Mohamed Yassine Haouam
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Mohamed Yassine Haouam has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
- Issam Bendib
University of Larbi Tebessi
6 shared publications - Mohamed Amroune
Informatics and systems (LAMIS) Laboratory of mathematics Echahid Cheikh Larbi Tebessi University 12002 Tebessa Algeria
5 shared publications - Abdallah Meraoumia
Echahid Cheikh Larbi Tebessi University
4 shared publications - Lakhdar Laimeche
Laboratory of Mathematics, Informatics and Systems (LAMIS), University of Larbi Tebessi, Tebessa, Algeria
4 shared publications - Abdelmadjid Benmachiche
Laboratory of Computer Science and Applied Mathematics, Dept. of Computer Science, Faculty of Science and Technology, Chadli Bendjedid, University, El-Tarf, Algeria
2 shared publications - Hama Soltani
Laboratory of Mathematics, Informatics and Systems (LAMIS), Echahid Cheikh Larbi Tebessi University, Tebessa, Algeria
2 shared publications
Latest Publications
- 7 May 2026
- Published by Elsevier in Digital Signal Processing
- Vol. 180
GAN-PSO: A novel approach for effective data augmentation through medical image generation
- 7 May 2026
- Published by Elsevier in Digital Signal Processing
- Vol. 180
GAN-PSO: A novel approach for effective data augmentation through medical image generation
- Open Access
Exploring Variational Autoencoders for Medical Image Generation: A Comprehensive Study
Variational autoencoder (VAE) is one of the most common techniques in the field of medical image generation, where this architecture has shown advanced researchers in recent years and has developed into various architectures. VAE has advantages including improving datasets by adding samples in smaller datasets and in datasets with imbalanced classes, and this is how data augmentation works. This paper provides a comprehensive review of studies on VAE in medical imaging, with a special focus on their ability to create synthetic images close to real data so that they can be used for data augmentation. This study reviews important architectures and methods used to develop VAEs for medical images and provides a comparison with other generative models such as GANs on issues such as image quality, and low diversity of generated samples. We discuss recent developments and applications in several medical fields highlighting the ability of VAEs to improve segmentation and classification accuracy.
Open AccessExploring Variational Autoencoders for Medical Image Generation: A Comprehensive Study
Variational autoencoder (VAE) is one of the most common techniques in the field of medical image generation, where this architecture has shown advanced researchers in recent years and has developed into various architectures. VAE has advantages including improving datasets by adding samples in smaller datasets and in datasets with imbalanced classes, and this is how data augmentation works. This paper provides a comprehensive review of studies on VAE in medical imaging, with a special focus on their ability to create synthetic images close to real data so that they can be used for data augmentation. This study reviews important architectures and methods used to develop VAEs for medical images and provides a comparison with other generative models such as GANs on issues such as image quality, and low diversity of generated samples. We discuss recent developments and applications in several medical fields highlighting the ability of VAEs to improve segmentation and classification accuracy.
- 31 July 2024
- Published by Springer Nature
- p. 94-101
Detection of Obstructive Sleep Apnea Based on Deep Learning Models from ECG Signals: A Review
- 31 July 2024
- Published by Springer Nature
- p. 94-101
Detection of Obstructive Sleep Apnea Based on Deep Learning Models from ECG Signals: A Review
- 31 July 2024
- Published by Springer Nature
- p. 57-63
Application of Faster-RCNN with Detectron2 for Effective Breast Tumor Detection in Mammography
- 31 July 2024
- Published by Springer Nature
- p. 57-63
Application of Faster-RCNN with Detectron2 for Effective Breast Tumor Detection in Mammography
- Open Access
- 30 March 2024
- Published by Politechnika Lubelska in Applied Computer Science
- Vol. 20 (1) , 28–55
ENHANCING MEDICAL DATA SECURITY IN E-HEALTH SYSTEMS USING BIOMETRIC-BASED WATERMARKING
In the field of Electronic Health (e-Health), Electronic Health Records (EHR) are transmitted between health professionals using e-Health systems for cooperative medical practice, medical monitoring, telemedical expertise, and telemedical imaging. Medical images are a crucial component of EHR and are used in various aspects of telemedicine systems such as expertise, consultation, teaching, and research. However, protecting the authenticity and copyrights of medical images is essential to prevent duplication, modification, or unauthorized distribution. This paper proposes a robust medical image copyright protection method that uses patient palm-print template as watermark and Lorenz chaotic map for template concealing and selecting the appropriate embedding positions in medical images. The novelty of the method lies in optimizing the expected number of modifications per pixel of the medical images after being watermarked. Experimental results indicate that this approach has a high performance with a genuine accept rate of 99.86% and can withstand various image processing attacks, including Gaussian noise, compression, and image rotations, while ensuring personal data security during telemedicine data exchange.
- 30 March 2024
- Published by Politechnika Lubelska in Applied Computer Science
- Vol. 20 (1) , 28–55
Open AccessENHANCING MEDICAL DATA SECURITY IN E-HEALTH SYSTEMS USING BIOMETRIC-BASED WATERMARKING
In the field of Electronic Health (e-Health), Electronic Health Records (EHR) are transmitted between health professionals using e-Health systems for cooperative medical practice, medical monitoring, telemedical expertise, and telemedical imaging. Medical images are a crucial component of EHR and are used in various aspects of telemedicine systems such as expertise, consultation, teaching, and research. However, protecting the authenticity and copyrights of medical images is essential to prevent duplication, modification, or unauthorized distribution. This paper proposes a robust medical image copyright protection method that uses patient palm-print template as watermark and Lorenz chaotic map for template concealing and selecting the appropriate embedding positions in medical images. The novelty of the method lies in optimizing the expected number of modifications per pixel of the medical images after being watermarked. Experimental results indicate that this approach has a high performance with a genuine accept rate of 99.86% and can withstand various image processing attacks, including Gaussian noise, compression, and image rotations, while ensuring personal data security during telemedicine data exchange.
- 27 September 2023
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 83 (12) , 35763-35780
Breast lesions segmentation and classification in a two-stage process based on Mask-RCNN and Transfer Learning
- 27 September 2023
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 83 (12) , 35763-35780
Breast lesions segmentation and classification in a two-stage process based on Mask-RCNN and Transfer Learning
- 15 September 2023
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 83 (10) , 30965-30980
Early detection and diagnosis of lung cancer using YOLO v7, and transfer learning
- 15 September 2023
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 83 (10) , 30965-30980
Early detection and diagnosis of lung cancer using YOLO v7, and transfer learning
- 18 March 2022
- Published by Pleiades Publishing Ltd in Pattern Recognition and Image Analysis
- Vol. 32 (1) , 109-128
A New Cancelable Deep Biometric Feature Using Chaotic Maps
In addition to the high security required for sensitive data in recent years, the availability of low-cost data acquisition devices for biometrics and impressive advances in digital technology have significantly increased the use of biometric technologies for automatic human identity recognition. Unfortunately, human biometrics are very sensitive due to constant communication with consumers. This justifies growing concerns about human integrity and anonymity before any hacking attempt. Therefore, much research has been focused on extracting reversible biometric functions and finding a way to replace them whenever they are compromised. In this paper, a new cancelable deep feature extraction method (C-PCANet) using chaotic maps is proposed. Our scheme can effectively provide lightweight and cancelable deep biometric features that can employed in a variety of high-security applications.
- 18 March 2022
- Published by Pleiades Publishing Ltd in Pattern Recognition and Image Analysis
- Vol. 32 (1) , 109-128
A New Cancelable Deep Biometric Feature Using Chaotic Maps
In addition to the high security required for sensitive data in recent years, the availability of low-cost data acquisition devices for biometrics and impressive advances in digital technology have significantly increased the use of biometric technologies for automatic human identity recognition. Unfortunately, human biometrics are very sensitive due to constant communication with consumers. This justifies growing concerns about human integrity and anonymity before any hacking attempt. Therefore, much research has been focused on extracting reversible biometric functions and finding a way to replace them whenever they are compromised. In this paper, a new cancelable deep feature extraction method (C-PCANet) using chaotic maps is proposed. Our scheme can effectively provide lightweight and cancelable deep biometric features that can employed in a variety of high-security applications.
- 25 June 2021
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 80 (28-29) , 36059-36091
S-DCTNet: Security-oriented biometric feature extraction technique
- 25 June 2021
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 80 (28-29) , 36059-36091
S-DCTNet: Security-oriented biometric feature extraction technique
- 1 May 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 229-234
Does the Learning Principle Help Us Improve Hand-Crafted Finger-Knuckle-Print Features?
One of the most critical steps in pattern recognition systems is to extract the most distinctive features of the image. Therefore, the accuracy of these systems is strongly related to the efficiency of this step to represent the image. In general, hand-craft image features are obtained using feature extraction methods that often have no prior knowledge about the image type, which may result in poor features. In this paper, a hand-craft image feature learning method, based on Local Binary Pattern (LBP), for Finger-Knuckle-Print representation and recognition is applied. Thus, in the learning phase, each training finger image is first divided into several non-overlapping regions, and the feature filter and the codebook of each region are individually learned. For the enrolment phase, the obtained learned filter and codebook are applied to each image to extract the histogram feature of each region. Then, the different histograms are concatenated in a single feature vector to represent the finger features. Finally, an SVM classifier is used for the identification phase. The experimental results clearly show that the learning principle offers a good gain in the system accuracy, which can provide an excellent identification rate and thus improve security.
- 1 May 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 229-234
Does the Learning Principle Help Us Improve Hand-Crafted Finger-Knuckle-Print Features?
One of the most critical steps in pattern recognition systems is to extract the most distinctive features of the image. Therefore, the accuracy of these systems is strongly related to the efficiency of this step to represent the image. In general, hand-craft image features are obtained using feature extraction methods that often have no prior knowledge about the image type, which may result in poor features. In this paper, a hand-craft image feature learning method, based on Local Binary Pattern (LBP), for Finger-Knuckle-Print representation and recognition is applied. Thus, in the learning phase, each training finger image is first divided into several non-overlapping regions, and the feature filter and the codebook of each region are individually learned. For the enrolment phase, the obtained learned filter and codebook are applied to each image to extract the histogram feature of each region. Then, the different histograms are concatenated in a single feature vector to represent the finger features. Finally, an SVM classifier is used for the identification phase. The experimental results clearly show that the learning principle offers a good gain in the system accuracy, which can provide an excellent identification rate and thus improve security.