Andrew Beng Jin Teoh
YOU?
Author Swipe
View article: Fake Indian Currency Detection Using Deep Learning
Fake Indian Currency Detection Using Deep Learning Open
The system leverages intrinsic security features of currency notes such as watermarks, security threads, micro-text, and serial numbers, which serve as unique identifiers to distinguish genuine notes from counterfeit ones. ”Fake currency i…
View article: Android malware detection using machine learning
Android malware detection using machine learning Open
Because Android is open-source and widely used, it has emerged as the most popular mobile operating system. But because of its widespread use, fraudsters who disseminate malicious software have found it to be a prime target. Although they …
View article: Federated Learning for Large Models in Medical Imaging: A Comprehensive Review
Federated Learning for Large Models in Medical Imaging: A Comprehensive Review Open
Artificial intelligence (AI) has demonstrated considerable potential in the realm of medical imaging. However, the development of high-performance AI models typically necessitates training on large-scale, centralized datasets. This approac…
View article: Palmprint De-Identification Using Diffusion Model for High-Quality and Diverse Synthesis
Palmprint De-Identification Using Diffusion Model for High-Quality and Diverse Synthesis Open
Palmprint recognition techniques have advanced significantly in recent years, enabling reliable recognition even when palmprints are captured in uncontrolled or challenging environments. However, this strength also introduces new risks, as…
View article: TailedCore: Few-Shot Sampling for Unsupervised Long-Tail Noisy Anomaly Detection
TailedCore: Few-Shot Sampling for Unsupervised Long-Tail Noisy Anomaly Detection Open
We aim to solve unsupervised anomaly detection in a practical challenging environment where the normal dataset is both contaminated with defective regions and its product class distribution is tailed but unknown. We observe that existing m…
View article: AggreGait: Automatic gait feature extraction for human age and gender classification with possible occlusion
AggreGait: Automatic gait feature extraction for human age and gender classification with possible occlusion Open
The growing interest in smart surveillance and automated public access control necessitates robust age and gender classification (AGC) techniques that can operate effectively in unconstrained environments. While model-based gait obtained v…
View article: Learnable Anchor Embedding for Asymmetric Face Recognition
Learnable Anchor Embedding for Asymmetric Face Recognition Open
Face verification and identification traditionally follow a symmetric matching approach, where the same model (e.g., ResNet-50 vs. ResNet-50) generates embeddings for both gallery and query images, ensuring compatibility. However, real-wor…
View article: Deep Learning in Palmprint Recognition-A Comprehensive Survey
Deep Learning in Palmprint Recognition-A Comprehensive Survey Open
Palmprint recognition has emerged as a prominent biometric technology, widely applied in diverse scenarios. Traditional handcrafted methods for palmprint recognition often fall short in representation capability, as they heavily depend on …
View article: Deep Learning in Palmprint Recognition-A Comprehensive Survey
Deep Learning in Palmprint Recognition-A Comprehensive Survey Open
Palmprint recognition has emerged as a prominent biometric technology, widely applied in diverse scenarios. Traditional handcrafted methods for palmprint recognition often fall short in representation capability, as they heavily depend on …
View article: Classifying Scam Calls Through Content Analysis With Dynamic Sparsity Top-<i>k</i> Attention Regularization
Classifying Scam Calls Through Content Analysis With Dynamic Sparsity Top-<i>k</i> Attention Regularization Open
The rise of scam calls in recent years necessitated effective countermeasures against these fraudulent activities, which cause financial losses and threaten personal security. Although previous research utilizing traditional machine learni…
View article: Multivariate Time Series Clustering with State Space Dynamical Modeling and Grassmann Manifold Learning: A Systematic Review on Human Motion Data
Multivariate Time Series Clustering with State Space Dynamical Modeling and Grassmann Manifold Learning: A Systematic Review on Human Motion Data Open
Multivariate time series (MTS) clustering has been an essential research topic in various domains over the past decades. However, inherent properties of MTS data—namely, temporal dynamics and inter-variable correlations—make MTS clustering…
View article: Conditional Deployable Biometrics: Matching Periocular and Face in Various Settings
Conditional Deployable Biometrics: Matching Periocular and Face in Various Settings Open
In this paper, we introduce the concept of Conditional Deployable Biometrics (CDB), designed to deliver consistent performance across various biometric matching scenarios, including intra-modal, multimodal, and cross-modal applications. Th…
View article: Cross-Chirality Palmprint Verification: Left is Right for the Right Palmprint
Cross-Chirality Palmprint Verification: Left is Right for the Right Palmprint Open
Palmprint recognition has emerged as a prominent biometric authentication method, owing to its high discriminative power and user-friendly nature. This paper introduces a novel Cross-Chirality Palmprint Verification (CCPV) framework that c…
View article: Enhancing Image Dehazing with a Multi-DCP Approach with Adaptive Airlight and Gamma Correction
Enhancing Image Dehazing with a Multi-DCP Approach with Adaptive Airlight and Gamma Correction Open
Haze imagery suffers from reduced clarity, which can be attributed to atmospheric conditions such as dust or water vapor, resulting in blurred visuals and heightened brightness due to light scattering. Conventional methods employing the da…
View article: Gait-based age group classification with adaptive Graph Neural Network
Gait-based age group classification with adaptive Graph Neural Network Open
Deep learning techniques have recently been utilized for model-free age-associated gait feature extraction.
\nHowever, acquiring model-free gait demands accurate pre-processing such as background subtraction, which
\nis non-trivial in unco…
View article: WiFaKey: Generating Cryptographic Keys from Face in the Wild
WiFaKey: Generating Cryptographic Keys from Face in the Wild Open
Deriving a unique cryptographic key from biometric measurements is a challenging task due to the existing noise gap between the biometric measurements and error correction coding. Additionally, privacy and security concerns arise as biomet…
View article: Face Reconstruction Transfer Attack as Out-of-Distribution Generalization
Face Reconstruction Transfer Attack as Out-of-Distribution Generalization Open
Understanding the vulnerability of face recognition systems to malicious attacks is of critical importance. Previous works have focused on reconstructing face images that can penetrate a targeted verification system. Even in the white-box …
View article: Beyond First-Order: A Multi-Scale Approach to Finger Knuckle Print Biometrics
Beyond First-Order: A Multi-Scale Approach to Finger Knuckle Print Biometrics Open
Recently, finger knuckle prints (FKPs) have gained attention due to their rich textural patterns, positioning them as a promising biometric for identity recognition. Prior FKP recognition methods predominantly leverage first-order feature …
View article: CoreTemp: Coreset Sampled Templates for Multimodal Mobile Biometrics
CoreTemp: Coreset Sampled Templates for Multimodal Mobile Biometrics Open
Smart devices have become the core ingredient in maintaining human society, where their applications span basic telecommunication, entertainment, education, and even critical security tasks. However, smartphone security measures have not k…
View article: Abnormal behavior recognition using SRU with attention mechanism
Abnormal behavior recognition using SRU with attention mechanism Open
In response to the critical need for enhanced public safety measures, this study introduces an advanced intelligent surveillance system designed to autonomously detect abnormal behaviors within public spaces. Leveraging the computational e…
View article: On the security risk of pre-image attack on cancelable biometrics
On the security risk of pre-image attack on cancelable biometrics Open
Over the years, a number of biometric template protection schemes, often based on the notion of “cancelable biometrics”, have been proposed. An ideal cancelable biometric algorithm complies with four criteria: irreversibility, revocability…
View article: A Dual-Level Cancelable Framework for Palmprint Verification and Hack-Proof Data Storage
A Dual-Level Cancelable Framework for Palmprint Verification and Hack-Proof Data Storage Open
In recent years, palmprints have been widely used for individual verification. The rich privacy information in palmprint data necessitates its protection to ensure security and privacy without sacrificing system performance. Existing syste…
View article: A Realistic Hand Image Composition Method for Palmprint ROI Embedding Attack
A Realistic Hand Image Composition Method for Palmprint ROI Embedding Attack Open
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 …
View article: Guest Editorial: Special issue on advances in representation learning for computer vision
Guest Editorial: Special issue on advances in representation learning for computer vision Open
Deep learning has been a catalyst for a transformative revolution in machine learning and computer vision in the past decade. Within these research domains, methods grounded in deep learning have exhibited exceptional performance across a …
View article: Scale-aware competition network for palmprint recognition
Scale-aware competition network for palmprint recognition Open
Palmprint biometrics garner heightened attention in palm-scanning payment and social security due to their distinctive attributes. However, prevailing methodologies singularly prioritize texture orientation, neglecting the significant text…
View article: Energizing Federated Learning via Filter-Aware Attention
Energizing Federated Learning via Filter-Aware Attention Open
Federated learning (FL) is a promising distributed paradigm, eliminating the need for data sharing but facing challenges from data heterogeneity. Personalized parameter generation through a hypernetwork proves effective, yet existing metho…
View article: Understanding the Feature Norm for Out-of-Distribution Detection
Understanding the Feature Norm for Out-of-Distribution Detection Open
A neural network trained on a classification dataset often exhibits a higher vector norm of hidden layer features for in-distribution (ID) samples, while producing relatively lower norm values on unseen instances from out-of-distribution (…
View article: Nearest Neighbor Guidance for Out-of-Distribution Detection
Nearest Neighbor Guidance for Out-of-Distribution Detection Open
Detecting out-of-distribution (OOD) samples are crucial for machine learning models deployed in open-world environments. Classifier-based scores are a standard approach for OOD detection due to their fine-grained detection capability. Howe…
View article: Physics-Driven Spectrum-Consistent Federated Learning for Palmprint Verification
Physics-Driven Spectrum-Consistent Federated Learning for Palmprint Verification Open
Palmprint as biometrics has gained increasing attention recently due to its discriminative ability and robustness. However, existing methods mainly improve palmprint verification within one spectrum, which is challenging to verify across d…