Alignment (JPFA) framework for such cross-dataset palmprint recognition scenarios. Two-stage alignment is applied to obtain adaptive features in source and target datasets. 1) Deep style transfer model is adopted to convert source images into fake images to reduce the dataset gaps and perform data augmentation on pixel level. 2) A new deep domain adaptation model is proposed to extract adaptive features by aligning the dataset-specific distributions of target-source and target-fake pairs on feature level. Adequate experiments are conducted on several benchmarks including constrained and unconstrained palmprint databases. The results demonstrate that our JPFA outperforms other models to achieve the state-of-the-arts. Compared with baseline, the accuracy of cross-dataset identification is improved by up to 28.10% and the Equal Error Rate (EER) of cross-dataset verification is reduced by up to 4.69%. To make our results reproducible, the codes are publicly available at http://gr.xjtu.edu.cn/web/bell/resource.