Research Interests:
3D shape generation is widely applied in various industries to create, visualize, and analyse complex data, designs, and simulations. Typically, 3D shape generation uses a large dataset of 3D shapes as the input. This paper proposes a... more
3D shape generation is widely applied in various industries to create, visualize, and analyse complex data, designs, and simulations. Typically, 3D shape generation uses a large dataset of 3D shapes as the input. This paper proposes a variational autoencoder with a signed distance function relativistic average generative adversarial network, referred to as 3D-VAE-SDFRaGAN, for 3D shape generation from 2D input images. Both the generative adversarial network (GAN) and variational autoencoder (VAE) algorithms are typical algorithms used to generate realistic 3D shapes. However, it is very challenging to train a stable 3D shape generation model using VAE-GAN. This paper proposes an efficient approach to stabilize the training process of VAE-GAN to generate high-quality 3D shapes. A 3D mesh-based shape is first generated using a 3D signed distance function representation by feeding a single 2D image into a 3D-VAE-SDFRaGAN network. The signed distance function is used to maintain inside–...
Research Interests:
Although biometrics is a powerful tool against repudiation, it still suffers from some inherent biometric specific threats. There is risk of being compromised by attacker where an attacker might use the biometrics information to... more
Although biometrics is a powerful tool against repudiation, it still suffers from some inherent biometric specific threats. There is risk of being compromised by attacker where an attacker might use the biometrics information to masquerade as the person. The worst is a biometric feature cannot be replaced once it is compromised. In this research, we introduce the concept of private biometrics to overcome these drawbacks
Masked face recognition (MFR) is an interesting topic in which researchers have tried to find a better solution to improve and enhance performance. Recently, COVID-19 caused most of the recognition system fails to recognize facial images... more
Masked face recognition (MFR) is an interesting topic in which researchers have tried to find a better solution to improve and enhance performance. Recently, COVID-19 caused most of the recognition system fails to recognize facial images since the current face recognition cannot accurately capture or detect masked face images. This paper introduces the proposed method known as histogram-based recurrent neural network (HRNN) MFR to solve the undetected masked face problem. The proposed method includes the feature descriptor of histograms of oriented gradients (HOG) as the feature extraction process and recurrent neural network (RNN) as the deep learning process. We have proven that the combination of both approaches works well and achieves a high true acceptance rate (TAR) of 99 percent. In addition, the proposed method is designed to overcome the underfitting problem and reduce computational burdens with large-scale dataset training. The experiments were conducted on two benchmark d...
Research Interests:
Masked face recognition embarks the interest among the researchers to find a better algorithm to improve the performance of face recognition applications, especially in the Covid-19 pandemic lately. This paper introduces a proposed masked... more
Masked face recognition embarks the interest among the researchers to find a better algorithm to improve the performance of face recognition applications, especially in the Covid-19 pandemic lately. This paper introduces a proposed masked face recognition method known as Principal Random Forest Convolutional Neural Network (PRFCNN). This method utilizes the strengths of Principal Component Analysis (PCA) with the combination of Random Forest algorithm in Convolution Neural Network to pre-train the masked face features. PRFCNN is designed to assist in extracting more salient features and prevent overfitting problems. Experiments are conducted on two benchmarked datasets, RMFD (Real-World Masked Face Dataset) and LFW Simulated Masked Face Dataset using various parameter settings. The experimental result with a minimum recognition rate of 90% accuracy promises the effectiveness of the proposed PRFCNN over the other state-of-the-art methods.
Research Interests:
This paper presents the robustness of the proposed metric learning formulation, dubbed Discriminative Spectral Regression Metric Learning in offering a simplistic solution for measuring the Mahalanobis metric to solve unconstrained face... more
This paper presents the robustness of the proposed metric learning formulation, dubbed Discriminative Spectral Regression Metric Learning in offering a simplistic solution for measuring the Mahalanobis metric to solve unconstrained face verification problems. It takes advantage of distance metric learning on pairs of doublets by adopting the merit of the quadratic kernel function in the verification task. To be specific, the spectral graph analysis and the linear discriminant analysis are unified into the distance metric learning process for better exploitation of the intrinsic discriminant structure of face data. The proposed formulation is evaluated with four benchmarked constrained and unconstrained face datasets, with different tuning parameters under the restricted protocol. The promising result of 89.07% verification rate evinces the effectiveness and feasibility of the proposed formulation in unconstrained face verification compared to the state-of-the-art methods.
Research Interests:
The evolution of mobile devices, especially in these modern days, has drastically changed the face of business. A mobile phone device is often expected to offer computer-like functionality. These days, most mobile phone users find it... more
The evolution of mobile devices, especially in these modern days, has drastically changed the face of business. A mobile phone device is often expected to offer computer-like functionality. These days, most mobile phone users find it somehow inconvenient to do some tasks using their computers. Most individuals prefer to change positions while sitting, stretching, and also feeling a bit more comfortable when browsing through their computers. It can be very impractical to be confined to the keyboard and mouse while sitting 5 or 10 feet from the computer. Hence, the proposed application is meant to turn the hand phone into a wireless keyboard and mouse with a touch-pad, through the wireless network. This prototype is proven to be able to perform most of the actions a normal computer keyboard and mouse can perform.
Research Interests:
A new formulation of metric learning is introduced by assimilating the kernel ridge regression KRR and weighted side-information linear discriminant analysis WSILD to enjoy the best of both worlds for unconstrained face verification task.... more
A new formulation of metric learning is introduced by assimilating the kernel ridge regression KRR and weighted side-information linear discriminant analysis WSILD to enjoy the best of both worlds for unconstrained face verification task. To be specific, we formulate a doublet constrained metric learning problem by means of a second degree polynomial kernel function. The said metric learning problem can be solved analytically for Mahalanobis distance metric due to simplistic nature of KRR in which we named KRRML. In addition, the WSILD further enhances the learned Mahalanobis distance metric by leveraging the within-class and between-class scatter matrix of doublets. We evaluate the proposed method with Labeled Faces in the Wild database, a large benchmark dataset targeted for unconstrained face verification. The promising result attests the robustness and feasibility of the proposed method.
Research Interests:
In this paper, a kernel classification distance metric learning framework is investigated for face verification. The framework is to model the metric learning as a Support Vector Machine face classification problem, where a Mahalanobis... more
In this paper, a kernel classification distance metric learning framework is investigated for face verification. The framework is to model the metric learning as a Support Vector Machine face classification problem, where a Mahalanobis distance metric is learnt in the original face feature space. In the process, pairwise doublets that are constructed from the training samples can be packed and represented in a means of degree-2 polynomial kernel. By utilizing the standard SVM solver, the metric learning problem can be solved in a simpler and efficient way. We evaluate the kernel classification-based metric learning on three different face datasets. We demonstrate that the method manages to show its simplicity and robustness in face verification with satisfactory results in terms of training time and accuracy when compared with the state-of-the-art methods.
Research Interests:
Privacy preserving scheme for face verification is a biometric system embedded with template protection to protect the data in ensuring data integrity. This paper proposes a new method called Histogram of Oriented Gradient Random Template... more
Privacy preserving scheme for face verification is a biometric system embedded with template protection to protect the data in ensuring data integrity. This paper proposes a new method called Histogram of Oriented Gradient Random Template Protection (HOGRTP). The proposed method utilizes Histogram of Oriented Gradient approach as a feature extraction technique and is combined with Random Template Protection method. The proposed method acts as a multi-factor authentication technique and adds a layer of data protection to avoid the compromising biometric issue because biometric is irreplaceable. The performance accuracy of HOGRTP is tested on the unconstrained face images using the benchmarked dataset, Labeled Face in the Wild (LFW). A promising result is obtained to prove that HOGRTP achieves a higher verification rate in percentage than the pure biometric scheme.
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
An iris verification system based on the integration of secret pseudo-random number and the user-specific iris feature, which generated from the ID Log-Gabor filters, to produce a unique compact binary code per person is proposed in this... more
An iris verification system based on the integration of secret pseudo-random number and the user-specific iris feature, which generated from the ID Log-Gabor filters, to produce a unique compact binary code per person is proposed in this paper. This dual factor authentication approach coined as S-Iris Ecoding has significant functional advantages over solely biometrics such as token replacement. In addition, the risk of security threats can be greatly reduced such as iris fabrication. Experimental results show that this method has good performance over traditional iris verification in which perfect verification rate of the genuine and imposter populations can be produced. By applying S-Iris Encoding, the original iris feature length is notably reduced to around 5% of the original size and a 0.0025%" ≈ 0% of EER can be achieved.
Research Interests:
The standard for wireless mobile communication system has been set higher since the introduction of Long Term Evolution (LTE) system by Third Generation Partnership Project (3GPP). Marketed as part of the 4G wireless technology, LTE... more
The standard for wireless mobile communication system has been set higher since the introduction of Long Term Evolution (LTE) system by Third Generation Partnership Project (3GPP). Marketed as part of the 4G wireless technology, LTE offers an outstanding connectivity with high throughput, low latency and improved spectral efficiency. LTE possesses a Quality of Service (QoS) framework to ensure satisfying user- perceived end-to-end performance according to demand. QoS parameters are highly variable according to application, user and service differentiation. Therefore, to satisfy QoS requirements, various studies have proposed algorithms fitting for their specific traffic scenarios. This paper covers a survey of proposed algorithms in QoS framework of LTE system.
Research Interests:
A flexible feature descriptor, Gabor-based Region Covariance Matrix (GRCM), embeds the Gabor features into the covariance matrix has emerged in face recognition. GRCM locates on Tensor manifold, a non-Euclidean space, utilises distance... more
A flexible feature descriptor, Gabor-based Region Covariance Matrix (GRCM), embeds the Gabor features into the covariance matrix has emerged in face recognition. GRCM locates on Tensor manifold, a non-Euclidean space, utilises distance measures such as Affine-invariant Riemannian Metric (AIRM) and Log-Euclidean Riemannian Metric (LERM) to calculate the distance between two covariance matrices. However, these distance measures are computationally expensive. Therefore, a machine learning approach via manifold flattening is proposed to alleviate the problem. Besides, several feature fusions that integrate the 2.5D partial data and 2D texture image are investigated to boost the recognition rate. Experimental results have exhibited the effectiveness of the proposed method in improving the recognition rate for 2.5D face recognition.
Research Interests:
Research Interests: Computer Science and IEEE
Research Interests:
Research Interests:
Research Interests:
Gabor-based region covariance matrix (GRCM) is a very flexible face descriptor where it allows different combination of features to be fused to construct a covariance matrix. GRCM resides on Tensor manifold where the computation of... more
Gabor-based region covariance matrix (GRCM) is a very flexible face descriptor where it allows different combination of features to be fused to construct a covariance matrix. GRCM resides on Tensor manifold where the computation of geodesic distance between two points requires the consideration of geometry characteristics of the manifold. Affine Invariant Riemannian Metric (AIRM) is the most widely used geodesic distance metric. However, it is computationally heavy. This paper investigates several geodesic distance metrics on Tensor manifold to find out the alternative speedy method for 2.5D face recognition using GRCM. Besides, we propose a feature-level fusion for 2.5D partial and 2D data to enhance the recognition performance.
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Abstract:-An iris verification system based on the integration of secret pseudo-random number and the userspecific iris feature, which generated from the ID Log-Gabor filters, to produce a unique compact binary code per person is proposed... more
Abstract:-An iris verification system based on the integration of secret pseudo-random number and the userspecific iris feature, which generated from the ID Log-Gabor filters, to produce a unique compact binary code per person is proposed in this paper. This dual factor authentication approach coined as S-Iris Ecoding has significant functional advantages over solely biometrics such as token replacement. In addition, the risk of security threats can be greatly reduced such as iris fabrication. Experimental results show that this method has ...
Research Interests:
Abstract This paper presents a novel method of integrating the user-specific secret pseudo-random number and iris feature extracted from wavelet packet transform as a feature vector for iris verification. The proposed method helps to... more
Abstract This paper presents a novel method of integrating the user-specific secret pseudo-random number and iris feature extracted from wavelet packet transform as a feature vector for iris verification. The proposed method helps to improve the traditional iris verification system which depends solely on iris feature. The security risks such as iris fabrication can be avoided through the token replacement. Experimental results show that the proposed method has an encouraging performance. The optimum result is obtained for mean ...