Pour savoir comment effectuer et gérer un dépôt de document, consultez le « Guide abrégé – Dépôt de documents » sur le site Web de la Bibliothèque. Pour toute question, écrivez à corpus@ulaval.ca.
 

Personne :
Yousefi, Bardia

En cours de chargement...
Photo de profil

Adresse électronique

Date de naissance

Projets de recherche

Structures organisationnelles

Fonction

Nom de famille

Yousefi

Prénom

Bardia

Affiliation

Université Laval. Département de génie électrique et de génie informatique

ISNI

ORCID

Identifiant Canadiana

ncf11899549

person.page.name

Résultats de recherche

Voici les éléments 1 - 7 sur 7
  • PublicationAccès libre
    Thermography data fusion and non-negative matrix factorization for the evaluation of cultural heritage objects and buildings
    (Springer, 2018-08-24) Avdelidis, Nicolas P.; Maldague, Xavier; Ibarra Castanedo, Clemente; Yousefi, Bardia; Sfarra, Stefano
    The application of the thermal and infrared technology in different areas of research is considerably increasing. These applications involve nondestructive testing, medical analysis (computer aid diagnosis/detection—CAD), and arts and archeology, among many others. In the arts and archeology field, infrared technology provides significant contributions in terms of finding defects of possible impaired regions. This has been done through a wide range of different thermographic experiments and infrared methods. The proposed approach here focuses on application of some known factor analysis methods such as standard nonnegative matrix factorization (NMF) optimized by gradient-descent-based multiplicative rules (SNMF1) and standard NMF optimized by nonnegative least squares active-set algorithm (SNMF2) and eigen-decomposition approaches such as principal component analysis (PCA) in thermography, and candid covariance-free incremental principal component analysis in thermography to obtain the thermal features. On the one hand, these methods are usually applied as preprocessing before clustering for the purpose of segmentation of possible defects. On the other hand, a wavelet-based data fusion combines the data of each method with PCA to increase the accuracy of the algorithm. The quantitative assessment of these approaches indicates considerable segmentation along with the reasonable computational complexity. It shows the promising performance and demonstrated a confirmation for the outlined properties. In particular, a polychromatic wooden statue, a fresco, a painting on canvas, and a building were analyzed using the above-mentioned methods, and the accuracy of defect (or targeted) region segmentation up to 71.98%, 57.10%, 49.27%, and 68.53% was obtained, respectively.
  • PublicationAccès libre
    Incremental low rank noise reduction for robust infrared tracking of body temperature during medical imaging
    (MDPI, 2019-11-07) Maldague, Xavier; Klein, Matthieu; Ibarra Castanedo, Clemente; Laurendeau, Denis; Eskandari, Mana; Watts, Raymon; Sharifipour, Hossein Memarzadeh; Yousefi, Bardia
    Thermal imagery for monitoring of body temperature provides a powerful tool to decrease health risks (e.g., burning) for patients during medical imaging (e.g., magnetic resonance imaging). The presented approach discusses an experiment to simulate radiology conditions with infrared imaging along with an automatic thermal monitoring/tracking system. The thermal tracking system uses an incremental low-rank noise reduction applying incremental singular value decomposition (SVD) and applies color based clustering for initialization of the region of interest (ROI) boundary. Then a particle filter tracks the ROI(s) from the entire thermal stream (video sequence). The thermal database contains 15 subjects in two positions (i.e., sitting, and lying) in front of thermal camera. This dataset is created to verify the robustness of our method with respect to motion-artifacts and in presence of additive noise (2–20%—salt and pepper noise). The proposed approach was tested for the infrared images in the dataset and was able to successfully measure and track the ROI continuously (100% detecting and tracking the temperature of participants), and provided considerable robustness against noise (unchanged accuracy even in 20% additive noise), which shows promising performance
  • PublicationAccès libre
    Mineral identification using data-mining in hyperspectral infrared imagery
    (2018) Yousefi, Bardia; Beaudoin, Georges; Maldague, Xavier
    Les applications de l’imagerie infrarouge dans le domaine de la géologie sont principalement des applications hyperspectrales. Elles permettent entre autre l’identification minérale, la cartographie, ainsi que l’estimation de la portée. Le plus souvent, ces acquisitions sont réalisées in-situ soit à l’aide de capteurs aéroportés, soit à l’aide de dispositifs portatifs. La découverte de minéraux indicateurs a permis d’améliorer grandement l’exploration minérale. Ceci est en partie dû à l’utilisation d’instruments portatifs. Dans ce contexte le développement de systèmes automatisés permettrait d’augmenter à la fois la qualité de l’exploration et la précision de la détection des indicateurs. C’est dans ce cadre que s’inscrit le travail mené dans ce doctorat. Le sujet consistait en l’utilisation de méthodes d’apprentissage automatique appliquées à l’analyse (au traitement) d’images hyperspectrales prises dans les longueurs d’onde infrarouge. L’objectif recherché étant l’identification de grains minéraux de petites tailles utilisés comme indicateurs minéral -ogiques. Une application potentielle de cette recherche serait le développement d’un outil logiciel d’assistance pour l’analyse des échantillons lors de l’exploration minérale. Les expériences ont été menées en laboratoire dans la gamme relative à l’infrarouge thermique (Long Wave InfraRed, LWIR) de 7.7m à 11.8 m. Ces essais ont permis de proposer une méthode pour calculer l’annulation du continuum. La méthode utilisée lors de ces essais utilise la factorisation matricielle non négative (NMF). En utlisant une factorisation du premier ordre on peut déduire le rayonnement de pénétration, lequel peut ensuite être comparé et analysé par rapport à d’autres méthodes plus communes. L’analyse des résultats spectraux en comparaison avec plusieurs bibliothèques existantes de données a permis de mettre en évidence la suppression du continuum. Les expérience ayant menés à ce résultat ont été conduites en utilisant une plaque Infragold ainsi qu’un objectif macro LWIR. L’identification automatique de grains de différents matériaux tels que la pyrope, l’olivine et le quartz a commencé. Lors d’une phase de comparaison entre des approches supervisées et non supervisées, cette dernière s’est montrée plus approprié en raison du comportement indépendant par rapport à l’étape d’entraînement. Afin de confirmer la qualité de ces résultats quatre expériences ont été menées. Lors d’une première expérience deux algorithmes ont été évalués pour application de regroupements en utilisant l’approche FCC (False Colour Composite). Cet essai a permis d’observer une vitesse de convergence, jusqu’a vingt fois plus rapide, ainsi qu’une efficacité significativement accrue concernant l’identification en comparaison des résultats de la littérature. Cependant des essais effectués sur des données LWIR ont montré un manque de prédiction de la surface du grain lorsque les grains étaient irréguliers avec présence d’agrégats minéraux. La seconde expérience a consisté, en une analyse quantitaive comparative entre deux bases de données de Ground Truth (GT), nommée rigid-GT et observed-GT (rigide-GT: étiquet manuel de la région, observée-GT:étiquetage manuel les pixels). La précision des résultats était 1.5 fois meilleur lorsque l’on a utlisé la base de données observed-GT que rigid-GT. Pour les deux dernières epxérience, des données venant d’un MEB (Microscope Électronique à Balayage) ainsi que d’un microscopie à fluorescence (XRF) ont été ajoutées. Ces données ont permis d’introduire des informations relatives tant aux agrégats minéraux qu’à la surface des grains. Les résultats ont été comparés par des techniques d’identification automatique des minéraux, utilisant ArcGIS. Cette dernière a montré une performance prometteuse quand à l’identification automatique et à aussi été utilisée pour la GT de validation. Dans l’ensemble, les quatre méthodes de cette thèse représentent des méthodologies bénéfiques pour l’identification des minéraux. Ces méthodes présentent l’avantage d’être non-destructives, relativement précises et d’avoir un faible coût en temps calcul ce qui pourrait les qualifier pour être utilisée dans des conditions de laboratoire ou sur le terrain.
  • PublicationRestreint
    Comparison assessment of low rank sparse-PCA based-clustering/ classification for automatic mineral identification in long wave infrared hyperspectral imagery
    (Elsevier, 2018-07-17) Beaudoin, Georges; Chamberland, Martin; Maldague, Xavier; Ibarra Castanedo, Clemente; Sojasi, Saeed; Yousefi, Bardia
    The developments in hyperspectral technology in different applications are known in many fields particularly in remote sensing, airborne imagery, mineral identification and core logging. The automatic mineral identification system provides considerable assistance in geology to identify mineral automatically. Here, the proposed approach addresses an automated system for mineral (i.e. pyrope, olivine, quartz) identification in the long-wave infrared (7.7–11.8 μm - LWIR) ground-based spectroscopy. A low-rank Sparse Principal Component Analysis (Sparse-PCA) based spectral comparison methods such as Spectral Angle Mapper (SAM), Spectral Information Divergence (SID), Normalized Cross Correlation (NCC) have been used to extract the features in the form of false colors composite. Low-rank Sparse-PCA is used to extract the spectral reference which and showed high similarity to the ASTER (JPL/NASA) spectral library. For decision making step, two methods used to establish a comparison between a kernel Extreme Learning Machine (ELM) and Principal Component Analysis (PCA) kernel K-means clustering. ELM yields classification accuracy up to 76.69% using SAM based polynomial kernel ELM for pyrope mixture, and 70.95% using SAM based sigmoid kernel ELM for olivine mixture. This accuracy is slightly lower as compared to clustering which yields an identification accuracy of 84.91% (NCC) and 69.9% (SAM). However, the supervised classification significantly depends on the number of training samples and is considerably more difficult as compared to clustering due to labeling and training limitations. Moreover, the results indicate considerable similarity between the spectra from low rank approximation from the spectra of pure sample and the spectra from the ASTER spectral library.
  • PublicationRestreint
    Low-rank sparse principal component thermography (sparse-PCT) : comparative assessment on detection of subsurface defects
    (Pergamon, 2019-03-18) Maldague, Xavier; Ibarra Castanedo, Clemente; Sarasini, Fabrizio; Yousefi, Bardia; Sfarra, Stefano
    Infrared Non-destructive Testing (IRNDT) applications are unequivocally expanded and portend a commodity to improve the quality of defect detection in different fields such as aviation and industrial methods to arts and archaeology. The proposed approach focuses on the application of low-rank sparse principal component thermography (Sparse-PCT or SPCT) to assess the advantages and drawbacks of the method for non-destructive testing. For benchmarking the approach, two types of infrared image sets are tested: the Square Pulse Thermography (SPT) method for two hybrid composites (carbon and flax fiber reinforced epoxy), and passive infrared test of Bell Tower and the University of L’Aquila (AQ) faculty’s wall infrared sets. The quantitative assessment of the approach is also compared for every method and indicate considerable segmentation performance where other similar approaches were not able to detect the defects. SPCT performance was compared to some popular decomposition methods such as principal component thermography (PCT), candid covariancefree incremental principal component thermography (CCIPCT), non-negative matrix factorization (NMF) using gradient descent (GD) or non-negative least square (NNLS). The comparative results demonstrate the considerable performance while the other methods failed.
  • PublicationAccès libre
    Unsupervised automatic tracking of thermal changes in human body
    (Optical Society of America, 2015-09-30) Jo, Marcelo Sung Ma; Labrie-Larrivée, Félix; Fleuret, Julien; Maldague, Xavier; Fréchet, Simon; Ghaffari, Seyed Alireza; Yousefi, Bardia; Watt, Raymond
    An automated system for detecting and tracking of the thermal fluctuation in human body is addressed. It applies HSV based k-means clustering which initialized and controlled the points which lie on the ROI boundary. Afterward a particle filter tracked the targeted ROI in the thermal video stream. There were six subjects have voluntarily participated on these experiments. For simulating the hot spots occur during the some medical tests a controllable heater utilized close to the subjects body. The results indicated promising accuracy of the proposed approach for tracking the hot spots. However, there were some approximations (e.g. the transmittance of the atmosphere and emissivity of the fabric) which can be neglected because of independency of the proposed approach for these parameters. The approach can track the heating spots efficiently considering the movement in the subjects which provided a confidence of considerable robustness against motion-artifact usually occurs in the medical tests.
  • PublicationAccès libre
    Automated assessment and tracking of human body thermal variations using unsupervised clustering
    (The Optical Society of America, 2016-11-17) Fleuret, Julien; Zhang, Hai; Maldague, Xavier; Yousefi, Bardia; Watt, Raymond; Klein, Matthieu
    The presented approach addresses a review of the overheating that occurs during radiological examinations, such as magnetic resonance imaging, and a series of thermal experiments to determine a thermally suitable fabric material that should be used for radiological gowns. Moreover, an automatic system for detecting and tracking of the thermal fluctuation is presented. It applies hue-saturated-value-based kernelled k-means clustering, which initializes and controls the points that lie on the region-of-interest (ROI) boundary. Afterward, a particle filter tracks the targeted ROI during the video sequence independently of previous locations of overheating spots. The proposed approach was tested during experiments and under conditions very similar to those used during real radiology exams. Six subjects have voluntarily participated in these experiments. To simulate the hot spots occurring during radiology, a controllable heat source was utilized near the subject’s body. The results indicate promising accuracy for the proposed approach to track hot spots. Some approximations were used regarding the transmittance of the atmosphere, and emissivity of the fabric could be neglected because of the independence of the proposed approach for these parameters. The approach can track the heating spots continuously and correctly, even for moving subjects, and provides considerable robustness against motion artifact, which occurs during most medical radiology procedures.