M. LALAOUI Lahouaoui

Prof

Directory of teachers

Department

Departement of ELECTRONICS

Research Interests

traitement d'images automates programmables industrielles

Contact Info

University of M'Sila, Algeria

Email : lahouaoui.lalaoui@univ-msila.dz

On the Web:

  • Google Scholar N/A
  • ResearchGate
    ResearchGate N/A
  • ORCID N/A
  • SC
    Scopus N/A

Recent Publications

2024-10-01

Sea Clutter Modelling using Compound Gaussian with Nakagami Texture plus Thermal Noise

Sea clutter modelling is crucial issue for constant false alarm rate (CFAR) radar detection. Several works had shown that sea clutter has a
non-Gaussian nature. several heavy-tailed distributions have been proposed to model the sea clutter such as compound K (Ck), compound inverse
Gaussian (CIG) and compound inverted exponentiated Rayleigh distribution (CIER). Recently, a new compound model has introduced by using
Nakagami-distributed texture (CGNG) to model sea clutter with high-resolution at medium/high grazing angles. In this manuscript, we propose to
extend the CGNG distribution to cover the presence of additive thermal noise and show the modelling performance using high resolution sea clutter
data.
Citation

M. LALAOUI Lahouaoui, (2024-10-01), "Sea Clutter Modelling using Compound Gaussian with Nakagami Texture plus Thermal Noise", [national] PRZEGLĄD ELEKTROTECHNICZNY , http://pe.org.pl/issue.php?lang=1&num=10/2024

Read Full Paper
2024-07-19

Enhancement multi interest U-Net for Medical image segmentation

rien
Citation

M. LALAOUI Lahouaoui, (2024-07-19), "Enhancement multi interest U-Net for Medical image segmentation", [international] international conference on applied analysis and mathematical modeling 2024 , turquie

Read Full Paper
2024-02-29

Enhancing Image Classification Through a Hybrid Approach: Integrating Convolutional Neural Networks with Hidden Markov Mod

In the field of computer vision, image classification stands as a pivotal task, aiming to categorize images based on their inherent visual information. This paper presents an innovative hybrid approach, merging the strengths of Convolutional Neural Networks (CNNs) and Hidden Markov Models (HMMs) to enhance the efficacy of image classification. The integration of these two methodologies, each excelling in distinct aspects of data analysis, forms the cornerstone of our research. CNNs, renowned for their proficiency in extracting spatial data and fine-grained features, are adept at generalizing across diverse datasets. Conversely, HMMs, with their robust sequential data modeling capabilities, adeptly capture dependencies within the feature sets derived from CNNs. This synergy is embodied in the HMM-CNN framework, wherein CNNs serve to extract pertinent features from images, while HMMs model the spatial dependencies between adjacent pixels. Empirical evaluations on benchmark datasets substantiate the superior performance of this hybrid approach over traditional CNNs, particularly in scenarios where temporal dependencies are paramount, such as video analysis, action recognition, and gesture classification. A comparative analysis employing five datasets and six metrics-recall, precision, val_loss, val_accuracy, val_precision, and val_recall-reveals the superiority of the CNN-HMM model. Specifically, against a standalone CNN model with an accuracy of 87%, the CNN-HMM model demonstrates an accuracy of approximately 89.09%. This paper's findings underscore the efficacy of combining CNN and HMM methodologies for advanced image classification tasks, offering significant implications for future research in this domain.
Citation

M. LALAOUI Lahouaoui, (2024-02-29), "Enhancing Image Classification Through a Hybrid Approach: Integrating Convolutional Neural Networks with Hidden Markov Mod", [national] traitement du signal , IIETA

Read Full Paper
2023-11-22

performance analusis of coherent detection in compound Gaussian clutter with invere rayleigh texture

rrr
Citation

M. LALAOUI Lahouaoui, (2023-11-22), "performance analusis of coherent detection in compound Gaussian clutter with invere rayleigh texture", [international] The 1st edition of the international conference on electronics engineering and telecommunications , BBA Algeria

Read Full Paper
2023-11-02

An improved learning algorithm for training neural network based lattice equalizer

gggggg
Citation

M. LALAOUI Lahouaoui, (2023-11-02), "An improved learning algorithm for training neural network based lattice equalizer", [international] The International workshop on Machatronic Systems Supervision(IW_MSS) , Tunisie

Read Full Paper

The morphological Analysis of Human Skin Layers Using Computational Image segmentation

gggg
Citation

M. LALAOUI Lahouaoui, (2023-11-02), "The morphological Analysis of Human Skin Layers Using Computational Image segmentation", [international] The International workshop on Machatronic Systems Supervision (IW_MSS) , Tunisie

Read Full Paper
2023

Markov random field model and expectation of maximization for images segmentation

Image segmentation is a significant issue in image processing. Among the
various models and approaches that have been developed, some are
commonly used the Markov random field (MRF) model, statistical
techniques MRF. In this study a Markov random field proposed is based on
an expectation-maximization (EM) modified (EMM) model. In this paper,
the local optimization is based on a modified EM method for parameter
estimation and the iterative conditional model (ICM) method for finding the
solution given a fixed set of these parameters. To select the combination
strategy, it is necessary to carry out a comparative study to find the best
result. The effectiveness of our proposed methods has been proven by
experimentation. We have applied this segmented algorithm to different
types of images, exhibiting the algorithm's image segmentation strength with
its best values criteria for EM statics and other methods.
Citation

M. LALAOUI Lahouaoui, (2023), "Markov random field model and expectation of maximization for images segmentation", [national] Indonesian Journal of Electrical Engineering and Computer Science , http://ijeecs.iaescore.com

Read Full Paper
2022-11-26

Medical Image Segmentation used Unsupervised Convolutional Neural Network

VVVV
Citation

M. LALAOUI Lahouaoui, (2022-11-26), "Medical Image Segmentation used Unsupervised Convolutional Neural Network", [international] International conference Advanced Technology in Electronic and Electric engineering(ICATEEE) Msila , Msila Algeria

Read Full Paper
2022

Medical Image Segmentation Used Unsupervised Convolutional Neural Network

Segmenting skin lesions is a crucial step in computer-aided melanoma diagnosis, but it is also a highly difficult task because of the imprecise lesion boundaries and varied lesion textures. We describe a deep fully convolutional network-based, totally automatic technique for skin lesion segmentation (FCNs). In order to extend ConvNets for tasks requiring medical picture segmentation, this work provides unsupervised domain adaption techniques employing adversarial learning. By combining the prior knowledge stored by the shallow network with the deep FCNs, we are able to show that our newly built network may increase accuracy for lesion segmentation. Our approach is robust and does not require extensive parameter tuning or data augmentation. The experimental findings demonstrate the method's considerable potential for efficient model generalization.
Citation

M. LALAOUI Lahouaoui, (2022), "Medical Image Segmentation Used Unsupervised Convolutional Neural Network", [international] the 2022 International Conference of advanced Technology in Electronic and Electrical Engineering (ICATEEE) , Université de Msila

Read Full Paper

Image Classification Using a Fully Convolutional Neural Network CNN

This article reviews the field of image processing in recent years is enormously
developed and it has been used in several specialties like medical, stand-alone, satellite
and the purpose of this field is to improve image quality and extract information.
Pneumonia has become in recent years a defective disease that affects the majorities of
the population is especially the elderly and can sometimes put their lives in danger, in
order to save human life early pneumonia diagnostic is necessary; in this work we have
based on the detection and classification of patients with pneumonia from their chest xray. However, there are several areas where image classification is applied with success,
in our work we have used deep learning based on the most common convolutional
neural networks to make an image classification of pneumonia disease and to obtained
good results and gave several advantages
Citation

M. LALAOUI Lahouaoui, (2022), "Image Classification Using a Fully Convolutional Neural Network CNN", [national] Mathematical Modelling of Engineering Problems , Journal home page: http://iieta.org/journals/mmep

Read Full Paper
2021-03-14

Segmentation for different image modality

ddddd
Citation

M. LALAOUI Lahouaoui, (2021-03-14), "Segmentation for different image modality", [national] Algerian Journal of Engineering, Architecture and Urbanism (AJEAU) , https://www.aneau.org/ajeau/

Read Full Paper

Unsupervised segmentation of images by Markov segmentation into regions

ggghhjkkl
Citation

M. LALAOUI Lahouaoui, (2021-03-14), "Unsupervised segmentation of images by Markov segmentation into regions", [national] Algerian Journal of Engineering, Architecture and Urbanism (AJEAU) , https://www.aneau.org/ajeau/

Read Full Paper
2021

UNSUPERVISED SEGMENTATION OF IMAGES BY MARKOV SEGMENTATION INTO REGIONS

Image segmentation is a preliminary and fundamental step in computer aided magnetic resonance imaging
(MRI) images analysis. Markov random field model (MRF) has attracted great attention in the field of image
segmentation. Such super pixel-based or region-based MRF models have their own advantages and
disadvantages. In order to complement advantages of each other, a unified Markov random field (UMRF) model
proposed in this paper. However, the performance of most current image segmentation methods easily
depreciated by noise in MRI images. In this paper, we proposed the hidden Markov random field (HMRF)
model based on KMeans and Expectation-Maximization (EM) algorithm for image segmentation. We implement
a MATLAB toolbox named HMRF-EM-image for 2D image segmentation using the HMRF-EM framework2.
This toolbox also implements edge-prior preserving image segmentation, and can be easily reconfigured for
other problems, such as 3D image segmentation. We have applied this algorithm segmented different type of
image, to evaluate the method a validation of the results provided, demonstrating the strength of the algorithm
for image with noise.
Citation

M. LALAOUI Lahouaoui, (2021), "UNSUPERVISED SEGMENTATION OF IMAGES BY MARKOV SEGMENTATION INTO REGIONS", [international] Algerian Journal of Engineering Architecture and Urbanism , oran

Read Full Paper
← Back to Researchers List