Omaima El Bahi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Omaima El Bahi has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Ahmad El Allaoui
Moulay Ismail University of Meknes
8 shared publications - Ali Omari Alaoui
L-IMIA, T-IDMS, FST Errachidia/Moulay Ismail University
6 shared publications - Youssef Qaraai
MSIA Team, IMIA Laboratory, Faculty of Sciences and Technology, Errachidia, Moulay Ismail University Meknes, Morocco
4 shared publications - Yousef Farhaoui
IMIA Laboratory, T-IDMS Faculty of Sciences and Techniques of Errachidia, Moulay Ismail University of Meknes, Meknes, Morocco
3 shared publications - Mohamed Rida Fethi
Moulay Ismail University
2 shared publications - Othmane Farhaoui
Moulay Ismail University
2 shared publications
Latest Publications
- 9 July 2025
- Published by Springer Nature in Signal, Image and Video Processing
- Vol. 19 (10) , 1-11
Deformation field prediction based on a modified loss function with U-Net for non rigid image registration
- 9 July 2025
- Published by Springer Nature in Signal, Image and Video Processing
- Vol. 19 (10) , 1-11
Deformation field prediction based on a modified loss function with U-Net for non rigid image registration
- 30 May 2025
- Published by Springer Nature
- p. 683-688
Graph-Based Matching for High-Resolution Images Using SIFT Features and ML Metrics
- 30 May 2025
- Published by Springer Nature
- p. 683-688
Graph-Based Matching for High-Resolution Images Using SIFT Features and ML Metrics
- 23 April 2024
- Published by Springer Nature
- p. 45-52
Deep Multi-temporal Matching of Satellite Images for Agricultural Dams
- 23 April 2024
- Published by Springer Nature
- p. 45-52
Deep Multi-temporal Matching of Satellite Images for Agricultural Dams
- 5 March 2024
- Published by Springer Nature
- p. 256-262
Comparative Analysis of Pre-trained CNN Models for Image Classification of Emergency Vehicles
- 5 March 2024
- Published by Springer Nature
- p. 256-262
Comparative Analysis of Pre-trained CNN Models for Image Classification of Emergency Vehicles
- 5 March 2024
- Published by Springer Nature
- p. 516-521
Deep Feature-Based Matching of High-Resolution Multitemporal Images Using VGG16 and VGG19 Algorithms
- 5 March 2024
- Published by Springer Nature
- p. 516-521
Deep Feature-Based Matching of High-Resolution Multitemporal Images Using VGG16 and VGG19 Algorithms
- Open Access
- 30 December 2023
- Published by Salud, Ciencia y Tecnologia in Data and Metadata
- Vol. 2, 153
Pre-trained CNNs: Evaluating Emergency Vehicle Image Classification
In this paper, we aim to provide a comprehensive analysis of image classification, specifically in the context of emergency vehicle classification. We have conducted an in-depth investigation, exploring the effectiveness of six pre-trained Convolutional Neural Network (CNN) models. These models, namely VGG19, VGG16, MobileNetV3Large, MobileNetV3Small, MobileNetV2, and MobileNetV1, have been thoroughly examined and evaluated within the domain of emergency vehicle classification. The research methodology utilized in this study is carefully designed with a systematic approach. It includes the thorough preparation of datasets, deliberate modifications to the model architecture, careful selection of layer operations, and fine-tuning of the model compilation. To gain a comprehensive understanding of the performance, we conducted a detailed series of experiments. We analyzed nuanced performance metrics such as accuracy, loss, and training time, considering important factors in the evaluation process. The results obtained from this study provide a comprehensive understanding of the advantages and disadvantages of each model. Moreover, they emphasize the crucial significance of carefully choosing a suitable pre-trained Convolutional Neural Network (CNN) model for image classification tasks. Essentially, this article provides a comprehensive overview of image classification, highlighting the crucial significance of pre-trained CNN models in achieving precise outcomes, especially in the demanding field of emergency vehicle classification
- 30 December 2023
- Published by Salud, Ciencia y Tecnologia in Data and Metadata
- Vol. 2, 153
Open AccessPre-trained CNNs: Evaluating Emergency Vehicle Image Classification
In this paper, we aim to provide a comprehensive analysis of image classification, specifically in the context of emergency vehicle classification. We have conducted an in-depth investigation, exploring the effectiveness of six pre-trained Convolutional Neural Network (CNN) models. These models, namely VGG19, VGG16, MobileNetV3Large, MobileNetV3Small, MobileNetV2, and MobileNetV1, have been thoroughly examined and evaluated within the domain of emergency vehicle classification. The research methodology utilized in this study is carefully designed with a systematic approach. It includes the thorough preparation of datasets, deliberate modifications to the model architecture, careful selection of layer operations, and fine-tuning of the model compilation. To gain a comprehensive understanding of the performance, we conducted a detailed series of experiments. We analyzed nuanced performance metrics such as accuracy, loss, and training time, considering important factors in the evaluation process. The results obtained from this study provide a comprehensive understanding of the advantages and disadvantages of each model. Moreover, they emphasize the crucial significance of carefully choosing a suitable pre-trained Convolutional Neural Network (CNN) model for image classification tasks. Essentially, this article provides a comprehensive overview of image classification, highlighting the crucial significance of pre-trained CNN models in achieving precise outcomes, especially in the demanding field of emergency vehicle classification
- Open Access
- 24 May 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-6
Optimizing Emergency Vehicle Detection for Safer and Smoother Passages
Optimizing the detection of emergency vehicles is a key part of intelligent transportation systems to maintain safety and decrease reaction times. The aim of this work, we offer a strategy that applies the YOLOv8 algorithm with a custom dataset to control items such as traffic lights, hospital doors, and other obstacles to make the passage smoother and more secure. Our proposed method was evaluated and contrasted with different YOLO versions (YOLOv5, YOLOv6, and YOLOv7) utilizing our custom dataset. The assessment metrics utilized for the correlation were precision, recall, and mAP. The outcomes indicated that the YOLOv8 algorithm surpassed the other forms of YOLO regarding Recall, Precision, and mean average precision (mAP). Moreover, the recommended system can upgrade crisis reaction vehicle security by giving continuous oversight to dodge disasters and save time. Moreover, our proposed strategy can improve vehicle recognition and improve overall safety pass.
- 24 May 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-6
Open AccessOptimizing Emergency Vehicle Detection for Safer and Smoother Passages
Optimizing the detection of emergency vehicles is a key part of intelligent transportation systems to maintain safety and decrease reaction times. The aim of this work, we offer a strategy that applies the YOLOv8 algorithm with a custom dataset to control items such as traffic lights, hospital doors, and other obstacles to make the passage smoother and more secure. Our proposed method was evaluated and contrasted with different YOLO versions (YOLOv5, YOLOv6, and YOLOv7) utilizing our custom dataset. The assessment metrics utilized for the correlation were precision, recall, and mAP. The outcomes indicated that the YOLOv8 algorithm surpassed the other forms of YOLO regarding Recall, Precision, and mean average precision (mAP). Moreover, the recommended system can upgrade crisis reaction vehicle security by giving continuous oversight to dodge disasters and save time. Moreover, our proposed strategy can improve vehicle recognition and improve overall safety pass.