Electrical and Electronic Engineering, Hardware and Architecture, Computer Vision and Pattern Recognition, Signal Processing
77
Scopus Publications
1026
Scholar Citations
16
Scholar h-index
29
Scholar i10-index
Scopus Publications
YOLO11-MSCA: A Multi-Scale Channel Attention Model for Lumbar Vertebra Detection in X-Ray Images Hana Ben Fredj, Hatem Garrab, Chokri Souani Electronics Switzerland, 2026 Automated identification of lumbar vertebrae plays a key role in modern spine analysis, offering valuable assistance for diagnostic assessment and preoperative decision-making. Despite recent progress in deep learning-based detection methods, accurately localizing vertebral structures remains challenging due to anatomical variability and heterogeneous image quality. To address the difficulty of capturing subtle vertebral structures, we introduce a Multi-Scale Channel Attention Block (MSCABlock) integrated into the YOLO11 backbone. Unlike conventional attention-based or multi-scale convolutional designs, MSCABlock jointly exploits channel-wise feature interaction and multi-scale receptive fields to enhance both local detail sensitivity and contextual representation, while preserving computational efficiency. The proposed approach is designed to improve detection performance without significantly increasing model complexity. Our model is trained and validated using only the AP-view images from the Burapha University Lumbar-Spine Dataset (BUU-LSPINE), which provides well-annotated lumbar spine X-ray images from 400 unique patients. The proposed approach operates in a fully end-to-end manner, allowing vertebrae to be identified directly from input images without relying on handcrafted feature engineering or complex preprocessing pipelines. Experimental evaluations show that the proposed model achieves strong detection performance, with mAP@0.5 and mAP@0.5–0.95 reaching 0.982 and 0.79, respectively, alongside a precision of 0.93 and a recall of 0.975. Compared with the YOLO11 baseline, ablation and efficiency analyses demonstrate that MSCABlock consistently improves detection performance. It introduces only marginal increases in model parameters and computational cost, thereby preserving a lightweight architecture and maintaining efficient inference. These results show that the optimized YOLO11-based system generalizes well across lumbar levels. It maintains reliable detection under challenging conditions, providing robust automated localization to support large-scale clinical spine analysis.
YOLO-TSR: A Novel YOLOv8-Based Network for Robust Traffic Sign Recognition Wajdi Farhat, Olfa Ben Rhaiem, Hassene Faiedh, Chokri Souani Transportation Research Record, 2025 Self-driving cars have recently gained in popularity. This is because of rapid advances in vehicle and artificial intelligence technology. Autonomous cars’ ability to drive effectively and safely depends heavily on their capacity to recognize traffic signs. Traditional visual recognition of things, conversely, relies heavily on the extraction of visual features, such as color and edge. Despite these efforts, the varying appearance of road signs across geographical areas, lighting changes, and complex background situations continues to prevent the development of accurate traffic sign recognition platforms. In this paper, we present YOLO-TSR, a novel network based on YOLOv8 that innovatively tackles the challenges encountered in road sign recognition (TSR). Our intention is to provide a method to detect and recognize traffic signs in complex situations and under varying weather conditions. The proposed method was validated against three separate traffic sign datasets: our privately curated dataset, the widely recognized German Traffic Sign Recognition Benchmark (GTSRB) dataset, and the Belgium Traffic Sign Dataset. We conducted numerous experiments to validate the proposed algorithm’s effectiveness. The proposed algorithm achieves 98.79% accuracy, 92.18% recall, 96.21% mAP@0.5, and 84.32% mAP@0.5:0.95 for the GTSRB dataset. For our private dataset, the algorithm had an accuracy of 96.62%, a recall of 90.81%, mAP@0.5 of 94.83%, and mAP@0.5:0.95 of 81.70%. Furthermore, the algorithm maintains a consistent frame rate of 73 frames per second, which meets real-time detection requirements.
Medical Images Classification Using Convolutional Neural Network Hana Ben Fredj, Yosra Ben Fadhel, Chokri Souani 22nd IEEE International Multi Conference on Systems Signals and Devices Ssd 2025, 2025 The World Health Organization has announced the most recent coronavirus-related disease, Covid-19 (Coronavirus Disease-2019), a pandemic. In addition, the worldwide lockdown implementation has made the whole globe to have millions of people dead. Added to the fact of being extremely contagious, this virus has a high mortality rate. In other words, it puts pressure on the healthcare system because of infecting many individuals. Therefore, identifying Covid-19 has become critical. In fact, this study aims to apply X-ray as well as Computed Tomography (CT) augmented datasets in order to realize a deep learning technique based on the Convolutional Neural Network (CNN) to immediately detect and diagnose Covid-19. With an efficient loss function, we have typically developed our deep learning model performance. Furthermore, the proposed system carried out high Covid-19 detection performance with a significant accuracy.
Embedded System for Real-time Traffic Signs Recognition with Augmented Reality Implemented in ARM Amani Chebbah, Hana Ben Fredj, Chokri Souani 22nd IEEE International Multi Conference on Systems Signals and Devices Ssd 2025, 2025 Automatic detection and recognition of traffic signs improve driving safety by alerting drivers to hazards they may not perceive. This paper proposes an embedded real-time methodology for traffic sign detection and recognition, enhanced with augmented reality to increase driver vigilance. The algorithm operates in three stages: detection, recognition, and augmented reality merging. Color filtering and shape matching are used to extract Regions Of Interest (ROIs), followed by a Haar cascade classifier for detection and categorization. The recognition stage utilizes the ORB algorithm. Implemented on an ARM platform, the system achieves 96 % accuracy in detection and recognition at 12 fps in real-world conditions.
Yolo Deep Model for Pallet Recognition Contribution into Industrial Area Anis Ammar, Rim Ghozzi, Souhir Sghaier, Gassab Aziz, Chokri Souani Proceedings of 2025 4th International Conference on Computing and Information Technology Iccit 2025, 2025 Recent object detection developments have been largely influenced by advances in the field of deep learning. In this context, we have developed a pallet detection model integrated into a forklift robot in order to optimize the picking process in storage and logistics environments in industrial settings. The project based on the architecture of the YOLO (You Only Look Once) model to improve pallet recognition and estimation of position and distance allowing robots to autonomously locate and pick pallets. This model stands out for its ability to provide fast and accurate object detection in high-resolution images, making them particularly suitable for real-time applications such as robotics and logistics.
Robotic Exoskeleton for Upper Arm Stroke Rehabilitation Rim Ghozzi, Anis Ammar, Mahmoud Hammouda, Jasser Hadj Ali, Samer Lahouar, et al. Proceedings of 2025 4th International Conference on Computing and Information Technology Iccit 2025, 2025
An efficient face recognition method using CNN Hana ben Fredj, Souhir Sghaier, Chokri Souani 2021 International Conference of Women in Data Science at Taif University Widstaif 2021, 2021
FFT implementation and optimization on FPGA Tarek Belabed, Sabeur Jemmali, Chokri Souani 2018 4th International Conference on Advanced Technologies for Signal and Image Processing Atsip 2018, 2018
DSP implementation and performances evaluation of JPEG2000 wavelet filters Biosignals 2008 Proceedings of the 1st International Conference on Bio Inspired Systems and Signal Processing, 2008
Optimized VLSI design of wavelet transform architecture Proceedings of the International Conference on Microelectronics Icm, 2004
YOLO11-MSCA: A Multi-Scale Channel Attention Model for Lumbar Vertebra Detection in X-Ray Images HB Fredj, H Garrab, C Souani Electronics 15 (7), 1341 , 2026 2026
A novel architecture for efficient pedestrian detection in autonomous vehicles W Farhat, O Ben Rhaiem, H Faiedh, C Souani Connection Science 37 (1), 2529261 , 2025 2025 Citations: 3
An IoT-Based Smart Agriculture System Using LoRa and Cloud Monitoring for Automated Greenhouse Control NB Abid, AM Khattab, HAM Harb, C Souani International Journal of Computer Applications 187 (52), 7-15 , 2025 2025 Citations: 2
Pedestrian detection and tracking using an enhanced YOLOv9 model for automotive vehicles W Farhat, OB Rhaiem, H Faiedh, C Souani Measurement 254, 118009 , 2025 2025 Citations: 14
Intelligent collision avoidance system for urban scenarios using deep learning W Farhat, M Guizani, O Ben Rhaiem, H Faiedh, C Souani Proceedings of the Institution of Mechanical Engineers, Part D: Journal of … , 2025 2025
Real-Time Traffic Analysis: Data processing using MQTT and InfluxDB YR Slim, J Ferreira, C Souani 2025 International Conference on Control, Automation and Diagnosis (ICCAD), 1-5 , 2025 2025
YOLO-TSR: a novel YOLOv8-based network for robust traffic sign recognition W Farhat, OB Rhaiem, H Faiedh, C Souani Transportation Research Record 2679 (7), 443-466 , 2025 2025 Citations: 7
A robust deep learning-based system for pedestrian-aware collision prevention in autonomous vehicles W Farhat, M Guizani, OB Rhaiem, R Zaghdoud, H Faiedh, C Souani International Journal of Transportation Science and Technology , 2025 2025 Citations: 1
TraSFlow: learning traditional optical flow proposal and segmentation for optical flow estimation improvement A Ammar, R Ghozzi, C Souani Signal, Image and Video Processing 19 (6), 462 , 2025 2025 Citations: 1
Robotic Exoskeleton for Upper Arm Stroke Rehabilitation R Ghozzi, A Ammar, M Hammouda, JH Ali, S Lahouar, C Souani 2025 4th International Conference on Computing and Information Technology … , 2025 2025
Yolo Deep Model for Pallet Recognition Contribution into Industrial Area A Ammar, R Ghozzi, S Sghaier, G Aziz, C Souani 2025 4th International Conference on Computing and Information Technology … , 2025 2025 Citations: 1
Optimized deep learning for pedestrian safety in autonomous vehicles W Farhat, OB Rhaiem, H Faiedh, C Souani International Journal of Transportation Science and Technology , 2025 2025 Citations: 6
Embedded system for real-time traffic signs recognition with augmented reality implemented in ARM A Chebbah, HB Fredj, C Souani 2025 IEEE 22nd International Multi-Conference on Systems, Signals & Devices … , 2025 2025 Citations: 1
Medical Images Classification Using Convolutional Neural Network HB Fredj, YB Fadhel, C Souani 2025 IEEE 22nd International Multi-Conference on Systems, Signals & Devices … , 2025 2025
A novel cooperative collision avoidance system for vehicular communication based on deep learning W Farhat, O Ben Rhaiem, H Faiedh, C Souani International Journal of Information Technology 16 (3), 1661-1675 , 2024 2024 Citations: 20
An Intelligent Collision Avoidance System Utilizing YOLOv8-Based Deep Learning W Farhat, S BenOthmen, OB Rhaiem, H Faiedh, C Souani 2024
Robust Face Verification Using Deep Learning in Uncontrolled HB Fredj, R Ghozzi, C Souani Selected Studies in Geotechnics, Geo-informatics and Remote Sensing … , 2023 2023
An efficient implementation of traffic signs recognition system using CNN HB Fredj, A Chabbah, J Baili, H Faiedh, C Souani Microprocessors and Microsystems 98, 104791 , 2023 2023 Citations: 38
Improved architecture for traffic sign recognition using a self-regularized activation function: SigmaH S Bouguezzi, H Ben Fredj, H Faiedh, C Souani The Visual Computer 38 (11), 3747-3764 , 2022 2022 Citations: 11
Comparative study of latest cnn based optical flow estimation A Ammar, A Chebbah, HB Fredj, C Souani 2022 International Conference on Intelligent Systems and Computer Vision … , 2022 2022 Citations: 11
MOST CITED SCHOLAR PUBLICATIONS
Face recognition in unconstrained environment with CNN H Ben Fredj, S Bouguezzi, C Souani The Visual Computer 37 (2), 217-226 , 2021 2021 Citations: 157
Efficient algorithm for automatic road sign recognition and its hardware implementation C Souani, H Faiedh, K Besbes Journal of real-time image processing 9 (1), 79-93 , 2014 2014 Citations: 74
An efficient FPGA-based convolutional neural network for classification: Ad-MobileNet S Bouguezzi, HB Fredj, T Belabed, C Valderrama, H Faiedh, C Souani Electronics 10 (18), 2272 , 2021 2021 Citations: 59
Design of efficient embedded system for road sign recognition W Farhat, S Sghaier, H Faiedh, C Souani Journal of Ambient Intelligence and Humanized Computing 10 (2), 491-507 , 2019 2019 Citations: 50
Real-time embedded system for traffic sign recognition based on ZedBoard W Farhat, H Faiedh, C Souani, K Besbes Journal of Real-Time Image Processing 16 (5), 1813-1823 , 2019 2019 Citations: 42
An efficient implementation of traffic signs recognition system using CNN HB Fredj, A Chabbah, J Baili, H Faiedh, C Souani Microprocessors and Microsystems 98, 104791 , 2023 2023 Citations: 38
User driven FPGA-based design automated framework of deep neural networks for low-power low-cost edge computing T Belabed, MGF Coutinho, MAC Fernandes, CV Sakuyama, C Souani IEEE Access 9, 89162-89180 , 2021 2021 Citations: 31
Hardware implementation of tanh exponential activation function using fpga S Bouguezzi, H Faiedh, C Souani 2021 18th International Multi-Conference on Systems, Signals & Devices (SSD … , 2021 2021 Citations: 30
VLSI design of 1-D DWT architecture with parallel filters C Souani, M Abid, K Torki, R Tourki Integration 29 (2), 181-207 , 2000 2000 Citations: 30
Novel technique for 3D face recognition using anthropometric methodology S Sghaier, W Farhat, C Souani International Journal of Ambient Computing and Intelligence (IJACI) 9 (1), 60-77 , 2018 2018 Citations: 29
Automatic crack detection from pavement images using fuzzy thresholding NBC Ahmed, S Lahouar, C Souani, K Besbes 2017 international conference on control, automation and diagnosis (ICCAD … , 2017 2017 Citations: 29
Accurate realtime motion estimation using optical flow on an embedded system A Ammar, HB Fredj, C Souani Electronics 10 (17), 2164 , 2021 2021 Citations: 28
Parallel implementation of Sobel filter using CUDA HB Fredj, M Ltaif, A Ammar, C Souani 2017 International Conference on Control, Automation and Diagnosis (ICCAD … , 2017 2017 Citations: 25
A novel cooperative collision avoidance system for vehicular communication based on deep learning W Farhat, O Ben Rhaiem, H Faiedh, C Souani International Journal of Information Technology 16 (3), 1661-1675 , 2024 2024 Citations: 20
Slim mobilenet: An enhanced deep convolutional neural network S Bouguezzi, H Faiedh, C Souani 2021 18th International Multi-Conference on Systems, Signals & Devices (SSD … , 2021 2021 Citations: 20
An efficient face recognition method using CNN H Ben Fredj, S Sghaier, C Souani 2021 International Conference of Women in Data Science at Taif University … , 2021 2021 Citations: 16
Road signs classification by ANN for real-time implementation S Hamdi, H Faiedh, C Souani, K Besbes 2017 international conference on control, automation and diagnosis (ICCAD … , 2017 2017 Citations: 15
Pedestrian detection and tracking using an enhanced YOLOv9 model for automotive vehicles W Farhat, OB Rhaiem, H Faiedh, C Souani Measurement 254, 118009 , 2025 2025 Citations: 14
Real-time hardware/software co-design of a traffic sign recognition system using Zynq FPGA W Farhat, H Faiedh, C Souani, K Besbes 2016 11th international design & test symposium (IDT), 302-307 , 2016 2016 Citations: 14
Real-time recognition of road traffic signs in video scenes W Farhat, H Faiedh, C Souani, K Besbes 2016 2nd International Conference on Advanced Technologies for Signal and … , 2016 2016 Citations: 14
