Med Salim Bouhlel
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Med Salim Bouhlel has a total of 169 co-authors. Here are the top co-authors by number of shared publications:
- Ali Khalfallah
University of Sfax
23 shared publications Karim Saheb Ettabaa
Department of Computer Sciences, IMT Atlantic Laboratory, ISITCom, University of Sousse, Tunisia
8 shared publications- Ali Mansouri
ISBS
6 shared publications Med Karim Abdmouleh
6 shared publicationsNeziha Jaouedi
Higher Institute of Biotechnology of Sfax, Tunisia,National Engineering School of Gabes, Tunisia SETIT Lab.,Gabes,Tunisia
6 shared publicationsHassen Hamouda
5 shared publications
Latest Publications
- 25 July 2024
- Published by Springer Nature
- p. 371-379
Towards Hybrid Approach Based SVM and Radiomics Features for COVID-19 Classification and Segmentation
- 25 July 2024
- Published by Springer Nature
- p. 371-379
Towards Hybrid Approach Based SVM and Radiomics Features for COVID-19 Classification and Segmentation
- 24 July 2024
- Published by Springer Nature
- p. 481-490
Hybrid Approach for COVID-19 Segmentation: Integrating ResNet-Darknet19 Based Transfer Learning with Radiomics Features
- 24 July 2024
- Published by Springer Nature
- p. 481-490
Hybrid Approach for COVID-19 Segmentation: Integrating ResNet-Darknet19 Based Transfer Learning with Radiomics Features
- 23 July 2024
- Published by Springer Nature
- p. 1-10
Comparative Study of Image Compression Methods Using Artificial Neural Networks Based on Semi-log Quantization
- 23 July 2024
- Published by Springer Nature
- p. 1-10
Comparative Study of Image Compression Methods Using Artificial Neural Networks Based on Semi-log Quantization
- Open Access
- 28 September 2023
- Published by Springer Nature in Research Square
Deep Learning based Automatic Image Annotation System for Image Retrieval with Arabic language
Social media platforms like YouTube, Twitter, and Facebook have grown into new modalities of communication, allowing a great number of individuals to interact and learn. Furthermore, many social media users currently produce and share incorrect thoughts and images that are not accompanied by words. The automated generation of any text for raw photos is a difficult operation, particularly when working with Arabic and a limited amount of training samples. To tackle this challenge, smart technology and deep learning technology have been offered. The method employs a bi-level architecture, which allows for the use of self-supervision to produce rotation variants in order to increase the number of training samples. This, in turn, enhances the variability of the model representation and enables the investigation of high-level object information for more detailed picture production. GoogleNet model automatically overcomes the stability issues associated with parsing and synthesising any picture. The proposed technique makes use of deep learning technology to explain images received from the internet environment and gather information about the existence of identified items in order to create an optimal detection method that does not interfere with the deep learning process.
- 28 September 2023
- Published by Springer Nature in Research Square
Open AccessDeep Learning based Automatic Image Annotation System for Image Retrieval with Arabic language
Social media platforms like YouTube, Twitter, and Facebook have grown into new modalities of communication, allowing a great number of individuals to interact and learn. Furthermore, many social media users currently produce and share incorrect thoughts and images that are not accompanied by words. The automated generation of any text for raw photos is a difficult operation, particularly when working with Arabic and a limited amount of training samples. To tackle this challenge, smart technology and deep learning technology have been offered. The method employs a bi-level architecture, which allows for the use of self-supervision to produce rotation variants in order to increase the number of training samples. This, in turn, enhances the variability of the model representation and enables the investigation of high-level object information for more detailed picture production. GoogleNet model automatically overcomes the stability issues associated with parsing and synthesising any picture. The proposed technique makes use of deep learning technology to explain images received from the internet environment and gather information about the existence of identified items in order to create an optimal detection method that does not interfere with the deep learning process.
- Open Access
- 1 January 2023
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 2839 (1)
Automatic image annotation system to images retrieval based on deep learning technique
The paper proposed an automatic image annotation (AIA) model that is assigned method semantic labels to the new image automatically. It is also proposed a scheme for implementation an AIA-system based on deep learning method by using a Convolutional Neural Network (CNN) model that raw dataset (Corel-5K, ESP Game, IAPR TC-12, NUSWIDE, and MS-COCO). The photos are recorded and accessible for searching, categorization, and retrieval purposes. These photographs must be tagged with appropriate words, phrases, or keywords in order for the required action to be conducted properly. These operations are facing challenges in assigning labels to an image which is in form of keyword tagging or a very short description of the image, that lead to speed up the image’s retriever so that the aims of paper are to develop a multilayered tagging model that has common interaction layer by using deep learning method, CNN-RNN model. Although Back Propagation Through Time (BPTT) adjusts the weights of the neural network, and the model is used it to increase the quality of retrieved images that have a high level of relative keywords. In addition, it is a supervised learning algorithm that allows the network to be corrected concerning the errors that have occurred. Finally, the proposed model implemented by Python 3.7 because it has useful models and is change some parts to enhance the results of this paper.
- 1 January 2023
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 2839 (1)
Open AccessAutomatic image annotation system to images retrieval based on deep learning technique
The paper proposed an automatic image annotation (AIA) model that is assigned method semantic labels to the new image automatically. It is also proposed a scheme for implementation an AIA-system based on deep learning method by using a Convolutional Neural Network (CNN) model that raw dataset (Corel-5K, ESP Game, IAPR TC-12, NUSWIDE, and MS-COCO). The photos are recorded and accessible for searching, categorization, and retrieval purposes. These photographs must be tagged with appropriate words, phrases, or keywords in order for the required action to be conducted properly. These operations are facing challenges in assigning labels to an image which is in form of keyword tagging or a very short description of the image, that lead to speed up the image’s retriever so that the aims of paper are to develop a multilayered tagging model that has common interaction layer by using deep learning method, CNN-RNN model. Although Back Propagation Through Time (BPTT) adjusts the weights of the neural network, and the model is used it to increase the quality of retrieved images that have a high level of relative keywords. In addition, it is a supervised learning algorithm that allows the network to be corrected concerning the errors that have occurred. Finally, the proposed model implemented by Python 3.7 because it has useful models and is change some parts to enhance the results of this paper.
- 21 December 2022
- Published by Springer Nature in Personal and Ubiquitous Computing
- Vol. 27 (2) , 481-494
Usability of Montessori tangible user interfaces to support learners’ retention skills in preschools
- 21 December 2022
- Published by Springer Nature in Personal and Ubiquitous Computing
- Vol. 27 (2) , 481-494
Usability of Montessori tangible user interfaces to support learners’ retention skills in preschools
- 21 September 2022
- Published by Springer Nature
- p. 305-314
Application of the Laplacian Smoothing on 3D Static Models and Their Evaluation by the New Objective Quality Metric 3DrwPSNR
- 21 September 2022
- Published by Springer Nature
- p. 305-314
Application of the Laplacian Smoothing on 3D Static Models and Their Evaluation by the New Objective Quality Metric 3DrwPSNR
- 7 July 2022
- Published by Springer Nature in Education and Information Technologies
- Vol. 28 (1) , 833-855
Student Performance Prediction with Eye-Gaze Data in Embodied Educational Context
- 7 July 2022
- Published by Springer Nature in Education and Information Technologies
- Vol. 28 (1) , 833-855
Student Performance Prediction with Eye-Gaze Data in Embodied Educational Context
- 28 May 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 10341, 493-498
A survey on human behavior analysis and actions recognition from videos
Human behavior analysis using action recognition remains an active research domain of computer vision. Action prediction using Artificial Intelligence (AI) by machine learning has attracted the attention of several researchers. The presentation of human action is usually considered an important challenge. An effective representative should be robust to noise, invariant to viewpoint changes and complex scenes involving high speeds. Two main challenges in this task include how to efficiently represent spatio–temporal patterns of skeletal movements and how to learn their discriminative human features for activity classification. In this survey, we present an overview of human presence and action recognition methods used in the last years. The results of the related works are compared with our results. The performance of methods is evaluated with different human action dataset such as KTH, UCF101, UCF Sport and CAD-60.
- 28 May 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 10341, 493-498
A survey on human behavior analysis and actions recognition from videos
Human behavior analysis using action recognition remains an active research domain of computer vision. Action prediction using Artificial Intelligence (AI) by machine learning has attracted the attention of several researchers. The presentation of human action is usually considered an important challenge. An effective representative should be robust to noise, invariant to viewpoint changes and complex scenes involving high speeds. Two main challenges in this task include how to efficiently represent spatio–temporal patterns of skeletal movements and how to learn their discriminative human features for activity classification. In this survey, we present an overview of human presence and action recognition methods used in the last years. The results of the related works are compared with our results. The performance of methods is evaluated with different human action dataset such as KTH, UCF101, UCF Sport and CAD-60.