Edges in image with illumination variations scenarios: a review Ali S. Abosinnee, Gergely Bencsik, Firas Abedi Visual Computer, 2025 Variations in lighting conditions significantly impact the accuracy of object detection in computer vision applications, particularly when relying on edge detection techniques. This paper presents a comprehensive review of the complexities and challenges associated with edge detection with respect to varying illumination. We analyze the effects of lighting fluctuations on edge detection and explore a wide range of applications where a thorough understanding of light changes is crucial for accurate object localization. Furthermore, this work offers an extensive survey of traditional and deep-learning-based edge detection methods, with a particular focus on techniques that effectively address illumination variations. We also explore commonly used datasets, metrics, and measures for evaluating edge detection performance. Additionally, we delve into current challenges in edge detection, proposing potential future research directions to bridge the gap between automated methods and human visual perception. This comprehensive review aims to contribute to the advancement of edge detection by providing valuable insights and guidance for researchers and practitioners in the field.
The Impact of Bio-Inspired Models on Edge Detection: a Survey Ali Abosinnee, Gergely Bencsik, Firas Abedi Proceedings of SPIE the International Society for Optical Engineering, 2025 Edges constitute a fundamental low-dimensional visual structure that plays a critical role in complex image analysis and comprehension. Their detection serves as an essential initial step in biometric object recognition and subsequent information processing. This paper critically reviews bio-inspired edge detection methods, which draw inspiration from the mechanisms of the human visual system, including classical and non-classical receptive fields (CRFs and nCRFs), hierarchical pathways, and contextual modulation. Traditional methods are lightweight and effective in noise suppression but lack scalability, global context integration, and biological complexity. Bio-inspired deep learning approaches combine these principles with neural networks, enhancing edge detection through hierarchical simulations, multi-scale processing, and feedback mechanisms. In addition, we review the most used metrics to evaluate the performance of the methods. This analysis highlights the strengths and limitations of traditional and hybrid approaches, providing insights into their potential to advance detection in complex visual environments.
Reinforcement Learning-Driven Task Offloading and Resource Allocation in Wireless IoT Networks Zahraa Hashim Kareem, Rami Qais Malik, Sarmad Jawad, Firas Abedi IEEE Access, 2025 Mobile IoT networks face major problems in completing efficient task offloading and allocating resources effectively, as all major actions require ample energy consumption and service delays. This paper proposes a solution in the form of a reinforcement learning-based framework that is capable of dynamically optimizing these activities with the help of Group Relative Policy Optimization (GRPO). The new method outcompetes traditional heuristic-nometric methods by being able to adjust device inactivity, network activity, and available resources. Devices are structured into mobility groups and task offloading is defined as an MDP or Markov Decision Process. An ample amount of offloading strategies can be obtained by introducing declaration of tasks and corresponding computers, network throughput, and queueing delays. Additionally, GRPO aids in the allocation of computing power, network bandwidth, or storage to maximize resource allocation without breaking task deadlines and other resource limitations. Comparing the GRPO-based method to traditional methods via simulation showed increased performance and reduced service delay. The results clearly demonstrate that GRPO helps reduce service delay and consumption of energy significantly in high load with high dynamism conditions. With the inclusion of decision-making processes along with constraint-tolerance and reinforcement learning, this research aids in IoT frameworks that require low energy output with less delay. The recommended method helps build a strong base for efficient task delegation alongside increased performance and scalability, which subsequently enhances AI edge computing and smart management of IoT systems.
A survey on deep reinforcement learning architectures, applications and emerging trends Surjeet Balhara, Nishu Gupta, Ahmed Alkhayyat, Isha Bharti, Rami Q. Malik, Sarmad Nozad Mahmood, Firas Abedi Iet Communications, 2025 Abstract From a future perspective and with the current advancements in technology, deep reinforcement learning (DRL) is set to play an important role in several areas like transportation, automation, finance, medical and in many more fields with less human interaction. With the popularity of its fast‐learning algorithms there is an exponential increase in the opportunities for handling dynamic environments without any explicit programming. Additionally, DRL sophisticatedly handles real‐world complex problems in different environments. It has grasped great attention in the areas of natural language processing (NLP), speech recognition, computer vision and image classification which has led to a drastic increase in solving complex problems like planning, decision‐making and perception. This survey provides a comprehensive analysis of DRL and different types of neural network, DRL architectures, and their real‐world applications. Recent and upcoming trends in the field of artificial intelligence (AI) and its categories have been emphasized and potential challenges have been discussed.
Multi-objective optimization for vector quantization via genetic algorithm Firas Abedi, Ahmed Fahim Al-Baghdadi Optics Continuum, 2024 The issue of image compression continues to be a subject of ongoing research within the domain of image processing, particularly in the context of medical applications. The quality of the decompressed image can vary depending on the accuracy of the compression technique, resulting in either fine or distorted details. Therefore, the diagnostic procedure performed by medical professionals is contingent upon the precision of the compression and decompression process. In addition, the compression of medical images serves to decrease the amount of storage required, thereby enabling faster transmission over computer networks through the reduction of their bit size. This paper proposes a hybrid mix of the discrete wavelet transform (DWT) technique and vector quantization (VQ) to improve the compression technique of medical images. The aim of the proposed compression technique is to preserve diagnostic image information while achieving a high compression ratio. First, noise in medical images is caused by salt pepper noise. At the same time, the edges of the images are maintained in sharpness and context. Then, a lossless compression method is applied to the wavelet coefficients of the subband with the lowest frequency, while the thresholding method was used to efficiently construct coefficients for high-frequency sub-bands. This process will produce a traditional VQ, which is estimated via the Genetic Algorithm (GA) with fuzzy clustering. While Arithmetic encoded theory was being utilized to quantize coefficients, the proposed compression technique was evaluated by dividing the image into two levels and three levels of sub-bands, respectively, in two different scenarios. Comparing the decompressed image to the filtered image by means of different evaluation metrics, the proposed method can enhance compression performance and strike a balance between compression ratio and image visual quality.
Energy Efficient Improving Routing Model for UAVs Assisted Vehicular Adhoc Networks Ali Alsalamy, Firas Abedi, Fatima Hashim Abbas, Mohammed S. Noori, Mohamed Ayad Alkhafaji, Ahmed Alkhayyat, Sameer Alani, Muhammet Tahir Guneser, Sarmad Nozad Mahmood 2023 International Conference in Advances in Power Signal and Information Technology Apsit 2023, 2023
Hybrid Deep Learning Enabled Load Prediction for Energy Storage Systems Firas Abedi, Hayder M. A. Ghanimi, Mohammed A. M. Sadeeq, Ahmed Alkhayyat, Zahraa H. Kareem, Sarmad Nozad Mahmood, Ali Hashim Abbas, Ali S. Abosinnee, Waleed Khaild Al-Azzawi, Mustafa Musa Jaber, Mohammed Dauwed Computers Materials and Continua, 2023
Severity Based Light-Weight Encryption Model for Secure Medical Information System Firas Abedi, Subhi R.M. Zeebaree, Zainab Salih Ageed, Hayder M.A. Ghanimi, Ahmed Alkhayyat, Mohammed A.M. Sadeeq, Sarmad Nozad Mahmood, Ali S. Abosinnee, Zahraa H. Kareem, Ali Hashim Abbas, Waleed Khaild Al-Azzawi, Mustafa Musa Jaber, Mohammed Dauwed Computers Materials and Continua, 2023
Adaptive Filter Predistorter for Memory Saleh Model Firas Abedi, Hassoon Salman Fahama, Ayad Hamzah, Firas Mohammed Iiceta 2022 5th International Conference on Engineering Technology and Its Applications, 2022
Development of a Wireless Electromyography System Mohammed Najeh Nemah, Ghufran Mahdi Hatem, Firas Abedi, Ali N Jamaluddin, Ali S. Abosinnee Iiceta 2022 5th International Conference on Engineering Technology and Its Applications, 2022
Histogram Features Extraction for Edge Detection Approach Fallah H. Najjar, Kifah T. Khudhair, Ali Hussein Abdul Khaleq, Ola N. Kadhim, Firas Abedi, Ibrahim H. Al-Kharsan Iiceta 2022 5th International Conference on Engineering Technology and Its Applications, 2022
Soft Edge Detection by Mamdani Fuzzy Inference of Color Image Kifah T. Khudhair, Ola N. Kadhim, Fallah H. Najjar, Firas Abedi, Ali N. Jamaluddin, Ibrahim H. Al-Kharsan Iiceta 2022 5th International Conference on Engineering Technology and Its Applications, 2022
Investigating the Feasibility to Identify Oil Well Holes Ali N Jamaluddin, Firas Abedi, Yaser Norouzi, Gholamreza Moradi, Zaid Abdulkareem Naji, Ihab Mahdi Almaameri, Rand Muwafaq Hadi Iiceta 2022 5th International Conference on Engineering Technology and Its Applications, 2022
Authentication and revocation scheme for VANETs based on chinese remainder theorem Murtadha A. Alazzawi, Kai Chen, Ali A. Yassin, Hongwei Lu, Firas Abedi Proceedings 21st IEEE International Conference on High Performance Computing and Communications 17th IEEE International Conference on Smart City and 5th IEEE International Conference on Data Science and Systems Hpcc Smartcity Dss 2019, 2019
