Chen Soong Der
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Chen Soong Der has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Leong Yeng Weng
Department of Electrical & Electronic Engineering, College of Engineering, Universiti Tenaga Nasional, Kajang 43000, Malaysia
3 shared publications - Abdul Hadi Mohammed Alaidi
Computer Department, College of Computer Science and Information Technology, Wasit University, Wasit, Iraq
2 shared publications - Chai Phing Chen
Universiti Tenaga Nasional (UNITEN)
2 shared publications - Malik Kareem Kadhim
College of Engineering, Universiti Tenaga Nasional Selangor 1 , Kajang
2 shared publications - Abdul-Hadi Al-Hassani
Iraq University College, Basrah, Iraq
1 shared publication - Dalal Abdulmohsin Hammood
Middle Technical University
1 shared publication
Latest Publications
- 5 May 2026
- Published by Springer Nature in Neural Computing and Applications
- Vol. 38 (10) , 357
Ensemble-based decision support for X-ray threat detection: a review and hybrid MCDM framework under uncertainty
- 5 May 2026
- Published by Springer Nature in Neural Computing and Applications
- Vol. 38 (10) , 357
Ensemble-based decision support for X-ray threat detection: a review and hybrid MCDM framework under uncertainty
- Open Access
- 17 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 143020-143030
ARI-ORB: Adaptive Rotation-Invariant ORB for Enhanced Feature Matching in Dental X-Ray Imaging
Feature matching occupies a significant place in computer vision and some algorithms for speed and accuracy with an equal ratio includes ORB, SIFT, and AKAZE. In this paper, we propose a new modified ORB feature matching approach named ARI-ORB, incorporating the Rotation- Invariant capability for generating a more adaptive. Recent developments have pointed out a need for permutation invariant deep learning models that can be applied on Dental Panoramic X-Ray images. Thus, ARI-ORB coping with problems studied from noisy and rotationally varied datasets employs the three sub-modules: descriptor aggregation, rotation invariance, and adaptive key-point selection. Experimental analysis of the proposed ARI-ORB approach on separate dental X-ray datasets yields 82.55% precision, 83.13% accuracy, 82.55% recall, 82.55% F1 score, and a PDR of 41.28%. Compared to baseline algorithms, ARI-ORB significantly outperforms ORB (F1: 58.40, PDR: 29.20), SIFT with (F1 value: 46.71, PDR: 23.35), AKAZE with (F1 value of: 53.74 PDR: 26.87), BRISK with (F1 value: 36.03, PDR: 18.01), FAST (F1: 17.42 PDR: 8.71). Moreover, the average execution time was 0.1548 seconds per image, indicating good computational performance. Described visualizations of feature matches and match distance distributions show that the method is viable, especially in adverse imaging conditions.
- 17 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 143020-143030
Open AccessARI-ORB: Adaptive Rotation-Invariant ORB for Enhanced Feature Matching in Dental X-Ray Imaging
Feature matching occupies a significant place in computer vision and some algorithms for speed and accuracy with an equal ratio includes ORB, SIFT, and AKAZE. In this paper, we propose a new modified ORB feature matching approach named ARI-ORB, incorporating the Rotation- Invariant capability for generating a more adaptive. Recent developments have pointed out a need for permutation invariant deep learning models that can be applied on Dental Panoramic X-Ray images. Thus, ARI-ORB coping with problems studied from noisy and rotationally varied datasets employs the three sub-modules: descriptor aggregation, rotation invariance, and adaptive key-point selection. Experimental analysis of the proposed ARI-ORB approach on separate dental X-ray datasets yields 82.55% precision, 83.13% accuracy, 82.55% recall, 82.55% F1 score, and a PDR of 41.28%. Compared to baseline algorithms, ARI-ORB significantly outperforms ORB (F1: 58.40, PDR: 29.20), SIFT with (F1 value: 46.71, PDR: 23.35), AKAZE with (F1 value of: 53.74 PDR: 26.87), BRISK with (F1 value: 36.03, PDR: 18.01), FAST (F1: 17.42 PDR: 8.71). Moreover, the average execution time was 0.1548 seconds per image, indicating good computational performance. Described visualizations of feature matches and match distance distributions show that the method is viable, especially in adverse imaging conditions.
- Open Access
- 1 March 2025
- Published by AIP Publishing in AIP Advances
- Vol. 15 (3)
A new approach combining CNN, RNN, and an improved Otsu threshold method for detecting hand gestures in people with thumb finger size problems and hand tremors
The recognition of hand gestures involves the application of mathematical algorithms to detect human movements, with diverse applications in communication for the hearing impaired, human–computer interaction, autonomous driving, and virtual environments. This research presents a comprehensive approach to identifying dynamic hand gestures, which is particularly beneficial for individuals with finger disabilities. In addition, those with hand tremors may encounter challenges when using human–computer interaction devices. The proposed technique enhances the sensitivity of these devices through an advanced Otsu segmentation method. It begins by isolating hand gestures from complex backgrounds using this sophisticated segmentation algorithm and incorporates motion data derived from RGB video sequences. The gestures are then transformed into texture and contour characteristics, which are subsequently input into a hybrid architecture that combines a convolutional neural network (CNN) with a recurrent neural network (RNN). Our findings demonstrate that the proposed method achieves superior segmentation results to existing alternatives and can detect finger joint interactions and tremors with high sensitivity. When comparing the traditional Otsu method with our proposed Otsu method, our results indicate an improvement of 6.3% in accuracy for the CNN and RNN classifiers. The performance of the novel Otsu method has been evaluated and compared using accuracy and sensitivity metrics, yielding significant results.
- 1 March 2025
- Published by AIP Publishing in AIP Advances
- Vol. 15 (3)
Open AccessA new approach combining CNN, RNN, and an improved Otsu threshold method for detecting hand gestures in people with thumb finger size problems and hand tremors
The recognition of hand gestures involves the application of mathematical algorithms to detect human movements, with diverse applications in communication for the hearing impaired, human–computer interaction, autonomous driving, and virtual environments. This research presents a comprehensive approach to identifying dynamic hand gestures, which is particularly beneficial for individuals with finger disabilities. In addition, those with hand tremors may encounter challenges when using human–computer interaction devices. The proposed technique enhances the sensitivity of these devices through an advanced Otsu segmentation method. It begins by isolating hand gestures from complex backgrounds using this sophisticated segmentation algorithm and incorporates motion data derived from RGB video sequences. The gestures are then transformed into texture and contour characteristics, which are subsequently input into a hybrid architecture that combines a convolutional neural network (CNN) with a recurrent neural network (RNN). Our findings demonstrate that the proposed method achieves superior segmentation results to existing alternatives and can detect finger joint interactions and tremors with high sensitivity. When comparing the traditional Otsu method with our proposed Otsu method, our results indicate an improvement of 6.3% in accuracy for the CNN and RNN classifiers. The performance of the novel Otsu method has been evaluated and compared using accuracy and sensitivity metrics, yielding significant results.
- 21 January 2025
- Published by IOP Publishing in Engineering Research Express
- Vol. 7 (1) , 015228
Enhanced dynamic hand gesture recognition for finger disabilities using deep learning and an optimized Otsu threshold method
Hand gestures serve as a powerful means of communication, capable of conveying extensive information across various public health domains, including medicine and education. The process of hand gesture recognition involves the use of mathematical algorithms to identify human gestures and finds applications in areas such as communication for the deaf, human-computer interaction, intelligent driving, and virtual reality. This study introduces a robust method aimed at recognizing dynamic hand gestures, particularly for individuals with finger disabilities. The approach begins with segmenting hand gestures from intricate backgrounds using an advanced Otsu segmentation algorithm, while also integrating motion data from RGB video sequences. Hand gestures are transformed into texture and contour features, which are utilized as input for a hybrid model that merges a convolutional neural network (CNN) with a recurrent neural network (RNN). The model employs Inception-v3 for feature extraction complemented by an LSTM layer for classification. The focus of the study is on recognizing six dynamic gestures, with particular emphasis on ‘scroll right’ and ‘scroll down’ due to their high accuracy in recognition. The model demonstrated an average precision of 84.34% across all gestures, achieving 87.57% for gestures involving finger impairments. These results highlight the model’s effectiveness in practical applications for dynamic hand gesture recognition.
- 21 January 2025
- Published by IOP Publishing in Engineering Research Express
- Vol. 7 (1) , 015228
Enhanced dynamic hand gesture recognition for finger disabilities using deep learning and an optimized Otsu threshold method
Hand gestures serve as a powerful means of communication, capable of conveying extensive information across various public health domains, including medicine and education. The process of hand gesture recognition involves the use of mathematical algorithms to identify human gestures and finds applications in areas such as communication for the deaf, human-computer interaction, intelligent driving, and virtual reality. This study introduces a robust method aimed at recognizing dynamic hand gestures, particularly for individuals with finger disabilities. The approach begins with segmenting hand gestures from intricate backgrounds using an advanced Otsu segmentation algorithm, while also integrating motion data from RGB video sequences. Hand gestures are transformed into texture and contour features, which are utilized as input for a hybrid model that merges a convolutional neural network (CNN) with a recurrent neural network (RNN). The model employs Inception-v3 for feature extraction complemented by an LSTM layer for classification. The focus of the study is on recognizing six dynamic gestures, with particular emphasis on ‘scroll right’ and ‘scroll down’ due to their high accuracy in recognition. The model demonstrated an average precision of 84.34% across all gestures, achieving 87.57% for gestures involving finger impairments. These results highlight the model’s effectiveness in practical applications for dynamic hand gesture recognition.
- Open Access
- 2 December 2024
- Published by Engineering, Technology & Applied Science Research in Engineering, Technology & Applied Science Research
- Vol. 14 (6) , 18401-18408
Advancements and Challenges: A Comprehensive Review of GAN-based Models for the Mitigation of Small Dataset and Texture Sticking Issues in Fake License Plate Recognition
This review paper critically examines the recent advancements in refining Generative Adversarial Networks (GANs) to address the challenges posed by small datasets and the persisting issue of texture sticking in the domain of fake license plate recognition. Recognizing the limitations posed by insufficient data, the survey begins with an exploration of various GAN architectures, including pix2pix_GAN, CycleGAN, and SRGAN, that have been employed to synthesize diverse and realistic license plate images. Notable achievements include high accuracy in License Plate Character Recognition (LPCR), advancements in generating new format license plates, and improvements in license plate detection using YOLO. The second focal point of this review centers on mitigating the texture sticking problem, a crucial concern in GAN-generated content. Recent enhancements, such as the integration of StyleGAN2-ADA and StyleGAN3, aim to address challenges related to texture dynamics during video generation. Additionally, adaptive data augmentation mechanisms have been introduced to stabilize GAN training, particularly when confronted with limited datasets. The synthesis of these findings provides a comprehensive overview of the evolving landscape in mitigating challenges associated with small datasets and texture sticking in fake license plate recognition. The review not only underscores the progress made but also identifies emerging trends and areas for future exploration. These insights are vital for researchers, practitioners, and policymakers aiming to bolster the effectiveness and reliability of GAN-based models in the critical domain of license plate recognition.
- 2 December 2024
- Published by Engineering, Technology & Applied Science Research in Engineering, Technology & Applied Science Research
- Vol. 14 (6) , 18401-18408
Open AccessAdvancements and Challenges: A Comprehensive Review of GAN-based Models for the Mitigation of Small Dataset and Texture Sticking Issues in Fake License Plate Recognition
This review paper critically examines the recent advancements in refining Generative Adversarial Networks (GANs) to address the challenges posed by small datasets and the persisting issue of texture sticking in the domain of fake license plate recognition. Recognizing the limitations posed by insufficient data, the survey begins with an exploration of various GAN architectures, including pix2pix_GAN, CycleGAN, and SRGAN, that have been employed to synthesize diverse and realistic license plate images. Notable achievements include high accuracy in License Plate Character Recognition (LPCR), advancements in generating new format license plates, and improvements in license plate detection using YOLO. The second focal point of this review centers on mitigating the texture sticking problem, a crucial concern in GAN-generated content. Recent enhancements, such as the integration of StyleGAN2-ADA and StyleGAN3, aim to address challenges related to texture dynamics during video generation. Additionally, adaptive data augmentation mechanisms have been introduced to stabilize GAN training, particularly when confronted with limited datasets. The synthesis of these findings provides a comprehensive overview of the evolving landscape in mitigating challenges associated with small datasets and texture sticking in fake license plate recognition. The review not only underscores the progress made but also identifies emerging trends and areas for future exploration. These insights are vital for researchers, practitioners, and policymakers aiming to bolster the effectiveness and reliability of GAN-based models in the critical domain of license plate recognition.
- Open Access
- 1 January 2023
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 2804 (1) , 020002
Image denoising techniques: An overview
This article provides an in-depth overview of image denoising. Furthermore, the technical aspects developed for image denoising are highlighted in a wider sense
- 1 January 2023
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 2804 (1) , 020002
Open AccessImage denoising techniques: An overview
This article provides an in-depth overview of image denoising. Furthermore, the technical aspects developed for image denoising are highlighted in a wider sense
- Open Access
- 15 December 2022
- Published by Engineering, Technology & Applied Science Research in Engineering, Technology & Applied Science Research
- Vol. 12 (6) , 9732-9736
Increased Efficiency of the Artificial Bee Colony Algorithm Using the Pheromone Technique
Artificial Bee Colony (ABC) is a powerful metaheuristic algorithm inspired by the behavior of a honey bee swarm. ABC suffers from poor exploitation and, in some cases, poor exploration. Ant Colony Optimization (ACO) is another metaheuristic algorithm that uses pheromones as a guide for an ant to find its way. This study used a pheromone technique from ACO on ABC to enhance its exploration and exploitation. The performance of the proposed method was verified through twenty instances from TSPLIB. The results were compared with the original ABC method and showed that the proposed method leverages the performance of ABC.
- 15 December 2022
- Published by Engineering, Technology & Applied Science Research in Engineering, Technology & Applied Science Research
- Vol. 12 (6) , 9732-9736
Open AccessIncreased Efficiency of the Artificial Bee Colony Algorithm Using the Pheromone Technique
Artificial Bee Colony (ABC) is a powerful metaheuristic algorithm inspired by the behavior of a honey bee swarm. ABC suffers from poor exploitation and, in some cases, poor exploration. Ant Colony Optimization (ACO) is another metaheuristic algorithm that uses pheromones as a guide for an ant to find its way. This study used a pheromone technique from ACO on ABC to enhance its exploration and exploitation. The performance of the proposed method was verified through twenty instances from TSPLIB. The results were compared with the original ABC method and showed that the proposed method leverages the performance of ABC.
- Open Access
- 15 December 2022
- Published by Engineering, Technology & Applied Science Research in Engineering, Technology & Applied Science Research
- Vol. 12 (6) , 9510-9514
Artificial Bee Colony with Crossover Operations for Discrete Problems
The Artificial Bee Colony (ABC) is an algorithm designed to solve continuous problems. ABC has been proven to be more effective than other biological-inspired algorithms. However, it is needed to modify its functionality in order to solve a discrete problem. In this work, a natural modification to the original ABC is made to make it able to solve discrete problems. Six neighborhood operators are proposed to simulate the original behavior of ABC. Moreover, several Traveling Salesman Problem Library (TSPLIB) problems were used to examine the proposed method. The results of the proposed method are promising.
- 15 December 2022
- Published by Engineering, Technology & Applied Science Research in Engineering, Technology & Applied Science Research
- Vol. 12 (6) , 9510-9514
Open AccessArtificial Bee Colony with Crossover Operations for Discrete Problems
The Artificial Bee Colony (ABC) is an algorithm designed to solve continuous problems. ABC has been proven to be more effective than other biological-inspired algorithms. However, it is needed to modify its functionality in order to solve a discrete problem. In this work, a natural modification to the original ABC is made to make it able to solve discrete problems. Six neighborhood operators are proposed to simulate the original behavior of ABC. Moreover, several Traveling Salesman Problem Library (TSPLIB) problems were used to examine the proposed method. The results of the proposed method are promising.
- Open Access
- 6 November 2019
- Published by Area de Innovacion y Desarrollo, S.L. 3 Ciencias in 3C Tecnología_Glosas de innovación aplicadas a la pyme
- No. SI,p. 329-347
Study on enhancing the energy efficiency through real-time smart energy management systems for achieving green ICT campus
- 6 November 2019
- Published by Area de Innovacion y Desarrollo, S.L. 3 Ciencias in 3C Tecnología_Glosas de innovación aplicadas a la pyme
- No. SI,p. 329-347
Open AccessStudy on enhancing the energy efficiency through real-time smart energy management systems for achieving green ICT campus
- 15 December 2013
- Published by Science Alert in Journal of Applied Sciences
- Vol. 14 (1) , 18-25
A Statistical Evaluation of Image Quality Analyzer for Assessment of Histogram Equalization-based Contrast Enhancement Methods
- 15 December 2013
- Published by Science Alert in Journal of Applied Sciences
- Vol. 14 (1) , 18-25
A Statistical Evaluation of Image Quality Analyzer for Assessment of Histogram Equalization-based Contrast Enhancement Methods