Yacine Yaddaden
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
Yacine Yaddaden has a total of 28 co-authors. Here are the top co-authors by number of shared publications:
- Raef Cherif
Université du Québec à Rimouski, Rimouski, Canada
3 shared publications Abdenour Bouzouane
Université du Québec à Chicoutimi (UQAC)
2 shared publications- Raef Cherif
Universit du Qubec Rimouski,Dpartement de Mathmatiques, Informatique et gnie,Rimouski,Canada
2 shared publications - Xavier Maldague
Université Laval
2 shared publications - Abdenour Bouzouane
Department of Computer Science and Mathematics, Université du Québec à Chicoutimi, 555 Boulevard de l’Université, Chicoutimi, QC G7H 2B1, Canada
1 shared publication - Ali Bahloul
Institut de Recherche Robert-Sauvé en Santé et Sécurité du Travail (IRSST), Montréal, QC H3A 3C2, Canada
1 shared publication
Latest Publications
- Open Access
- 20 October 2026
- Published by MDPI AG in Electronics
- Vol. 15 (20) , 4856
Hierarchical Two-Phase Skin Lesion Classification Using Reused Convolutional Neural Network Feature Spaces and Cross-Stage Classifier Fusion
Skin cancer, particularly melanoma, represents a major public health concern due to its steadily increasing incidence. Conventional clinical diagnostic methods present several limitations, including inter-observer variability and the risk of misdiagnosis, motivating the adoption of artificial intelligence techniques for the early detection and reliable classification of skin lesions. In this study, we propose a hierarchical multi-level decision classification framework based on progressive deep feature extraction and hierarchical feature fusion. The proposed architecture employs pretrained convolutional neural networks (CNNs) with frozen weights as fixed feature extractors, with the feature representations obtained at each hierarchical level directly reused for the final classification. The processing pipeline consists of several sequential stages. Prior to preprocessing or data augmentation, two evaluation protocols are adopted to assess the robustness of the proposed framework: a conventional 80–20 train–test split and a five-fold cross-validation strategy. The training data are subsequently balanced using a combination of undersampling and oversampling techniques to mitigate class imbalance, while controlled undersampling may also be applied to highly overrepresented classes in the test set. Importantly, the testing sets consist exclusively of original, non-augmented images. The images are then preprocessed using histogram equalization and resized to a resolution of pixels. Regions of interest (ROIs) corresponding to skin lesions are subsequently extracted, followed by deep feature extraction using pretrained CNNs. Finally, the global and specialized feature representations are concatenated to construct an enriched hierarchical representation for the final classification stage. Unlike conventional flat multiclass classification approaches, the proposed framework progressively decomposes the decision space into an initial binary classification stage followed by specialized fine-grained classification. The feature representations extracted at different decision levels are hierarchically reused through feature concatenation, providing complementary global and group-specific information for the final classification stage. This hierarchical strategy improves class separability, reduces ambiguities between visually similar lesion categories, and enhances the overall robustness of the proposed system. Four classifiers—Nu-Support Vector Machine (NuSVM), Linear Discriminant Analysis (LDA), Bernoulli Naive Bayes (BNB), and Logistic Regression (LR)—were evaluated on four publicly available dermoscopic datasets. Three experimental scenarios were investigated: binary classification, direct multiclass classification, and the proposed two-stage hierarchical classification framework. Experimental results demonstrate the superiority of the proposed approach, particularly on the PH2 dataset, where accuracies of 98.43% for binary classification, 87.45% for direct multiclass classification, and 96.00% for hierarchical classification were achieved. Furthermore, the five-fold cross-validation results confirm the robustness and generalization capability of the proposed framework across different datasets and evaluation protocols, highlighting the effectiveness of hierarchical feature reuse and classifier fusion for computer-aided skin lesion diagnosis. The proposed pipeline relies on segmentation masks for region of interest extraction; consequently, classification performance may be influenced by the quality of these masks.- 20 October 2026
- Published by MDPI AG in Electronics
- Vol. 15 (20) , 4856
Open AccessHierarchical Two-Phase Skin Lesion Classification Using Reused Convolutional Neural Network Feature Spaces and Cross-Stage Classifier Fusion
Skin cancer, particularly melanoma, represents a major public health concern due to its steadily increasing incidence. Conventional clinical diagnostic methods present several limitations, including inter-observer variability and the risk of misdiagnosis, motivating the adoption of artificial intelligence techniques for the early detection and reliable classification of skin lesions. In this study, we propose a hierarchical multi-level decision classification framework based on progressive deep feature extraction and hierarchical feature fusion. The proposed architecture employs pretrained convolutional neural networks (CNNs) with frozen weights as fixed feature extractors, with the feature representations obtained at each hierarchical level directly reused for the final classification. The processing pipeline consists of several sequential stages. Prior to preprocessing or data augmentation, two evaluation protocols are adopted to assess the robustness of the proposed framework: a conventional 80–20 train–test split and a five-fold cross-validation strategy. The training data are subsequently balanced using a combination of undersampling and oversampling techniques to mitigate class imbalance, while controlled undersampling may also be applied to highly overrepresented classes in the test set. Importantly, the testing sets consist exclusively of original, non-augmented images. The images are then preprocessed using histogram equalization and resized to a resolution of pixels. Regions of interest (ROIs) corresponding to skin lesions are subsequently extracted, followed by deep feature extraction using pretrained CNNs. Finally, the global and specialized feature representations are concatenated to construct an enriched hierarchical representation for the final classification stage. Unlike conventional flat multiclass classification approaches, the proposed framework progressively decomposes the decision space into an initial binary classification stage followed by specialized fine-grained classification. The feature representations extracted at different decision levels are hierarchically reused through feature concatenation, providing complementary global and group-specific information for the final classification stage. This hierarchical strategy improves class separability, reduces ambiguities between visually similar lesion categories, and enhances the overall robustness of the proposed system. Four classifiers—Nu-Support Vector Machine (NuSVM), Linear Discriminant Analysis (LDA), Bernoulli Naive Bayes (BNB), and Logistic Regression (LR)—were evaluated on four publicly available dermoscopic datasets. Three experimental scenarios were investigated: binary classification, direct multiclass classification, and the proposed two-stage hierarchical classification framework. Experimental results demonstrate the superiority of the proposed approach, particularly on the PH2 dataset, where accuracies of 98.43% for binary classification, 87.45% for direct multiclass classification, and 96.00% for hierarchical classification were achieved. Furthermore, the five-fold cross-validation results confirm the robustness and generalization capability of the proposed framework across different datasets and evaluation protocols, highlighting the effectiveness of hierarchical feature reuse and classifier fusion for computer-aided skin lesion diagnosis. The proposed pipeline relies on segmentation masks for region of interest extraction; consequently, classification performance may be influenced by the quality of these masks. - Open Access
- 7 October 2026
- Published by MDPI AG in Industries
- Vol. 1 (2) , 10
An Industrial Carpet Defect Dataset and a Hybrid Two-Stage Inspection Framework for Automated Quality Control
Automated visual inspection has become a critical component of Industry 4.0 manufacturing systems, enabling improved product quality, reduced operational costs, and increased production efficiency. In the carpet manufacturing industry, quality inspection remains particularly challenging due to the high variability of textures, colors, patterns, and defect appearances, which often limits the effectiveness of conventional inspection systems. Furthermore, the scarcity of publicly available industrial carpet defect datasets limits the realistic assessment of automated inspection methods. Existing approaches are therefore frequently evaluated on benchmark datasets that do not fully capture the variability of real manufacturing environments or rely on computationally demanding end-to-end deep learning architectures, which may reduce their suitability for practical industrial deployment. To address these challenges, this paper introduces a new industrial carpet defect dataset acquired under controlled imaging conditions and containing defect-free samples together with four representative defect categories: Backing Seam, Bad Mend, Dirty Face, and End Out. In addition, we present an engineering study that systematically evaluates a practical two-stage inspection framework combining pretrained deep feature extraction, one-class anomaly detection, and supervised defect classification for industrial carpet quality control. A distinguishing aspect of this study is the systematic evaluation of the framework on both the public MVTec AD Carpet benchmark and the newly introduced industrial dataset, enabling its performance to be assessed under both benchmark and realistic industrial conditions. The first stage performs anomaly detection using one-class learning models trained exclusively on defect-free samples, while the second stage classifies detected defects into predefined categories. To investigate the impact of visual representations on inspection performance, multiple deep feature extraction backbones, including ConvNeXt, VGG-19, and Wide ResNet-50-2, are evaluated in combination with lightweight machine learning models. Experimental results demonstrate strong inspection performance, achieving an AUROC of 99.92% on the MVTec AD Carpet benchmark and 93.92% on the proposed industrial carpet dataset. The obtained results demonstrate that this integration of established techniques provides an effective and computationally lightweight solution for industrial deployment, while confirming the practical value of the proposed dataset as a realistic benchmark for future research.
- 7 October 2026
- Published by MDPI AG in Industries
- Vol. 1 (2) , 10
Open AccessAn Industrial Carpet Defect Dataset and a Hybrid Two-Stage Inspection Framework for Automated Quality Control
Automated visual inspection has become a critical component of Industry 4.0 manufacturing systems, enabling improved product quality, reduced operational costs, and increased production efficiency. In the carpet manufacturing industry, quality inspection remains particularly challenging due to the high variability of textures, colors, patterns, and defect appearances, which often limits the effectiveness of conventional inspection systems. Furthermore, the scarcity of publicly available industrial carpet defect datasets limits the realistic assessment of automated inspection methods. Existing approaches are therefore frequently evaluated on benchmark datasets that do not fully capture the variability of real manufacturing environments or rely on computationally demanding end-to-end deep learning architectures, which may reduce their suitability for practical industrial deployment. To address these challenges, this paper introduces a new industrial carpet defect dataset acquired under controlled imaging conditions and containing defect-free samples together with four representative defect categories: Backing Seam, Bad Mend, Dirty Face, and End Out. In addition, we present an engineering study that systematically evaluates a practical two-stage inspection framework combining pretrained deep feature extraction, one-class anomaly detection, and supervised defect classification for industrial carpet quality control. A distinguishing aspect of this study is the systematic evaluation of the framework on both the public MVTec AD Carpet benchmark and the newly introduced industrial dataset, enabling its performance to be assessed under both benchmark and realistic industrial conditions. The first stage performs anomaly detection using one-class learning models trained exclusively on defect-free samples, while the second stage classifies detected defects into predefined categories. To investigate the impact of visual representations on inspection performance, multiple deep feature extraction backbones, including ConvNeXt, VGG-19, and Wide ResNet-50-2, are evaluated in combination with lightweight machine learning models. Experimental results demonstrate strong inspection performance, achieving an AUROC of 99.92% on the MVTec AD Carpet benchmark and 93.92% on the proposed industrial carpet dataset. The obtained results demonstrate that this integration of established techniques provides an effective and computationally lightweight solution for industrial deployment, while confirming the practical value of the proposed dataset as a realistic benchmark for future research.
- Open Access
- 19 August 2025
- Published by MDPI AG in Big Data and Cognitive Computing
- Vol. 9 (8) , 213
Efficient Dynamic Emotion Recognition from Facial Expressions Using Statistical Spatio-Temporal Geometric Features
Automatic Facial Expression Recognition (AFER) is a key component of affective computing, enabling machines to recognize and interpret human emotions across various applications such as human–computer interaction, healthcare, entertainment, and social robotics. Dynamic AFER systems, which exploit image sequences, can capture the temporal evolution of facial expressions but often suffer from high computational costs, limiting their suitability for real-time use. In this paper, we propose an efficient dynamic AFER approach based on a novel spatio-temporal representation. Facial landmarks are extracted, and all possible Euclidean distances are computed to model the spatial structure. To capture temporal variations, three statistical metrics are applied to each distance sequence. A feature selection stage based on the Extremely Randomized Trees (ExtRa-Trees) algorithm is then performed to reduce dimensionality and enhance classification performance. Finally, the emotions are classified using a linear multi-class Support Vector Machine (SVM) and compared against the k-Nearest Neighbors (k-NN) method. The proposed approach is evaluated on three benchmark datasets: CK+, MUG, and MMI, achieving recognition rates of 94.65%, 93.98%, and 75.59%, respectively. Our results demonstrate that the proposed method achieves a strong balance between accuracy and computational efficiency, making it well-suited for real-time facial expression recognition applications.
- 19 August 2025
- Published by MDPI AG in Big Data and Cognitive Computing
- Vol. 9 (8) , 213
Open AccessEfficient Dynamic Emotion Recognition from Facial Expressions Using Statistical Spatio-Temporal Geometric Features
Automatic Facial Expression Recognition (AFER) is a key component of affective computing, enabling machines to recognize and interpret human emotions across various applications such as human–computer interaction, healthcare, entertainment, and social robotics. Dynamic AFER systems, which exploit image sequences, can capture the temporal evolution of facial expressions but often suffer from high computational costs, limiting their suitability for real-time use. In this paper, we propose an efficient dynamic AFER approach based on a novel spatio-temporal representation. Facial landmarks are extracted, and all possible Euclidean distances are computed to model the spatial structure. To capture temporal variations, three statistical metrics are applied to each distance sequence. A feature selection stage based on the Extremely Randomized Trees (ExtRa-Trees) algorithm is then performed to reduce dimensionality and enhance classification performance. Finally, the emotions are classified using a linear multi-class Support Vector Machine (SVM) and compared against the k-Nearest Neighbors (k-NN) method. The proposed approach is evaluated on three benchmark datasets: CK+, MUG, and MMI, achieving recognition rates of 94.65%, 93.98%, and 75.59%, respectively. Our results demonstrate that the proposed method achieves a strong balance between accuracy and computational efficiency, making it well-suited for real-time facial expression recognition applications.
- Open Access
- 14 May 2025
- Published by MDPI AG in Preprints.org
Efficient Dynamic Emotion Recognition from Facial Expressions Using Statistical Spatio-Temporal Geometric Features
{Automatic Facial Expression Recognition (AFER) is a key component of affective computing, enabling machines to recognize and interpret human emotions across various applications such as human–computer interaction, healthcare, entertainment, and social robotics. Dynamic AFER systems, which exploit image sequences, can capture the temporal evolution of facial expressions but often suffer from high computational costs, limiting their suitability for real-time use. In this paper, we propose an efficient dynamic AFER approach based on a novel spatio-temporal representation. Facial landmarks are extracted, and all possible Euclidean distances are computed to model the spatial structure. To capture temporal variations, three statistical metrics are applied to each distance sequence. A feature selection stage based on the Extremely Randomized Trees (ExtRa-Trees) algorithm is then performed to reduce dimensionality and enhance classification performance. Finally, the emotions are classified using a linear multi-class Support Vector Machine (SVM) and compared against the \textit{k}-Nearest Neighbors (k-NN) method. The proposed approach is evaluated on three benchmark datasets: CK+, MUG, and MMI, achieving recognition rates of 94.65%, 93.98%, and 75.59%, respectively. Our results demonstrate that the proposed method achieves a strong balance between accuracy and computational efficiency, making it well-suited for real-time facial expression recognition applications.
- 14 May 2025
- Published by MDPI AG in Preprints.org
Open AccessEfficient Dynamic Emotion Recognition from Facial Expressions Using Statistical Spatio-Temporal Geometric Features
{Automatic Facial Expression Recognition (AFER) is a key component of affective computing, enabling machines to recognize and interpret human emotions across various applications such as human–computer interaction, healthcare, entertainment, and social robotics. Dynamic AFER systems, which exploit image sequences, can capture the temporal evolution of facial expressions but often suffer from high computational costs, limiting their suitability for real-time use. In this paper, we propose an efficient dynamic AFER approach based on a novel spatio-temporal representation. Facial landmarks are extracted, and all possible Euclidean distances are computed to model the spatial structure. To capture temporal variations, three statistical metrics are applied to each distance sequence. A feature selection stage based on the Extremely Randomized Trees (ExtRa-Trees) algorithm is then performed to reduce dimensionality and enhance classification performance. Finally, the emotions are classified using a linear multi-class Support Vector Machine (SVM) and compared against the \textit{k}-Nearest Neighbors (k-NN) method. The proposed approach is evaluated on three benchmark datasets: CK+, MUG, and MMI, achieving recognition rates of 94.65%, 93.98%, and 75.59%, respectively. Our results demonstrate that the proposed method achieves a strong balance between accuracy and computational efficiency, making it well-suited for real-time facial expression recognition applications.
- 15 March 2025
- Published by Springer Nature in International Journal of Intelligent Transportation Systems Research
- Vol. 23 (2) , 720-732
Efficient Driver Drowsiness Detection Using Spatiotemporal Features with Support Vector Machine
- 15 March 2025
- Published by Springer Nature in International Journal of Intelligent Transportation Systems Research
- Vol. 23 (2) , 720-732
Efficient Driver Drowsiness Detection Using Spatiotemporal Features with Support Vector Machine
- Open Access
- 4 March 2025
- Published by Association for Computing Machinery (ACM)
- p. 129-134
Introducing a Novel Protocol for Collecting Annotated Images to Automate Concrete Structure Damage Severity Assessment
- 4 March 2025
- Published by Association for Computing Machinery (ACM)
- p. 129-134
Open AccessIntroducing a Novel Protocol for Collecting Annotated Images to Automate Concrete Structure Damage Severity Assessment
- 1 February 2025
- Published by Springer Nature in International Journal of Intelligent Robotics and Applications
- Vol. 9 (3) , 1082-1096
Automating quality control: real-time defect detection and automated decision-making with ai and doosan robotics
- 1 February 2025
- Published by Springer Nature in International Journal of Intelligent Robotics and Applications
- Vol. 9 (3) , 1082-1096
Automating quality control: real-time defect detection and automated decision-making with ai and doosan robotics
- Open Access
- 25 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 5648-5659
SafeRespirator: Comprehensive Database for N95 Filtering Facepiece Respirator Leakage Detection Including Infrared, RGB Videos, and Quantitative Fit Testing
The COVID-19 pandemic underscored the challenges of performing mandatory Quantitative Fit Tests (QNFT) for healthcare professionals and the limitations of self-administered fit checks. To address this, it is crucial to develop faster and more efficient methods for detecting, locating, and quantifying leaks in Filtering Facepiece Respirators (FFRs), providing wearers with immediate feedback on their safety. Infrared (IR) technology, which relies on temperature variation analysis around the face seal, has proven effective for locating leaks but has not yet achieved automated quantification. This paper introduces a validated protocol for creating a comprehensive database to advance automatic leak detection. The database includes synchronized and calibrated IR and RGB video data, along with QNFT results, collected from 62 participants wearing four different N95 FFR models in four distinct positions. High-performance IR and RGB cameras were used to precisely capture temperature variations, while a PortaCount® instrument served as the reference for fit quantification. Preliminary results demonstrate the ability of IR imaging to accurately monitor temperature variations across the facial seal, paving the way for automated detection. This open-access database is available to the scientific community to drive innovation in respiratory protection research and beyond.
- 25 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 5648-5659
Open AccessSafeRespirator: Comprehensive Database for N95 Filtering Facepiece Respirator Leakage Detection Including Infrared, RGB Videos, and Quantitative Fit Testing
The COVID-19 pandemic underscored the challenges of performing mandatory Quantitative Fit Tests (QNFT) for healthcare professionals and the limitations of self-administered fit checks. To address this, it is crucial to develop faster and more efficient methods for detecting, locating, and quantifying leaks in Filtering Facepiece Respirators (FFRs), providing wearers with immediate feedback on their safety. Infrared (IR) technology, which relies on temperature variation analysis around the face seal, has proven effective for locating leaks but has not yet achieved automated quantification. This paper introduces a validated protocol for creating a comprehensive database to advance automatic leak detection. The database includes synchronized and calibrated IR and RGB video data, along with QNFT results, collected from 62 participants wearing four different N95 FFR models in four distinct positions. High-performance IR and RGB cameras were used to precisely capture temperature variations, while a PortaCount® instrument served as the reference for fit quantification. Preliminary results demonstrate the ability of IR imaging to accurately monitor temperature variations across the facial seal, paving the way for automated detection. This open-access database is available to the scientific community to drive innovation in respiratory protection research and beyond.
- Open Access
Advanced Defect Detection on Curved Aeronautical Surfaces Through Infrared Imaging and Deep Learning
Detecting defects on aerospace surfaces is critical to ensure safety and maintain the integrity of aircraft structures. Traditional methods often need more precision and efficiency for effective defect detection. This paper proposes an innovative approach that leverages deep learning and infrared imaging techniques to detect defects with high precision. The core contribution of our work lies in accurately detecting the size and depth of defects. Our method involves segmenting the size of the defect and calculating its centre to determine its depth. We achieve a more comprehensive and precise assessment of defects by integrating deep learning with infrared imaging based on the U-net model for segmentation and the CNN model for classification. The proposed model was rigorously tested on both a simulation dataset and an experimental dataset, demonstrating its robustness and effectiveness in accurately identifying and assessing defects on aerospace surfaces. The results indicate significant improvements in detection accuracy and computational efficiency, showing advancements over state-of-the-art methods and paving the way for enhanced maintenance protocols in the aerospace industry.
Open AccessAdvanced Defect Detection on Curved Aeronautical Surfaces Through Infrared Imaging and Deep Learning
Detecting defects on aerospace surfaces is critical to ensure safety and maintain the integrity of aircraft structures. Traditional methods often need more precision and efficiency for effective defect detection. This paper proposes an innovative approach that leverages deep learning and infrared imaging techniques to detect defects with high precision. The core contribution of our work lies in accurately detecting the size and depth of defects. Our method involves segmenting the size of the defect and calculating its centre to determine its depth. We achieve a more comprehensive and precise assessment of defects by integrating deep learning with infrared imaging based on the U-net model for segmentation and the CNN model for classification. The proposed model was rigorously tested on both a simulation dataset and an experimental dataset, demonstrating its robustness and effectiveness in accurately identifying and assessing defects on aerospace surfaces. The results indicate significant improvements in detection accuracy and computational efficiency, showing advancements over state-of-the-art methods and paving the way for enhanced maintenance protocols in the aerospace industry.
- 21 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 28, 1-5
Enhancing Manufacturing Efficiency With Computer Vision And Doosan Robotics: An Overview Of Real-Time Object Detection And Automated Decision-Making
This article presents a solution developed with Doosan Robotics and OnRobot for identifying missing or broken pull tabs in manufacturing processes using computer vision and robotics integration. The solution involves a collaborative robot equipped with a 2.5D camera and an end-effector capable of grasping and manipulating objects. The 2.5D camera captures images of the objects, and computer vision algorithms are applied to detect and identify the presence of pull tabs and assess their condition. The system utilizes advanced image processing techniques to analyze the captured images, identifying any instances of missing or broken pull tabs. Upon detection, the robot employs its end-effector to interact with the identified pull tabs, facilitating their removal or replacement as necessary. The integration also incorporates automated decision-making algorithms to optimize production efficiency, reduce errors, and improve product quality. Integrating these technologies enhances precision, accuracy, and speed in identifying and manipulating objects, leading to increased productivity, cost reduction, and improved product quality.
- 21 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 28, 1-5
Enhancing Manufacturing Efficiency With Computer Vision And Doosan Robotics: An Overview Of Real-Time Object Detection And Automated Decision-Making
This article presents a solution developed with Doosan Robotics and OnRobot for identifying missing or broken pull tabs in manufacturing processes using computer vision and robotics integration. The solution involves a collaborative robot equipped with a 2.5D camera and an end-effector capable of grasping and manipulating objects. The 2.5D camera captures images of the objects, and computer vision algorithms are applied to detect and identify the presence of pull tabs and assess their condition. The system utilizes advanced image processing techniques to analyze the captured images, identifying any instances of missing or broken pull tabs. Upon detection, the robot employs its end-effector to interact with the identified pull tabs, facilitating their removal or replacement as necessary. The integration also incorporates automated decision-making algorithms to optimize production efficiency, reduce errors, and improve product quality. Integrating these technologies enhances precision, accuracy, and speed in identifying and manipulating objects, leading to increased productivity, cost reduction, and improved product quality.