Anh Duc Nguyen

Anh Duc Nguyen

Auto-generated profile, based on publicly available information

Anh Duc Nguyen

Department of Information Systems, VNU University of Engineering and Technology, Hanoi, Vietnam

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications

26 December 2023 in IEEE Transactions on Automation Science and Engineering
Verified
Journal Article
Closed access
PDPhuong Hanh DU
Phuong Hanh DU
ANAnh D. Nguyen
Anh D. Nguyen
DNDat T. Nguyen
Dat T. Nguyen
HNHoa Ngoc Nguyen
Hoa Ngoc Nguyen
DNDung H. P. Nguyen
Dung H. P. Nguyen
For autonomous vehicles, face-based authentication is one of the best ways to identify or verify a user. Deep learning methods, such as Deep Convolutional Neural Networks (DCNN), have brought excellent accuracy in recent years. However, building an optimal DCNN and ameliorating face-based authentication performance are still the main challenges for autonomous vehicles. From these challenges, we first investigate and analyze the effect of several novel effective loss functions on DCNN, such as CosFace, ArcFace, and MagFace, for face-based authentication. We then propose a parallel ensemble learning, namely PelFace, by taking advantage of recent models based on CosFace, ArcFace, and MagFace. PelFace elaborates on the voting mechanism that utilizes non-optimal pre-trained models to obtain better discriminative ability for face-based authentication. In addition, we propose to perform the matching phase for each PelFace model in parallel. To prove the performance of both the speed and accuracy of PelFace, we carry out rigorous experiments using several popular benchmarks, including LFW, CFP-FP, and AgeDB-30, as well as two renovations of LFW: CALFW and CPLFW. The results of our experiments achieve state-of-the-art figures, which show the proposed method’s massive potential in improving face-based authentication performance. Ablation studies and overall benchmarks significantly confirm the effectiveness of our PelFace. Note to Practitioners —This paper motivates to construct and improve the discriminative power of face-based authentication based on Deep Convolutional Neural Networks (DCNN) for autonomous vehicles. Facial authentication is widely applied to identify or verify a user, but its accuracy and speeds still need improvement, especially for autonomous vehicles. Thus, in this work, we propose a parallel ensemble method called PelFace, by combing several novel DCNN models, such as CosFace, ArcFace, and MagFace. Our method is built by using the original Torch library for Python language. We also describe how such trained models can be combined to obtain SOTA performance, allowing us to reduce the time for loss function hyper-parameters tuning to get optimal models. In addition, we also indicate the drawback of the combination method as well as an approach to solving. Our experiments indicate that using this technique to create high-accuracy facial authentication is possible without expensive hardware. Current results of PelFace allow proving its ability to devote user authentication in autonomous vehicles, such as passenger identification and driver verification.

14 April 2025 in IEEE Access
Verified
Journal Article
Open access
ANAnh D. Nguyen
Anh D. Nguyen
HKHye-Young Kim
Hye-Young Kim
HNHoa Ngoc Nguyen
Hoa Ngoc Nguyen
In modern information exchange, document images are vital, often embedding sensitive data. The emergence of advanced image editing tools and generative AI models has elevated the risks associated with document forgery and tampering, representing considerable security concerns. Although many studies have been developed recently, they focus on images saved with compression factors. For lossless compression images like PNG images, current methods based on segmentation show low performance. Thus, this study tackles the specific challenges of identifying tampered text within lossless compression factor images. We introduce a lightweight and efficient model for document image tampering detection, named TALIU, which is based on segmentation networks. Our model employs an encoder-decoder architecture with a novel streamlined iterative upsampling decoder specifically designed for the context of document tampering. Moreover, we present an innovative data augmentation strategy, tampered region augmentation, intended to enhance sample diversity during the training phase. Extensive experiments utilizing the DocTamper dataset, the largest of its kind, show that our TALIU model surpasses current state-of-the-art methods in both detection accuracy and computational efficiency for the problem of tampered text in lossless compression factor images.


1 December 2022
Verified
Conference Paper
Open access
ANAnh Duc Nguyen
Anh Duc Nguyen
DNDat Trong Nguyen
Dat Trong Nguyen
PDPhuong Hanh DU
Phuong Hanh DU
HNHai Nam Dao Ngoc
Hai Nam Dao Ngoc
HNHoa Ngoc Nguyen
Hoa Ngoc Nguyen
In recent years, designing new effective Deep Convolutional Neural Network (DCNN) architectures and loss functions are two crucial trends in improving face recognition (FR) accuracy. However, building an optimal DCNN and ameliorating FR performance are still the main challenges for researchers. Thus, we first investigate and analyzes the effect of several novel effective loss functions based on softmax on DCNN with the ResNet architecture. We then propose an ensemble learning, namely EnsFace, by taking advantage of recent novel FR methods based on CosFace, ArcFace, and MagFace. EnsFace elaborates on the voting mechanism that utilizes non-optimal pre-trained models to obtain better discriminative ability for FR. To prove the performance of both the speed and accuracy of EnsFace, we carry out rigorous experiments using several popular benchmarks, including LFW, CFP-FP, and AgeDB-30, as well as two renovations of LFW: CALFW and CPLFW. The results of our experiments achieve state-of-the-art figures, which show the proposed method’s massive potential to improve FR performance. Ablation studies and overall benchmarks undeniably prove the effectiveness of our EnsFace.

1 January 2025 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
ANAnh D. Nguyen
Anh D. Nguyen
HNHoa Ngoc Nguyen
Hoa Ngoc Nguyen
Text-based person retrieval is defined as the challenging task of searching for people's images based on given textual queries in natural language. Conventional methods primarily use deep neural networks to understand the relationship between visual and textual data, creating a shared feature space for cross-modal matching. The absence of awareness regarding variations in feature granularity between the two modalities, coupled with the diverse poses and viewing angles of images corresponding to the same individual, may lead to overlooking significant differences within each modality and across modalities, despite notable enhancements. Furthermore, the inconsistency in caption queries in large public datasets presents an additional obstacle to cross-modality mapping learning. Therefore, we introduce 3RTPR, a novel text-based person retrieval method that integrates a representation fusing mechanism and an adaptive loss refinement algorithm into a dual-encoder branch architecture. Moreover, we propose training two independent models simultaneously, which reciprocally support each other to enhance learning effectiveness. Consequently, our approach encompasses three significant contributions: (i) proposing a fused representation method to generate more discriminative representations for images and captions; (ii) introducing a novel algorithm to adjust loss and prioritize samples that contain valuable information; and (iii) proposing reciprocal learning involving a pair of independent models, which allows us to enhance general retrieval performance. In order to validate our method's effectiveness, we also demonstrate superior performance over state-of-the-art methods by performing rigorous experiments on three well-known benchmarks: CUHK-PEDES, ICFG-PEDES, and RSTPReid.