Search

Academic achievement is a critical measure of intellectual ability, prompting extensive research into cognitive tasks as potential predictors. Neuroimaging technologies, such as functional near-infrared spectroscopy (fNIRS), offer insights into brain hemodynamics, allowing understanding of the link between cognitive performance and academic achievement. Herein, we explored the association between cognitive tasks and academic achievement by analyzing prefrontal fNIRS signals. A novel quantum annealer (QA) feature selection algorithm was applied to fNIRS data to identify cognitive tasks correlated with CSAT scores. Twelve features (signal mean, median, variance, peak, number of peaks, sum of peaks, range, minimum, kurtosis, skewness, standard deviation, and root mean square) were extracted from fNIRS signals at two time windows (10- and 60-s) to compare results from various feature variable conditions. The feature selection results from the QA-based and XGBoost regressor algorithms were compared to validate the former's performance. In a two-step validation process using multiple linear regression models, model fitness (adjusted R2) and model prediction error (RMSE) values were calculated. The quantum annealer demonstrated comparable performance to classical machine learning models, and specific cognitive tasks, including verbal fluency, recognition, and the Corsi block tapping task, were correlated with academic achievement. Group analyses revealed stronger associations between Tower of London and N-back tasks with higher CSAT scores. Quantum annealing algorithms have significant potential in feature selection using fNIRS data, and represents a novel research approach. Future studies should explore predictors of academic achievement and cognitive ability. [ABSTRACT FROM AUTHOR]

Accurately extracting the Region of Interest (ROI) of a palm print was crucial for subsequent palm print recognition. However, under unconstrained environmental conditions, the user's palm posture and angle, as well as the background and lighting of the environment, were not controlled, making the extraction of the ROI of palm print a major challenge. In existing research methods, traditional ROI extraction methods relied on image segmentation and were difficult to apply to multiple datasets simultaneously under the aforementioned interference. However, deep learning-based methods typically did not consider the computational cost of the model and were difficult to apply to embedded devices. This article proposed a palm print ROI extraction method based on lightweight networks. Firstly, the YOLOv5-lite network was used to detect and preliminarily locate the palm, in order to eliminate most of the interference from complex backgrounds. Then, an improved UNet was used for keypoints detection. This network model reduced the number of parameters compared to the original UNet model, improved network performance, and accelerated network convergence. The output of this model combined Gaussian heatmap regression and direct regression and proposed a joint loss function based on JS loss and L2 loss for supervision. During the experiment, a mixed database consisting of 5 databases was used to meet the needs of practical applications. The results showed that the proposed method achieved an accuracy of 98.3% on the database, with an average detection time of only 28ms on the GPU, which was superior to other mainstream lightweight networks, and the model size was only 831k. In the open-set test, with a success rate of 93.4%, an average detection time of 5.95ms on the GPU, it was far ahead of the latest palm print ROI extraction algorithm and could be applied in practice. [ABSTRACT FROM AUTHOR]

With the rapid development of deep learning technology, an increasing number of people are adopting palmprint recognition algorithms based on deep learning for identity authentication. However, these algorithms are susceptible to factors such as palm placement, light source, and insufficient data sampling, resulting in poor recognition accuracy. To address these issues, this paper proposes a new end-to-end deep palmprint recognition algorithm (SSLAUL), which introduces self-supervised representation learning based on contextual prediction, utilizing unlabeled palmprint data for pre-training before introducing the trained parameters into the downstream model for fine-tuning. An uncertainty loss function is introduced into the downstream model, using the homoskedastic uncertainty as a benchmark to do adaptive weight adjustment for different loss functions dynamically. Channel and spatial attention mechanisms are also introduced to extract highly discriminative local features. In this paper, the algorithm is validated on publicly available IITD, CASIA, and PolyU palmprint datasets. The method always achieves the best recognition performance compared to other state-of-the-art algorithms. [ABSTRACT FROM AUTHOR]

This research designs a touchless fingerprint identification biometric system. This research problem stems from the user's need to change the conventional system to touchless in the hope of minimizing direct contact that can be scanned by someone who is not interested. This research aims to implement palm images in validating identity using GLCM (Gray-Level Co-occurrence Matrix) features with the K-Nearest Neighbours (K-NN) classification method in MATLAB. The identification process is divided into several stages: image acquisition, pre-processing, feature extraction with GLCM, and database matching using KNN classification. System testing uses the 10-fold cross validation method with 100 image samples (90 training images and 10 test images) that are tested in turn to calculate the average accuracy and analyze system performance. Furthermore, the test used GLCM angles (0o, 45o, 90o dan 135o) and K-NN with k values of 1, 5 and 7. The results showed the highest accuracy of 72% using an angle of 0° in GLCM and k=1 and the lowest at an angle of 90o and k=7 in K-NN. The advantage of this design is the recognition of the identity of the fingerprint owner in real time.

The palmprint recognition system has gained significant attention in security and law enforcement due to its unique features, such as principle lines, ridges, and wrinkles. However, many existing methods for extracting these features have limited accuracy, especially when the image illumination varies or the size of the processed pixels increases. Previous studies have shown that the local binary patterns (LBP) algorithm is effective for palmprint recognition due to the rich texture characteristics of a palmprint. In this paper, we propose a new technique for a robust contact-based palmprint identification system using vertical-LBP and KAZE feature detection. Our technique aims to improve recognition accuracy by using KAZE, which is a nonlinear diffusion approach that extracts nonlinear features from the evolution of the illuminance of an image. We also utilize principal component analysis (PCA) to reduce the dimensionality of the generated descriptor vector elements. The proposed method was tested on the PolyU database and achieved recognition accuracy of 99.7%. [ABSTRACT FROM AUTHOR]

Several researchers have used image enhancement methods to reduce detection errors and increase verification accuracy in palmprint identification. Divergent opinions exist among experts regarding the best method of image filtering to improve image palmprint recognition. Because of the unique characteristics of palmprints and the difficulties in preventing counterfeiting, image-filtering techniques are the subject of this current research. Researchers hope to create the best biometric system possible by utilizing various techniques. These techniques include image enhancement, Gabor orientation scales, dimension reduction techniques, and appropriate matching strategies. This study investigates how different filtering approaches might be combined to improve images. The palmprint identification system uses a 3W filter, which combines wavelet, Wiener, and weighted filters. Optimizing results entails coordinating the 3W filter with Gabor orientation scales, matching processes, and dimension reduction methods. The research shows that accuracy may be considerably increased using a 3W filter with a Gabor orientation scale of [8 x 7], the kernel principal component analysis (KPCA) dimension reduction methodology, and a cosine matching method. Specifically, a value of 99.722% can be achieved. These results highlight the importance of selecting appropriate settings and techniques for palmprint recognition systems. [ABSTRACT FROM AUTHOR]

Abstract A novel method based on the cross‐modality intersecting features of the palm‐vein and the palmprint is proposed for identity verification. Capitalising on the unique geometrical relationship between the two biometric modalities, the cross‐modality intersecting points provides a stable set of features for identity verification. To facilitate flexibility in template changes, a template transformation is proposed. While maintaining non‐invertibility, the template transformation allows transformation sizes beyond that offered by the conventional means. Extensive experiments using three public palm databases are conducted to verify the effectiveness the proposed system for identity recognition.

In response to the shortcomings of high computational cost and low accuracy of the local recognition descriptor method for palmprint images, this paper proposes a new Local Ordinal Code (LOC), which utilizes three common filters for multi-directional filtering coding. For the demand for large-scale retrieval, a new dimension control factor is proposed to perform linear feature dimensionality reduction to achieve fast matching. In addition, Feature Fusion coding schemes of LOC (FFLOC) are proposed on the basis of LOC, and the obtained feature codes are fused with different weights to achieve higher recognition accuracy. The algorithm proposed in this paper is tested in five publicly available palmprint databases and one self-collected palmprint database, and the best results are obtained on most datasets.

Nowadays, there is a growing concern about contactless palmprint recognition because of its high-recognition rate, efficiency, and convenience. With the development of image acquisition equipment, it is an often case that the palmprint images for identification and for registration are captured by different devices. At the same time, a large amount of well-labeled palmprint images are difficult to collect. Therefore, the performance of most existing contactless palmprint recognition methods will be poor in real-life applications. To address these issues, we proposed a self-attention CycleGAN for cross-domain semi-supervised palmprint recognition. Based on CycleGAN, the styles of contactless palmprint images in source domain and target domain can be swapped. Specifically, the spatial features are captured through self-attention modules by modeling long-range dependencies. In addition, an extra source domain classifier is trained with the labeled source domain images to give the unlabeled images in target domain a pseudo-label, by which images in target domain are efficiently utilized. The experiment results showed that our method achieved competitive performance. [ABSTRACT FROM AUTHOR]

The straight excitatory filters such as Gabor filters and Modified finite Radon transform can not include the vital and inherent curvature information residing in palmlines of the palmprint. Moreover, Gabor filter bank, employed in majority research work of the literature, is frequency dependent which require tuning to avoid false line representation for principle line/wrinkles. Therefore in this work to evade the false palmline assessment within the neighbourhood region and include inherent curvature attribute of the palmlines, a curvilinear anisotropic filter, ( C AGF ) is proposed and employed for palmprint representation. The proposed filter bank exploits both positive and negative concavities constituted within the palmlines. A novel representation called as the Anisotropic Differential Concavity ( A D C ) codes is obtained from difference plane obtained by subtracting curvilinear anisotropic filter responses of the palmprint sample at various orientations and for both positive and negative concavities, followed by the zero-crossings of these difference planes. Finally, it is observed that the experimental performance of the proposed representation, on standard PolyU 2D and IITD touch-less databases, outperforms several state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

Palmprint recognition (PPR) has recently garnered attention due to its robustness and accuracy. Many PPR methods rely on preprocessing the region of interest (ROI). However, the emergence of ROI attacks capable of generating synthetic ROI images poses a significant threat to PPR systems. Despite this, ROI attacks are less practical since PPR systems typically take hand images as input rather than just the ROI. Therefore, there is a pressing need for a method that specifically targets the system by composing hand images. The intuitive approach involves embedding an ROI into a hand image, a comparatively simpler process requiring less data than generating entirely synthetic images. However, embedding faces challenges, as the composited hand image must maintain a consistent color and texture. To overcome these challenges, we propose a training-free, end-to-end hand image composition method incorporating ROI harmonization and palm blending. The ROI harmonization process iteratively adjusts the ROI to seamlessly integrate with the hand using a modified style transfer method. Simultaneously, palm blending employs a pretrained inpainting model to composite a hand image with a continuous transition. Our results demonstrate that the proposed method achieves a high attack performance on the IITD and Tongji datasets, with the composited hand images exhibiting realistic visual quality. [ABSTRACT FROM AUTHOR]

A novel method based on the cross‐modality intersecting features of the palm‐vein and the palmprint is proposed for identity verification. Capitalising on the unique geometrical relationship between the two biometric modalities, the cross‐modality intersecting points provides a stable set of features for identity verification. To facilitate flexibility in template changes, a template transformation is proposed. While maintaining non‐invertibility, the template transformation allows transformation sizes beyond that offered by the conventional means. Extensive experiments using three public palm databases are conducted to verify the effectiveness the proposed system for identity recognition. [ABSTRACT FROM AUTHOR]

This paper suggests novel cancellable biometric realization approach recognition and template protection. In this paper, the Homomorphic Filtering Masking (HFM) encoding algorithm is utilized for cancelable palmprint recognition system. In the suggested technique, the Discreet Wavelet Transform (DWT) algorithm is applied on the palmprint. Then the DWT divides the image into four sub images. The resultant map is encrypted with the HFM algorithm, in order to the second HFM utilized in produced from the palmprint. This approach can be used to develop a frequency domain procedure for making this system for biometric template protection. The obtained results prove that the suggested technique is the best from the other algorithms. [ABSTRACT FROM AUTHOR]

This paper presents a comprehensive survey examining the prevailing feature extraction methodologies employed within biometric palmprint recognition models. It encompasses a critical analysis of extant datasets and a comparative study of algorithmic approaches. Specifically, this review delves into palmprint recognition systems, focusing on different feature extraction methodologies. As the dataset wields a profound impact within palmprint recognition, our study meticulously describes 20 extensively employed and recognized palmprint datasets. Furthermore, we classify these datasets into two distinct classes: contact-based datasets and contactless-based datasets. Additionally, we propose a novel taxonomy to categorize palmprint recognition feature extraction approaches into line-based approaches, texture descriptor-based approaches, subspace learning-based methods, local direction encoding-based approaches, and deep learning-based architecture approaches. Within each class, most foundational publications are reviewed, highlighting their core contributions, the datasets utilized, efficiency assessment metrics, and the best outcomes achieved. Finally, open challenges and emerging trends that deserve further attention are elucidated to push progress in future research. [ABSTRACT FROM AUTHOR]

Deep learning techniques have proven to be effective in solving the facial emotion recognition (FER) problem. However, it demands a significant amount of supervision data which is often unavailable due to privacy and ethical concerns. In this paper, we present a novel approach for addressing the FER problem using multi-source transfer learning. The proposed method leverages the knowledge from multiple data sources of similar domains to inform the model on a related task. The approach involves the optimization of aggregate multivariate correlation among the source tasks trained on the source dataset, thus controlling the transfer of information to the target task. The hypothesis is validated on benchmark datasets for facial emotion recognition and image classification tasks, and the results demonstrate the effectiveness of the proposed method in capturing the group correlation among features, as well as being robust to negative transfer and performing well in few-shot multi-source adaptation. With respect to the state-of-the-art methods MCW and DECISION, our approach shows an improvement of 7% and ∼ 15% respectively. [ABSTRACT FROM AUTHOR]

Multispectral and hyperspectral image fusion (MHF) aims to reconstruct high-resolution hyperspectral images by fusing spatial and spectral information. Unlike the traditional canonical polyadic decomposition and Tucker decomposition models, the block-term tensor decomposition model is able to improve the quality of fused images using known endmember and abundance information. This paper presents an improved hyperspectral image fusion algorithm. Firstly, the two abundance matrices are combined into a single bulk matrix to promote structural sparsity by introducing the L 2 , 1 -norm to eliminate the scaling effects present in the model. Secondly, the counter-scaling effect is eliminated by adding the L 2 -norm to the endmember matrix. Finally, the chunk matrix and the endmember matrix are coupled together, and the matrix is reorganized by adding the L 2 , 1 -norm to the matrix to facilitate chunk elimination and solved using an extended iterative reweighted least squares (IRLS) method, focusing on the problem of the inability to accurately estimate the tensor rank in the chunk-term tensor decomposition model and the noise/artifact problem arising from overestimation of rank. Experiments are conducted on standard and local datasets, and the fusion results are compared and analyzed in four ways: visual result analysis, metric evaluation, time of the algorithm, and classification results, and the experimental results show that the performance of the proposed method is better than the existing methods. An extensive performance evaluation of the algorithms is performed by conducting experiments on different datasets. The experimental results show that the proposed algorithm achieves significant improvements in terms of reconstruction error, signal-to-noise ratio, and image quality compared with the existing methods. Especially in the case of a low signal-to-noise ratio, the proposed algorithm shows stronger robustness and accuracy. These results show that the proposed algorithm has significant advantages in dealing with multispectral high-resolution hyperspectral data. [ABSTRACT FROM AUTHOR]

Palmprint biometrics has a broad application prospect owing to non-intrusiveness, ease of image acquisition and stable textural pattern. Hand-crafted approaches are vulnerable to non-ideal palmprint images caused by uneven illumination, motion blur and noise contamination. Many researchers have designed excellent texture descriptors or/and advanced image pre-processing algorithms. Nevertheless, they are highly targeted at some specific data, less adaptable to the emerging data. In this paper, a semi-pretrained contactless palmprint recognition deep network is developed to achieve high accuracy and robustness. Semi-CPRN is composed of underlying network structure from ResNet-152 and the proposed assistant layers dedicated to high-performance palmprint recognition. The well-designed assistant layers enhance convolutional neural network to steadily extract the real palmprint features even from the degraded images without being deceived by the degradation factors. Besides, to better carry out the research on palmprint recognition in the open environment, we established a new contactless database HIT-NIST-V1 under natural scene. The comparative experiments on CASIA, IITD, PolyU3D/2D, Tongji and HIT-NIST-V1 illustrate that Semi-CPRN is comparable and superior to previously published state-of-the-art approaches. Simultaneously, CNN-based palmprint biometrics methods show significant robustness to motion blur, Gaussian noise, and salt and pepper noise. [ABSTRACT FROM AUTHOR]

Simple Summary: The red palm weevil is an exotic and highly endangered pest that is extremely harmful to palm plants. In order to effectively control this pest, we propose an algorithm to automatically detect and count adult red palm weevils in traps. Previously, the trapping and counting of adult red palm weevils was done manually. The population density and damage level were then inferred from the number of adults trapped to guide control efforts. However, the efficiency of this method is very low. The algorithm proposed in this paper solves the drawbacks of manual counting, and the recognition accuracy reaches 93.8%, which also improves the efficiency of agricultural monitoring. The red palm weevil (RPW, Rhynchophorus ferrugineus) is an invasive and highly destructive pest that poses a serious threat to palm plants. To improve the efficiency of adult RPWs' management, an enhanced YOLOv5 object detection algorithm based on an attention mechanism is proposed in this paper. Firstly, the detection capabilities for small targets are enhanced by adding a convolutional layer to the backbone network of YOLOv5 and forming a quadruple down-sampling layer by splicing and down-sampling the convolutional layers. Secondly, the Squeeze-and-Excitation (SE) attention mechanism and Convolutional Block Attention Module (CBAM) attention mechanism are inserted directly before the SPPF structure to improve the feature extraction capability of the model for targets. Then, 2600 images of RPWs in different scenes and forms are collected and organized for data support. These images are divided into a training set, validation set and test set following a ratio of 7:2:1. Finally, an experiment is conducted, demonstrating that the enhanced YOLOv5 algorithm achieves an average precision of 90.1% (mAP@0.5) and a precision of 93.8% (P), which is a significant improvement compared with related models. In conclusion, the enhanced model brings a higher detection accuracy and real-time performance to the RPW-controlled pest pre-detection system, which helps us to take timely preventive and control measures to avoid serious pest infestation. It also provides scalability for other pest pre-detection systems; with the corresponding dataset and training, the algorithm can be adapted to the detection tasks of other pests, which in turn brings a wider range of applications in the field of monitoring and control of agricultural pests. [ABSTRACT FROM AUTHOR]

• Propose a crossing palmprint to palmvein recognition method. • Propose a multi-layer feature learning to minimize the heterogeneous image gap. • Exploits the discriminative and common features from heterogeneous palm images. • Experimental results show the promising effectiveness of the proposed method. Palmprint has shown promising potential for biometrics recognition due to its excellent contactless and hygienic properties. However, most existing methods focus only on feature learning of unimodal palmprint images leading to the challenge of palmprint recognition crossing different modalities. In this paper, we propose a modality-invariant binary features learning (MIBFL) method for crossing palmprint to palm-vein recognition, where palm images are captured under visible and invisible near-infrared illumination, respectively. We first map the multiple modal palm images into their high-dimensional alignment representation to reduce the impact of misalignment and noise between different image modalities. Then, we simultaneously learn the discriminative features from different modalities of alignment images via matrix factorization by enforcing the orthogonal and balanced constraints. Lastly, we jointly learn a pair of encoding functions to project multi-modal palm features into the common binary feature descriptor for crossing palmprint to palm-vein recognition. Experimental results on the widely used PolyU multi-spectral palmprint database are presented to demonstrate the effectiveness of the proposed MIBFL method. [ABSTRACT FROM AUTHOR]

Palmprint identification has been conducted over the last two decades in many biometric systems. High-dimensional data with many uncorrelated and duplicated features remains difficult due to several computational complexity issues. This paper presents an interactive authentication approach based on deep learning and feature selection that supports Palmprint authentication. The proposed model has two stages of learning; the first stage is to transfer pre-trained VGG-16 of ImageNet to specific features based on the extraction model. The second stage involves the VGG-16 Palmprint feature extraction in the Siamese network to learn Palmprint similarity. The proposed model achieves robust and reliable end-to-end Palmprint authentication by extracting the convolutional features using VGG-16 Palmprint and the similarity of two input Palmprint using the Siamese network. The second stage uses the CASIA dataset to train and test the Siamese network. The suggested model outperforms comparable studies based on the deep learning approach achieving accuracy and EER of 91.8% and 0.082%, respectively, on the CASIA left-hand images and accuracy and EER of 91.7% and 0.084, respectively, on the CASIA right-hand images. [ABSTRACT FROM AUTHOR]

In the past few years, deep learning-based models have been very successful in achieving state-of-the-art results in many tasks in computer vision, speech recognition, and natural language processing. These models seem to be a natural fit for handling the ever-increasing scale of biometric recognition problems, from cellphone authentication to airport security systems. Deep learning-based models have increasingly been leveraged to improve the accuracy of different biometric recognition systems in recent years. In this work, we provide a comprehensive survey of more than 150 promising works on biometric recognition (including face, fingerprint, iris, palmprint, ear, voice, signature, and gait recognition), which deploy deep learning models, and show their strengths and potentials in different applications. For each biometric, we first introduce the available datasets that are widely used in the literature and their characteristics. We will then talk about several promising deep learning works developed for that biometric, and show their performance on popular public benchmarks. We will also discuss some of the main challenges while using these models for biometric recognition, and possible future directions to which research in this area is headed. [ABSTRACT FROM AUTHOR]

An arc fault is the leading cause of electrical fire. Aiming at the problems of difficulty in manually extracting features, poor generalization ability of models and low prediction accuracy in traditional arc fault detection algorithms, this paper proposes a fault arc detection method based on the fusion of channel attention mechanism and residual network model. This method is based on the channel attention mechanism to perform global average pooling of information from each channel of the feature map assigned by the residual block while ignoring the local spatial data to enhance the detection and recognition rate of the fault arc. This paper introduces a one-dimensional depth separable convolution (1D-DS) module to reduce the network model parameters and shorten the time of single prediction samples. The experimental results show that the F1 score of the network model for arc fault detection under mixed load conditions is 98.07%, and the parameter amount is reduced by 46.06%. The method proposed in this paper dramatically reduces the parameter quantity, floating-point number and time complexity of the network structure while ensuring a high recognition rate, which improves the real-time response ability to detect arc fault. It has a guiding significance for applying arc fault on the edge side. [ABSTRACT FROM AUTHOR]

In this research, a Deep Supervised Lacunarity Analysis Model based on the Weight Adaptive Local Binary Pattern Texture for Palmprint Recognition (DSLPR) system is proposed for evolving the innovative Palmprint Recognition System (PRS). To reveal the originality of DSLPR system, a new Section-based Contour Lacunarity Analysis based on Weight Adaptive Local Binary Pattern (SCLA-WALBP) feature extraction approach and a Deep Learning Network classifier using a Supervised Algorithm (DLNSANet) are implemented to gain the superior substantiation accuracy rate for accessing the digital content and highly worthy assets. To accomplish the DSLPR system, Two Dimensional Palmprint Region of Interest (2D-PROI) image is preprocessed (PI), spotted out all tiny edges, ridges, and wrinkles of PI using Weight Adaptive Local Binary Pattern (WALBP) algorithm, and traced all outlines of the PI using a canny edge detection algorithm. SCLA-WALBP approach is invoked to produce an exclusive feature vector. Classify this feature vector using DLNSANet classifier approach to substantiate the authentic person with more accuracy rate. This research work experiment is employed on PolyU's multispectral 2D-PROI image database. This DSLPR system has been appraised with 99% of authentication accuracy. [ABSTRACT FROM AUTHOR]

【Objective】Cage biometrics and statistics are one of the key reference factors for marine pasture farming management. Aiming at the interference of reverberation noise and complex background, this paper constructs fish detection data sets under different lighting conditions, and uses forward-looking sonar imaging technology to propose a fish recognition lightweight model based on YOLOV5-MobilenetV3 and sonar images (LAPR-Net) to realize fish recognition in water cages in turbid or dark scenes.【Method】Taking tilapia as the research object, based on the frame structure of the YOLOV5 model, the backbone network module ado pts the lightweight Mob ileNetV3 bneck block, using the linear bottleneck inverse residual structure and depth separable convolution extract the features of fish in sonar images, applying the attention mechanism SE-Net to obtain multi-scale semantic features of sonar images and enhance the correlation between features; the neck network adopts the path aggregation network structure to perform multi-scale fusion of target features, to enhance the feature fusion ability; the prediction part adopts the maximum local search based on the non-maximum suppression method, removes the redundant detection frame, screens the detection frame with the highest confidence, and finally outputs and displays the detection result of the fish, including the position, category and detection probability of detecting an object.【Result】Four other mainstream detection models were selected for comparative experiments, including YOLOV3-ting (Darknet53), YOLOV5 (CSPdarknet53), YOLOV5 (Repvgg), and YOLOV5s (Transformer). It proposes the model parameter quantityof 3 545 453, FLOPs of 6.3 G, and the mAP of 0.957, and the average inference speed of each picture of the model is 0.08868 s. Compared with the YOLOV5 model, the mAP of the improved model has increased by 9.7%.【Conclusion】The proposed network improves the speed of training and recognition, reduces the requirements for hardware equipment, and provides a reference for the detection model of cage cultured fish in marine pastures. [ABSTRACT FROM AUTHOR]

Unconstrained Palmprint Recognition (UPR) shows engaging potential owing to its high hygiene and privacy. The unconstrained acquisition usually produces wide variations, against which deep methods resort to large samples that are unavailable in practice, however. We focus on Few-Shot UPR (FS-UPR), a more general problem, recognizing query samples given a few support samples per class. Because scarce samples insufficiently represent potential variations, the augmentation methods train independent hallucinators on large samples to generate more ones. Whereas, the hallucinators trained independently of Few-Shot Learning (FSL) are blind of generating promising samples to boost the downstream FSL. Moreover, training hallucinators requires large samples per class, unavailable from unconstrained palmprint databases. We aim to address FS-UPR via contrastive augmentation merely on the support samples. Observing the variations to be transferable across samples, we exploit low-rank representation to disentangle support samples into principles and variations in embedding space and augment features by variation transfer. To this end, we devise an end-to-end Deep Low-Rank Representation Feature Augmentation Network (DLRR-FAN) to simultaneously learn the embedding space and augmentation features with guaranteed reality and diversity. Furthermore, a Contrastive Recognition Regularizer (CRR) is tailored to secure the discriminability of augmentation features. During each training episode, the task motivates DLRR-FAN to augment such features that correct the biased prototypes towards upcoming query samples with variations unseen in the support samples, namely task-driven prototype correction. Extensive experiments on both the typical and extended FS-UPR tasks demonstrate the efficacy of DLRR-FAN versus the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Palmprint has gained popularity as a biometric modality and has recently attracted significant research interest. The competition-based method is the prevailing approach for hand-crafted palmprint recognition, thanks to its powerful discriminative ability to identify distinctive features. However, the competition mechanism possesses vast untapped advantages that have yet to be fully explored. In this paper, we reformulate the traditional competition mechanism and propose a $\boldsymbol {C}$ omprehensive $\boldsymbol {C}$ ompetition Network (CCNet). The traditional competition mechanism focuses solely on selecting the winner of different channels without considering the spatial information of the features. Our approach considers the spatial competition relationships between features while utilizing channel competition features to extract a more comprehensive set of competitive features. Moreover, existing methods for palmprint recognition typically focus on first-order texture features without utilizing the higher-order texture feature information. Our approach integrates the competition process with multi-order texture features to overcome this limitation. CCNet incorporates spatial and channel competition mechanisms into multi-order texture features to enhance recognition accuracy, enabling it to capture and utilize palmprint information in an end-to-end manner efficiently. Extensive experimental results have shown that CCNet can achieve remarkable performance on four public datasets, showing that CCNet is a promising approach for palmprint recognition that can achieve state-of-the-art performance. Related codes will be released at https://github.com/Zi-YuanYang/CCNet. [ABSTRACT FROM AUTHOR]

Unsupervised discretization is a crucial step in many knowledge discovery tasks. The state-of-the-art method for one-dimensional data infers locally adaptive histograms using the minimum description length (MDL) principle, but the multi-dimensional case is far less studied: current methods consider the dimensions one at a time (if not independently), which result in discretizations based on rectangular cells of adaptive size. Unfortunately, this approach is unable to adequately characterize dependencies among dimensions and/or results in discretizations consisting of more cells (or bins) than is desirable. To address this problem, we propose an expressive model class that allows for far more flexible partitions of two-dimensional data. We extend the state of the art for the one-dimensional case to obtain a model selection problem based on the normalized maximum likelihood, a form of refined MDL. As the flexibility of our model class comes at the cost of a vast search space, we introduce a heuristic algorithm, named PALM, which partitions each dimension alternately and then merges neighboring regions, all using the MDL principle. Experiments on synthetic data show that PALM (1) accurately reveals ground truth partitions that are within the model class (i.e., the search space), given a large enough sample size; (2) approximates well a wide range of partitions outside the model class; (3) converges, in contrast to the state-of-the-art multivariate discretization method IPD. Finally, we apply our algorithm to three spatial datasets, and we demonstrate that, compared to kernel density estimation (KDE), our algorithm not only reveals more detailed density changes, but also fits unseen data better, as measured by the log-likelihood. [ABSTRACT FROM AUTHOR]

Direct usage of original biometric features/templates definitely leads to serious privacy leakage. In biometric cryptosystems, a biometric key is generated and then strictly protected with a one-way function. However, it is highly difficult to balance the template size and accuracy. Palmprint has many remarkable strengths, so it is considered as a promising biometric modality. In our previous work, deep hashing network (DHN) was leveraged to extract discriminative deep hashing code (DHC) of palmprint. In this paper, a palmprint fuzzy commitment (FC) is proposed based on DHC. A palmprint FC is proposed based on DHC. The DHC has high accuracy, small size, strong robustness, and is free from shift-matching for dislocation problems, so the proposed palmprint FC can satisfactorily balance the accuracy, storage cost and computational complexity. In addition, the DHCs of multi-spectral palmprints are concatenated and the bits are selected according to discrimination power analysis, so the accuracy is further improved. The sufficient experimental results show that, when B, N and R spectrums are fused and only 292 bits are selected, EER can be 0.0001%. [ABSTRACT FROM AUTHOR]

Palmprint recognition (PPR) has recently garnered attention due to its robustness and accuracy. Many PPR methods rely on preprocessing the region of interest (ROI). However, the emergence of ROI attacks capable of generating synthetic ROI images poses a significant threat to PPR systems. Despite this, ROI attacks are less practical since PPR systems typically take hand images as input rather than just the ROI. Therefore, there is a pressing need for a method that specifically targets the system by composing hand images. The intuitive approach involves embedding an ROI into a hand image, a comparatively simpler process requiring less data than generating entirely synthetic images. However, embedding faces challenges, as the composited hand image must maintain a consistent color and texture. To overcome these challenges, we propose a training-free, end-to-end hand image composition method incorporating ROI harmonization and palm blending. The ROI harmonization process iteratively adjusts the ROI to seamlessly integrate with the hand using a modified style transfer method. Simultaneously, palm blending employs a pretrained inpainting model to composite a hand image with a continuous transition. Our results demonstrate that the proposed method achieves a high attack performance on the IITD and Tongji datasets, with the composited hand images exhibiting realistic visual quality.

Palmprint is deemed as one of the most important biometric modalities. Many coding-based palmprint recognition methods have achieved satisfactory recognition performance, which can be free from training and require low storage cost and computational complexity. Downsampling is typically used to improve real-time ability, reduce the storage cost and improve the discriminative ability. Unfortunately, downsampling was not fully considered and studied. In this paper, we propose downsampling in uniformly-spaced windows (DUSW) and conduct it on two state-of-the-art downsampling methods as their reformative versions, dubbed uniformly-spaced extreme downsampling method (U-EDM) and uniformly-spaced democratic voting downsampling method (U-DVDM). In DUSW, the upper-left four pixels rather than all pixels in each block are selected to jointly decide the winner whose value is used as the representative feature of this block. DUSW overcomes the dictatorship of a single pixel and simultaneously ensures the sufficient spatial distance between the adjacent winners. Thus, DUSW reduces the correlation between the adjacent winners, and accordingly improves the discrimination and robustness. Meanwhile, the computational complexity is only 1/4 of the original downsampling methods for the representative reduction. The sufficient experiments demonstrate that DUSW can be easily embedded into the existing downsampling methods of coding-based palmprint recognition and improve their recognition performances. [ABSTRACT FROM AUTHOR]

Palmprint shows great potential in biometric-based security due to its advantages of great stability, easy collection, and high accuracy. However, with insufficient training samples, how to extract discriminative features applicable in various scenarios is still challenging. This paper proposes a general palmprint recognition framework. First, based on the integrated Gabor filter (IGF), a multi-scale integrated Gabor convolutional network (MS-IGCN) with large and small receptive fields is built. Compared with the existing DCNN, MS-IGCN applies fewer trainable parameters to targetable grasp principle lines and wrinkles features. Notably, our constructed IGF in MS-IGCN completes the feature extraction. The fixed Gabor filters in IGF extract spatial features of different orientations, and the learnable filters learn complementary features that cannot be extracted by the fixed Gabor filters. Then, the multi-scale discriminant representation (MSDR) of palmprint is learned through MS-IGCN. Finally, to make MSDR flexibly applicable to various scenarios, the ProCRC is implemented. A large number of experiments on public databases are conducted. The experimental results show that compared with various advanced palmprint recognition methods, MSDR has the best recognition effect. In addition, we complete the palmprint collection in an unconstrained environment and established an unconstrained palmprint dataset. The experimental results on the unconstrained palmprint dataset fully demonstrate that MSDR maintains the best performance in practical applications. [ABSTRACT FROM AUTHOR]

As a type of biometric recognition, palmprint recognition uses unique discriminative features on the palm of a person to identify his/her identity. It has attracted much attention because of its advantages of contactlessness, stability, and security. Recently, many palmprint recognition methods based on convolutional neural networks (CNN) have been proposed in academia. Convolutional neural networks are limited by the size of the convolutional kernel and lack the ability to extract global information of palmprints. This paper proposes a framework based on the integration of CNN and Transformer-GLGAnet for palmprint recognition, which can take advantage of CNN’s local information extraction and Transformer’s global modeling capabilities. A gating mechanism and an adaptive feature fusion module are also designed for palmprint feature extraction. The gating mechanism filters features by a feature selection algorithm and the adaptive feature fusion module fuses them with the features extracted by the backbone network. Through extensive experiments on two datasets, the experimental results show that the recognition accuracy is 98.5% for 12,000 palmprints in the Tongji University dataset and 99.5% for 600 palmprints in the Hong Kong Polytechnic University dataset. This demonstrates that the proposed method outperforms existing methods in the correctness of both palmprint recognition task. [ABSTRACT FROM AUTHOR]

As a discriminative biometric modality, palmprint accommodates two attributes of soft biometrics, namely chirality and gender. Our study reveals that the false matching of a pair of palmprint templates from two identities could be possible if their representations are mirror-insensitive or gender-insensitive, despite the palmprint images have significant distinctive appearances. This could seriously impair the accuracy performance of the palmprint recognition systems. As a remedy, the useful knowledge learned from the classification of soft palmprint attributes, namely chirality and gender, is transferred to palmprint recognition, which improves the accuracy of palmprint-based identity recognition. To be specific, this paper pre-trains a shared-weight multi-task network with soft palmprint attributes under transfer learning paradigm. The pre-trained network is then transferred to the down-stream identity recognition task. Several shared-weight architectures are explored and examined to determine the suitable model. Extensive experiments demonstrate that the proposed method can effectively avoid the false matching between the templates of different chiralities / genders. The proposed method can be applied to other biometric modalities, where their associated soft biometrics can be exploited for performance gain. The related codes will be released as soon as possible if the paper is accepted. The link is https://github.com/1119231393/Multi-task-Pre-training-with-Soft-Biometrics-for-Transfer-learning-Palmprint-Recognition. [ABSTRACT FROM AUTHOR]

Palm vein recognition has received some considerable attention regarding its use in biometric identification. Palm vein characteristics offer a superior level of security and reliability in personal identification compared to extrinsic methods such as fingerprint, face, and palm print recognition, as vein patterns are difficult to duplicate and do not change throughout one's lifetime. This study proposes both segmentation and recognition methods to enhance the authentication performance and achieve correct identification using palm vein features. First, we propose a segmentation model based on the U-Net model, enhanced with an attention gate, to effectively segment palm vein patterns. The incorporation of both the attention gate and residual block allows the segmentation model for the learning of the essential features required for specific segmentation tasks. The Hessian-based Jerman filtering method is used for ground-truth labeling. The segmentation model extracts the palm vein patterns and filters out the irrelevant and noisy pixels for the purpose of recognition. The efficient channel attention residual network is trained to learn discriminative features for personal identification using combined margin-based loss functions for palm vein recognition. The channel attention module enhances the useful information and suppresses irrelevant features in the feature maps, which overcomes the problem of rotation, position translation, and scale transformation, as well as improves the recognition rate. The combined loss function used in this study increases the similarity between the intra-class samples and the diversity between inter-class samples. The proposed recognition model achieved 100% accuracy for palm vein recognition and an equal error rate of 0.018 for palm vein verification. [ABSTRACT FROM AUTHOR]

The outputs of deep hash network (DHN) are binary codes, so DHN has high retrieval efficiency in matching phase and can be used for high-speed palmprint recognition, which is a promising biometric modality. In this paper, the templates and network parameters are both quantized for fast and light-weight palmprint recognition. The parameters of DHN are binarized to compress the network weight and accelerate the speed. To avoid accuracy degradation caused by quantization, mutual information is leveraged to optimize the ambiguity in Hamming space to obtain a tri-valued hash code as a palmprint template. Kleene Logic's tri-valued Hamming distance measures the dissimilarity between palmprint templates. The ablation experiments are tested on the binarization of the network parameter, and the normalization and trivialization of the deep hash output value. The sufficient experiments conducted on several contact and contactless palmprint datasets confirm the multiple advantages of our method. [ABSTRACT FROM AUTHOR]

Aiming at the problems of long detection time and low detection accuracy in the existing coal gangue recognition, this paper proposes a method to collect the multispectral images of coal gangue using spectral technology and match with the improved YOLOv5s (You Only Look Once Version-5s) neural network model to apply it to coal gangue target recognition and detection, which can effectively reduce the detection time and improve the detection accuracy and recognition effect of coal gangue. In order to take the coverage area, center point distance and aspect ratio into account at the same time, the improved YOLOv5s neural network replaces the original GIou Loss loss function with CIou Loss loss function. At the same time, DIou NMS replaces the original NMS, which can effectively detect overlapping targets and small targets. In the experiment, 490 sets of multispectral data were obtained through the multispectral data acquisition system. Using the random forest algorithm and the correlation analysis of bands, the spectral images of the sixth, twelfth and eighteenth bands from twenty-five bands were selected to form a pseudo RGB image. A total of 974 original sample images of coal and gangue were obtained. Through two image noise reduction methods, namely, Gaussian filtering algorithm and non-local average noise reduction, 1948 images of coal gangue were obtained after preprocessing the dataset. This was divided into a training set and test set according to an 8:2 ratio and trained in the original YOLOv5s neural network, improved YOLOv5s neural network and SSD neural network. By identifying and detecting the three neural network models obtained after training, the results can be obtained, the loss value of the improved YOLOv5s neural network model is smaller than the original YOLOv5s neural network and SSD neural network, the recall rate is closer to 1 than the original YOLOv5s neural network and SSD neural network, the detection time is the shortest, the recall rate is 100% and the average detection accuracy of coal and gangue is the highest. The average precision of the training set is increased to 0.995, which shows that the improved YOLOv5s neural network has a better effect on the detection and recognition of coal gangue. The detection accuracy of the improved YOLOv5s neural network model test set is increased from 0.73 to 0.98, and all overlapping targets can also be accurately detected without false detection or missed detection. At the same time, the size of the improved YOLOv5s neural network model after training is reduced by 0.8 MB, which is conducive to hardware transplantation. [ABSTRACT FROM AUTHOR]

Terrestrial hyperspectral light detection and ranging (LiDAR) (HSL), as one novel LiDAR system integrated with more wavelengths, has supplied enhanced possibilities in many fields by delivering the geographic coordinate and the hyperspectral backscattered intensity simultaneously. However, like the traditional single-wavelength LiDAR, it is faced with the distance effect, which restricts the accurate acquisition of the hyperspectral intensities and the quantitative retrieval of characteristics of the targets. The previously reported distance effect correction models mainly concentrated on the distance effect correction for the single-wavelength LiDAR system, and some normalization methods with the standard reflectance panel were also provided to calibrate the data measured by multispectral LiDAR and HSL, producing the reflectance-related value. Nevertheless, it is valuable to systematically explore the distance effect of HSL over long distances and search for the corresponding correction methods. Along these lines, in this study, the homogeneous targets and standard reflectance panels with different reflectance values were employed to participate in the distance experiment to systematically explore and analyze the distance effect phenomenon on terrestrial HSL data. A novel practical piecewise fitting model was proposed to output realistic correction results and it was also compared with the classic inverse distance square law and polynomial fitting model. To further demonstrate the feasibility and good capability, the models were employed in the intensity correction for the various vegetation leaf species. A simple 3-D scene experiment was then carried out to demonstrate the intensity variation before and after the implementation of the distance effect correction. From the acquired result, it suggests that (1) the distance effect on terrestrial HSL data is not related to the wavelength and the scanned target. All the wavelengths share a common distance effect; (2) the concept of the 'distance effect function' could represent well the distance effect for the terrestrial HSL; (3) as far as the correction ability is concerned, the proposed piecewise fitting model achieved better performance than the others because it exhibited the smallest standard deviation (σ), coefficient of variation (CV), and the ratio of the coefficient of variation (ε) for the correction results of the homogeneous targets, and the leaf experiments confirmed it again; and (4) the further 3-D experiment result exhibited the intensity variation. It proves that the distance effect does exist in the 3-D scanning results and the correction is necessary. Besides, for small-scanned scenes, the incidence angle effect dominates and largely affects the intensity data instead of the distance effect. This study enriches the study of the distance effect mechanism on the terrestrial HSL data, which facilitates the development of research on the radiative effect correction of the HSL. At the same time, the proposed model can be adopted for the analysis and correction of the distance effect on terrestrial HSL data in actual scanning tasks. [ABSTRACT FROM AUTHOR]