David Zhang

Verified

David verified their affiliation via an institutional email.

Learn more

Verified

David verified their affiliation via an institutional email.

Learn more

• Doctor of Engineering
• Professor (Assistant) at Kennesaw State University

Touchless palm recognition is increasingly popular for its effectiveness, privacy, and hygiene benefits in biometric systems. However, several challenges remain, including significant performance degradation caused by variations in palm positioning and capture distance. To address these issues, this paper introduces a comprehensive sensing system t...

Palm recognition facilitates various real-world applications such as security access control and identity verification. The contactless method of acquiring palm images significantly reduces the risk of bacterial transmission and enhances user-friendliness. However, this approach also presents inherent difficulties and challenges. Accurately identif...

Multilabel learning deals with datasets where each sample is associated with multiple labels. It is commonly assumed that label correlations should be well exploited to build an effective multilabel classifier. Moreover, the class imbalance problem occurs in many multilabel datasets and should be tackled to reduce the classification bias. While man...

Semi-supervised learning suffers from the imbalance of labeled and unlabeled training data in the video surveillance scenario. In this paper, we propose a new semi-supervised learning method called SIAVC for industrial accident video classification. Specifically, we design a video augmentation module called the Super Augmentation Block (SAB). SAB a...

Real-world datasets are often imbalanced, posing frequent challenges to canonical machine learning algorithms that assume a balanced class distribution. Moreover, the imbalance problem becomes more complicated when the dataset is multiclass. Although many approaches have been presented for imbalanced learning (IL), research on the multiclass imbala...

Semi-supervised learning suffers from the imbalance of labeled and unlabeled training data in the video surveillance scenario. In this paper, we propose a new semi-supervised learning method called SIAVC for industrial accident video classification. Specifically, we design a video augmentation module called the Super Augmentation Block (SAB). SAB a...

Anomaly detection has been widely explored by training an out-of-distribution detector with only normal data for medical images. However, detecting local and subtle irregularities without prior knowledge of anomaly types brings challenges for lung CT-scan image anomaly detection. In this paper, we propose a self-supervised framework for learning re...

Facial beauty analysis is an important topic in human society. It may be used as a guidance for face beautification applications such as cosmetic surgery. Deep neural networks (DNNs) have recently been adopted for facial beauty analysis and have achieved remarkable performance. However, most existing DNN‐based models regard facial beauty analysis a...

Tongue images have been proved to be effective in diabetes mellitus (DM) diagnosis. Without requirement of collecting blood sample, tongue image based diagnosis approach is non-invasive and convenient for the patients. Meanwhile, the colors of tongues play an important in aiding accurate diagnosis. However, the tongues' colors fall on a small color...

Domain generalizable person re-identification (DG ReID) is a challenging problem, because the trained model is often not generalizable to unseen target domains with different distribution from the source training domains. Data augmentation has been verified to be beneficial for better exploiting the source data to improve the model generalization....

Recently, the cross-domain object detection task has been raised by reducing the domain disparity and learning domain invariant features. Inspired by the image-level discrepancy dominated in object detection, we introduce a Multi-Adversarial Faster-RCNN (MAF). Our proposed MAF has two distinct contributions: (1) The Hierarchical Domain Feature Alig...

Convolutional neural networks (CNNs) have obtained remarkable performance via deep architectures. However, these CNNs often achieve poor robustness for image super-resolution (SR) under complex scenes. In this paper, we present a heterogeneous group SR CNN (HGSRCNN) via leveraging structure information of different types to obtain a high-quality im...

Deep convolutional neural networks (CNNs) are used for image denoising via automatically mining accurate structure information. However, most of existing CNNs depend on enlarging depth of designed networks to obtain better denoising performance, which may cause training difficulty. In this paper, we propose a multi-stage image denoising CNN with th...

Deep convolutional neural networks (CNNs) are used for image denoising via automatically mining accurate structure information. However, most of existing CNNs depend on enlarging depth of designed networks to obtain better denoising performance, which may cause training difficulty. In this paper, we propose a multi-stage image denoising CNN with th...

Computational pulse diagnosis is a convenient, non-invasive, and effective Diabetes Mellitus (DM) detection technique. Generally, diverse pulse features are extracted from different views to represent pulse signals and then used for achieving the pulse diagnosis. However, current pulse-based DM detection methods only used one pulse feature for dete...

A single infrared image or visible image cannot clearly present texture details and infrared information of the scene in poor illumination, bad weather, or other complex conditions. Thus, it is necessary to fuse the infrared and visible images into one image. In this paper, we propose a novel deep fusion architecture for fusing visible and infrared...

Deep learning methods have been successfully applied to audio super-resolution tasks. Although deep learning methods produce good performance, they are not practical for the real-world applications due to the large member of computations. To address this problem, we propose a Recursive Feature Diversity Networks (RFD-Nets), which is a lightweight m...

Weakly supervised object detection (WSOD) has become an effective paradigm, which requires only class labels to train object detectors. However, WSOD detectors are prone to learn highly discriminative features corresponding to local objects rather than complete objects, resulting in imprecise object localization. To address the issue, designing bac...

Video anomaly detection (VAD) refers to the discrimination of unexpected events in videos. The deep generative model (DGM)-based method learns the regular patterns on normal videos and expects the learned model to yield larger generative errors for abnormal frames. However, DGM cannot always do so, since it usually captures the shared patterns betw...

Background and objective: In traditional Chinese medicine and Ayurvedic medicine, wrist pulse wave fluctuations are an important indicator for distinguishing different health states. Owing to the development of modern sensing technology, computational methods have been used in the analysis of pulse wave signals. The description and quantification o...

Pulse diagnosis (PD) plays an indispensable role in healthcare in China, India, Korea, and other Orient countries. It requires considerable training and experience to master. The results of pulse diagnosis rely heavily on the practitioner's subjective analysis, which means that the results from different physicians may be inconsistent. To overcome...

Machine learning offers automatic and objective approaches for disease detection based on biomedical data. However, 1) the percentage of patients in the real world is smaller than that of healthy people; 2) the annotations by medical experts are costly. Therefore, medical datasets are often imbalanced and partially labeled. To address this problem,...

Objects often have different appearances because of viewpoint changes or part deformation. How to reasonably model these variations is still a big challenge for object detection. In this paper, we propose a novel Deformable Template Network (DTN), which exploits the pictorial structure to model possible variations of an object. DTN represents an ob...

Employing partition strategy to explore fine-grained features has been verified to be beneficial for person re-identification in recent literature. However, existing methods primarily rely on expert experience to manually design various partition strategies, which may lead to a sub-optimal solution for fine-grained features exploration. In this pap...

Weakly supervised object detection (WSOD aims to train object detectors by using only image-level annotations. Many recent works on WSOD adopt multiple instance detection networks (MIDN, which usually generate a certain number of proposals and regard proposal classification as a latent model learning within image classification. However, these meth...

Magnetic resonance (MR) imaging is a commonly used scanning technique for disease detection, diagnosis and treatment monitoring. Although it is able to produce detailed images of organs and tissues with better contrast, it suffers from a long acquisition time, which makes the image quality vulnerable to say motion artifacts. Recently, many approach...

Parameter Selection, Visualization of CBs, Clustering Analysis

Contactless palmprint recognition has recently made significant progress in palm-scanning payment and social security. However, most existing methods are based on handcrafted kernels and are sensitive to illumination and scale variations. To address this problem, a competitive convolutional neural network (CompNet) with constrained learnable Gabor...

With the development of deep encoder-decoder architectures and large-scale annotated medical datasets, great progress has been achieved in the development of automatic medical image segmentation. Due to the stacking of convolution layers and the consecutive sampling operations, existing standard models inevitably encounter the information recession...

Since human-labeled samples are free for the target set, unsupervised person re-identification (Re-ID) has attracted much attention in recent years, by additionally exploiting the source set. However, due to the differences on camera styles, illumination and backgrounds, there exists a large gap between source domain and target domain, introducing...

Restoring the clean background from the superimposed images containing a noisy layer is the common crux of a classical category of tasks on image restoration such as image reflection removal, image deraining and image dehazing. These tasks are typically formulated and tackled individually due to diverse and complicated appearance patterns of noise...

Deep convolutional neural networks (CNNs) have been widely applied for low-level vision over the past five years. According to the nature of different applications, designing appropriate CNN architectures is developed. However, customized architectures gather different features via treating all pixel points as equal to improve the performance of gi...

Heterogeneous palmprint recognition has attracted considerable research attention in recent years because it has the potential to greatly improve the recognition performance for personal authentication. In this article, we propose a simultaneous heterogeneous palmprint feature learning and encoding method for heterogeneous palmprint recognition. Un...

Deep convolutional neural networks (CNNs) have been widely applied for low-level vision over the past five years. According to nature of different applications, designing appropriate CNN architectures is developed. However, customized architectures gather different features via treating all pixel points as equal to improve the performance of given...

In convolutional neural networks (CNNs), generating noise for the intermediate feature is a hot research topic in improving generalization. The existing methods usually regularize the CNNs by producing multiplicative noise (regularization weights), called multiplicative regularization (Multi-Reg). However, Multi-Reg methods usually focus on improvi...

Defocus blur detection (DBD), which has been widely applied to various fields, aims to detect the out-of-focus or in-focus pixels from a single image. Despite the fact that the deep learning based methods applied to DBD have outperformed the hand-crafted feature based methods, the performance cannot still meet our requirement. In this paper, a nove...

In order to deploy deep Convolutional Neural Networks (CNNs) on the mobile devices, many mobile CNNs are introduced. Currently, some online applications are usually re-trained because of the constantly-increasing data. However, compared with the regular models, it is not very efficient to train the present mobile models. Therefore, the purpose of t...

Restoring the clean background from the superimposed images containing a noisy layer is the common crux of a classical category of tasks on image restoration such as image reflection removal, image deraining and image dehazing. These tasks are typically formulated and tackled individually due to the diverse and complicated appearance patterns of no...

Voice analysis is a non-invasive, painless, and convenient alternative for disease detection. Despite many existing methods for voice based pathology detection, they generally consider a single audio, even though different audios provide complementary information and a fusion of them would contribute to improving the classification performance. In...

With the title “Pathological voice analysis,” this book mainly focuses on the building models for the analysis of pathological voice. The book contains three parts. Firstly, a brief overview of pathological voice analysis and a guideline on the voice acquisition for clinical use are presented. Secondly, we introduce two important signal processing...

Pitch estimation is quite crucial to many applications. Although a number of estimation methods working in different domains have been put forward, there are still demands for improvement, especially for noisy speech. In this chapter, we present iPEEH, a general technique to raise performance of pitch estimators by enhancing harmonics. By analysis...

Glottal Closure Instants (GCIs) detection is important to many speech applications. However, most existing algorithms cannot achieve computational efficiency and accuracy simultaneously. In this chapter, we present the Glottal closure instants detection based on the Multiresolution Absolute TKEO (GMAT) that can detect GCIs with high accuracy and lo...

Voice analysis provides a non-invasive way for disease detection, in which most methods only consider a single audio, although different audios contain complementary information and a fusion of them is beneficial. In this chapter, a novel model JOLL4R (JOint Learning based on Label Relaxed low-Rank Ridge Regression) is proposed to fuse audios for v...

Detecting Parkinson’s disease (PD) based on voice analysis is meaningful due to the non-invasion and convenience. Traditional features adopted for PD detection are often hand-crafted, in which special expertise is needed. In this chapter, we propose to employ a feature learning technique to learn features automatically, where special expertise is u...

In pathological voice analysis, voice acquisition is of great importance since the quality of the voice has great impacts on the performance of voice analysis. In particular, the influence of SNR (signal-to-noise ratio) and sampling rate during recording are two key factors that require investigation.

Existing hashing methods have yielded significant performance in image and multimedia retrieval, which can be categorized into two groups: shallow hashing and deep hashing. However, there still exist some intrinsic limitations among them. The former generally adopts a one-step strategy to learn the hashing codes for discovering the discriminative b...

So far, there exist many publicly available palmprint databases. However, not all of them have provided the corresponding region of interest (ROI) images. If everyone uses their own extracted ROI images for performance testing, the final accuracy is not strictly comparable. Since ROI localization is the critical stage of palmprint recognition. The...

Currently, many palmprint acquisition devices have been proposed, but how to design the systems are seldom studied, such as how to choose the imaging sensor, the lens, and the working distance. This chapter aims to find the relationship between image sharpness and recognition performance and then utilize this information to direct the system design...

Deep convolutional neural networks (CNNs) for image denoising have recently attracted increasing research interest. However, plain networks cannot recover fine details for a complex task, such as real noisy images. In this paper, we propose a Dual denoising Network (DudeNet) to recover a clean image. Specifically, DudeNet consists of four modules:...

Currently, in order to deploy the convolutional neural networks (CNNs) on the mobile devices and address the over-fitting problem caused by the less abundant datasets, reducing the redundancy of parameters is the main target to construct the mobile CNNs. Based on this target, this paper proposes two novel convolutional kernels, multiple group reuse...

The performances of person re-identification tasks can be seriously degraded because of variations caused by view changes. In recent years, there are many methods focusing on how to solve cross view challenges which can be roughly divided into two categories: 1) learning view-invariant features without the help of view information. 2) combining vie...

Correlation filters (CFs) have been continuously advancing the state-of-the-art tracking performance and have been extensively studied in the recent few years. Nonetheless, the existing CF trackers adopt a cosine window to spatially reweight base image to alleviate boundary discontinuity. However, cosine window emphasizes more on the central region...

The heterogeneous gap among cross modalities is a critical problem in many applications (e.g., retrieval). Considering that the main purpose of cross-modal learning is to learn a common representation while there also exist specific components across different modalities, a similarity and diversity induced paired projection (SDPP) method is propose...

Image brightness in color representation has caught active research interests, while its influence to texture features is relatively rarely studied. In this paper, we address the issue of illuminance, or brightness, interference to texture descriptors, especially to the Gabor filter based approaches. Firstly, we reveal the fact that the Gabor respo...

Human fingers are 3D objects. More information will be provided if three dimensional (3D) fingerprints are available compared with two dimensional (2D) fingerprints. Thus, this chapter firstly collected 3D finger point cloud data by Structured-light Illumination method. Additional features from 3D fingerprint images are then studied and extracted....

Sweat pores on fingerprints have proven to be discriminative features and have recently been successfully employed in automatic fingerprint recognition systems (AFRS). It is crucial to extract pores precisely to achieve high recognition accuracy. In this chapter two extraction methods will be given. The first method is based on a dynamic anisotropi...

This chapter addresses the problem of feature-based 3D reconstruction model for close-range objects. Since it is almost impossible to find pixel-to-pixel correspondences from 2D images by algorithms when the object is imaged on a close range, the selection of feature correspondences, as well as the number and distribution of them, play important ro...

High resolution fingerprint images have been increasingly used in fingerprint recognition. They can provide more fine features (e.g. pores) than standard fingerprint images, which are expected to be helpful for improving the recognition accuracy. It is therefore demanded to investigate whether or not existing quality assessment methods are suitable...

This chapter shows an application of pores in the alignment of high resolution partial fingerprints, which is a crucial step in partial fingerprint recognition. Previously developed fingerprint alignment methods, including minutia-based and non-minutia feature based ones, are unsuitable for partial fingerprints because small fingerprint fragments o...

High-resolution automated fingerprint recognition systems (AFRS) offer higher security because they are able to make use of level 3 features, such as pores, that are not available in lower-resolution (<500 dpi) images. One of the main parameters affecting the quality of a digital fingerprint image and issues such as cost, interoperability, and perf...

This chapter concludes the book. We first highlight again the motivation of compiling such a book on the topic of advanced fingerprint recognition technology, in particular 3D fingerprints and high resolution fingerprints. We then briefly summarize the content of each chapter in the main body of this book. Finally, we discuss the remaining challeng...

Traditional fingerprints are captured in touch-based way, which results in partial or degraded images. Replacement of touch-based fingerprints by touchless ones can promote the development of touchless 3D AFRSs with high security and accuracy. This chapter reviewed technologies involved 3D AFRSs, including 3D fingerprint generation, 3D fingerprint...

Touchless-based fingerprint recognition technology is thought to be an alternative to touch-based systems to solve problems of hygienic, latent fingerprints, and maintenance. However, there are few studies about touchless fingerprint recognition systems due to the lack of a large database and the intrinsic drawback of low ridge-valley contrast of t...

Extended fingerprint features such as pores, dots and incipient ridges have attracted increasing attention from researchers and engineers working on automatic fingerprint recognition systems. A variety of methods have been proposed to combine these features with the traditional minutiae features. This chapter comparatively analyses the parallel and...

Fingerprint matching is an important and essential step in automated fingerprint recognition systems (AFRSs). The noise and distortion of captured fingerprints and the inaccurate of extracted features make fingerprint matching a very difficult problem. With the advent of high resolution fingerprint imaging techniques and the increasing demand for h...

This chapter provides an overview of Part II with focus on the background and development of fingerprint recognition using high resolution images. We first discuss the significance of high resolution fingerprint recognition in the context of fingerprint recognition history, and then introduce fingerprint features, particularly the features availabl...

The entropy of the codes usually serves as the rate loss in the recent learned lossy image compression methods. Precise estimation of the probabilistic distribution of the codes plays a vital role in the performance. However, existing deep learning based entropy modeling methods generally assume the latent codes are statistically independent or dep...

Precise estimation of the probabilistic structure of natural images plays an essential role in image compression. Despite the recent remarkable success of end-to-end optimized image compression, the latent codes are usually assumed to be fully statistically factorized in order to simplify entropy modeling. However, this assumption generally does no...

With the increased model size of convolutional neural networks (CNNs), overfitting has become the main bottleneck to further improve the performance of networks. Currently, the weighting regularization methods have been proposed to address the overfitting problem and they perform satisfactorily. Since these regularization methods cannot be used in...

Learning-based lossy image compression usually involves the joint optimization of rate-distortion performance, and requires to cope with the spatial variation of image content and contextual dependence among learned codes. Traditional entropy models can spatially adapt the local bit rate based on the image content, but usually are limited in exploi...

In this paper, a novel deep network is proposed for multi-focus image fusion, named Deep Regression Pair Learning (DRPL). In contrast to existing deep fusion methods which divide the input image into small patches and apply a classifier to judge whether the patch is in focus or not, DRPL directly converts the whole image into a binary mask without...

To sense the pulse in the representative positions of wrist is the basis of traditional Chinese pulse diagnosis. The pulse diagnosis has been obtaining more and more attentions for its non-invasive character and its convenience in analysis of health status. For objective analysis, various types of pulse features have been extracted from the pulse s...

Existing multi-label medical image learning tasks generally contain rich relationship information among pathologies such as label co-occurrence and interdependency, which is of great importance for assisting in clinical diagnosis and can be represented as the graph-structured data. However, most state-of-the-art works only focus on regression from...

Kinship verification in the wild is an interesting and challenging problem. The goal of kinship verification is to determine whether a pair of faces are blood relatives or not. Most previous methods for kinship verification can be divided as handcrafted features-based shallow learning methods and convolutional neural network (CNN)-based deep-learni...

Three-dimensional (3D) palmprint recognition has been investigated for over 10 years, various methods have been proposed for 3D palmprint recognition. In this paper, we present a comprehensive overview of feature extraction and matching for 3D palmprint recognition over the past decade. First, We introduce the 3D palmprint data acquisition and prep...

Fingerprints are among the most widely used biometric modalities and have been successfully applied in various scenarios. For example, in forensics, fingerprints serve as important legal evidence; and in civilian applications, fingerprints are used for access and attendance control as well as other identity services. Thanks to advances in three-dim...

While voice is widely used in speech recognition and speaker identification, its application in biomedical fields is much less common. This book systematically introduces the authors’ research on voice analysis for biomedical applications, particularly pathological voice analysis. Firstly, it reviews the field to highlight the biomedical value of v...

Due to the powerful capability of the data representation, deep learning has achieved a remarkable performance in supervised hash function learning. However, most of the existing hashing methods focus on point-to-point matching that is too strict and unnecessary. In this article, we propose a novel deep supervised hashing method by relaxing the mat...

Pore-based fingerprint recognition has been researched for decades. Many algorithms have been proposed to improve the recognition accuracy of the system. However, the accuracies are always improved at the cost of speed. This article proposes a novel method to compare the pores in high-resolution fingerprint images using the popular coarse-to-fine s...

Tongue image analysis has been an active study in medical imaging. Existing tongue image processing approaches deal with the issue of image alignment in oversimplified ways. These approaches mainly extract patches or simple regions on pre-defined positions, which are severely sensitive to tongue deformations. In this paper, we present a conformal m...

Traditional clinical experiences have shown the benefit of lesion location attention for improving clinical diagnosis tasks. Inspired by this point of interest, in this paper we propose a novel lesion location attention guided network named LLAGnet to focus on the discriminative features from lesion locations for multi-label thoracic disease classi...

A prevailing problem in many machine learning tasks is that the training (i.e., source domain) and test data (i.e., target domain) have different distribution [i.e., non-independent identical distribution (i.i.d.)]. Unsupervised domain adaptation (UDA) was proposed to learn the unlabeled target data by leveraging the labeled source data. In this ar...

The self-expressive property of data points, that is, each data point can be linearly represented by the other data points in the same subspace, has proven effective in leading subspace clustering (SC) methods. Most self-expressive methods usually construct a feasible affinity matrix from a coefficient matrix, obtained by solving an optimization pr...

Recently, learning to hash has been widely studied for image retrieval thanks to the computation and storage efficiency of binary codes. Most existing learning to hash methods have yielded significant performance. However, for most existing learning to hash methods, sufficient training images are required and used to learn precise hashing codes. In...

Group convolution is widely used in many mobile networks to remove the filter’s redundancy from the channel extent. In order to further reduce the redundancy of group convolution, this article proposes a novel repeated group convolutional (RGC) kernel, which has $M$ primary groups, and each primary group includes $N$ tiny groups. In every prima...

Sparse representation (SR) and collaborative representation (CR) have been successfully applied in many pattern classification tasks such as face recognition. In this paper, we propose a novel Non-negative Sparse and Collaborative Representation (NSCR) for pattern classification. The NSCR representation of each test sample is obtained by seeking a...

The recent success of deep network in visual trackers learning largely relies on human labeled data, which are however expensive to annotate. Recently, some unsupervised methods have been proposed to explore the learning of visual trackers without labeled data, while their performance lags far behind the supervised methods. We identify the main bot...

Most existing non-blind restoration methods are based on the assumption that a precise degradation model is known. As the degradation process can only partially known or inaccurately modeled, images may not be well restored. Rain streak removal and image deconvolution with inaccurate blur kernels are two representative examples of such tasks. For r...

It has long been understood that precisely estimating the probabilistic structure of natural visual images is crucial for image compression. Despite the remarkable success of recent end-to-end optimized image compression, the latent code representation is assumed to be fully statistically factorized such that the entropy modeling is feasible. Here...

Multiview learning has been widely studied in various fields and achieved outstanding performances in comparison to many single-view-based approaches. In this paper, a novel multiview learning method based on the Gaussian process latent variable model (GPLVM) is proposed. In contrast to existing GPLVM methods which only assume that there are transf...