Academic literature on the topic 'Detection et segmentation des lignes'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the lists of relevant articles, books, theses, conference reports, and other scholarly sources on the topic 'Detection et segmentation des lignes.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Journal articles on the topic "Detection et segmentation des lignes"
1
Lessard, Claude, and Creutzer Mathurin. "L’évolution du corps enseignant québécois : 1960-1986." Revue des sciences de l'éducation 15, no. 1 (November 26, 2009): 43–71. http://dx.doi.org/10.7202/900617ar.
Full textAbstract:
Résumé Dans cet article, les auteurs esquissent les grandes lignes d’une problématique de l’évolution du corps enseignant québécois des niveaux primaire et secondaire, de la Révolution tranquille à aujourd’hui. La démarche essentiellement socio-historique aborde à la fois la structuration interne du corps enseignant et ses paramètres d’intégration, de différenciation et de segmentation, et aussi l’évolution de la conception dominante de la fonction enseignante. Une attention est portée à l’Université comme instance de légitimation professionnelle des enseignants. Au plan théorique, les auteurs abordent l’opposition professionnalisation-prolétarisation en tant que manière de saisir et d’insérer le corps enseignant dans les rapports sociaux dominants.
2
Çiftci, Sadettin, and Bahattin Kerem Aydin. "Comment on Lee et al. Accuracy of New Deep Learning Model-Based Segmentation and Key-Point Multi-Detection Method for Ultrasonographic Developmental Dysplasia of the Hip (DDH) Screening. Diagnostics 2021, 11, 1174." Diagnostics 12, no. 7 (July 18, 2022): 1738. http://dx.doi.org/10.3390/diagnostics12071738.
Full textAbstract:
We have read the article titled “Accuracy of New Deep Learning Model-Based Segmentation and Key-Point Multi-Detection Method for Ultrasonographic Developmental Dysplasia of the Hip (DDH) Screening” by Lee et al. [...]
3
El-shazli, Alaa M. Adel, Sherin M. Youssef, and Marwa Elshennawy. "COMPUTER-AIDED MODEL FOR BREAST CANCER DETECTION IN MAMMOGRAMS." International Journal of Pharmacy and Pharmaceutical Sciences 8, no. 2 (September 17, 2016): 31. http://dx.doi.org/10.22159/ijpps.2016v8s2.15216.
Full textAbstract:
<p>The objective of this research was to introduce a new system for automated detection of breast masses in mammography images. The system will be able to discriminate if the image has a mass or not, as well as benign and malignant masses. The new automated ROI segmentation model, where a profiling model integrated with a new iterative growing region scheme has been proposed. The ROI region segmentation is integrated with both statistical and texture feature extraction and selection to discriminate suspected regions effectively. A classifier model is designed using linear fisher classifier for suspected region identification. To check the system’s performance, a large mammogram database has been used for experimental analysis. Sensitivity, specificity, and accuracy have been used as performance measures. In this study, the methods yielded an accuracy of 93% for normal/abnormal classification and a 79% accuracy for bening/malignant classification. The proposed model had an improvement of 8% for normal/abnormal classification, and a 7% improvement for benign/malignant classification over Naga <em>et al.</em>, 2001. Moreover, the model improved 8% for normal/abnormal classification over Subashimi <em>et al.</em>, 2015. The early diagnosis of this disease has a major role in its treatment. Thus the use of computer systems as a detection tool could be viewed as essential to helping with this disease.</p>
4
Nour, Majid, Hakan Öcal, Adi Alhudhaif, and Kemal Polat. "Skin Lesion Segmentation Based on Edge Attention Vnet with Balanced Focal Tversky Loss." Mathematical Problems in Engineering 2022 (June 14, 2022): 1–10. http://dx.doi.org/10.1155/2022/4677044.
Full textAbstract:
Segmentation of skin lesions from dermoscopic images plays an essential role in the early detection of skin cancer. However, skin lesion segmentation is still challenging due to artifacts such as indistinguishability between skin lesion and normal skin, hair on the skin, and reflections in the obtained dermoscopy images. In this study, an edge attention network (ET-Net) combining edge guidance module (EGM) and weighted aggregation module is added to the 2D volumetric convolutional neural network (Vnet 2D) to maximize the performance of skin lesion segmentation. In addition, the proposed fusion model presents a new fusion loss function by combining balanced binary cross-entropy (BBCE) and focal Tversky loss (FTL). The proposed model has been tested on the ISIC 2018 Task 1 Lesion Boundary Segmentation Challenge dataset. The proposed model outperformed the state-of-the-art studies as a result of the tests.
5
Chen, Shuo-Tsung, Tzung-Dau Wang, Wen-Jeng Lee, Tsai-Wei Huang, Pei-Kai Hung, Cheng-Yu Wei, Chung-Ming Chen, and Woon-Man Kung. "Coronary Arteries Segmentation Based on the 3D Discrete Wavelet Transform and 3D Neutrosophic Transform." BioMed Research International 2015 (2015): 1–9. http://dx.doi.org/10.1155/2015/798303.
Full textAbstract:
Purpose. Most applications in the field of medical image processing require precise estimation. To improve the accuracy of segmentation, this study aimed to propose a novel segmentation method for coronary arteries to allow for the automatic and accurate detection of coronary pathologies.Methods. The proposed segmentation method included 2 parts. First, 3D region growing was applied to give the initial segmentation of coronary arteries. Next, the location of vessel information, HHH subband coefficients of the 3D DWT, was detected by the proposed vessel-texture discrimination algorithm. Based on the initial segmentation, 3D DWT integrated with the 3D neutrosophic transformation could accurately detect the coronary arteries.Results. Each subbranch of the segmented coronary arteries was segmented correctly by the proposed method. The obtained results are compared with those ground truth values obtained from the commercial software from GE Healthcare and the level-set method proposed by Yang et al., 2007. Results indicate that the proposed method is better in terms of efficiency analyzed.Conclusion. Based on the initial segmentation of coronary arteries obtained from 3D region growing, one-level 3D DWT and 3D neutrosophic transformation can be applied to detect coronary pathologies accurately.
6
Zhong, Johnson. "Analyzing Out-of-Domain Generalization Performance of Pre-Trained Segmentation Models." Network and Communication Technologies 8, no. 1 (February 16, 2023): 1. http://dx.doi.org/10.5539/nct.v8n1p1.
Full textAbstract:
Artists illustrate objects to various degrees of complexity. As the amount of detail or the similarity to reality of a depiction decreases, the object tends to be reduced to its simplest, most relevant higher-level features (Harrison, 1981). One of the reasons Deep Neural Networks (DNN) may fail to identify objects in an image is that models are unable to recognize the order of importance of features such as shape, depth, or color within an image, which means even the most minute distortions of pixels within an image that would be imperceptible to humans would greatly impact the performance of the object detection models (Eykholt et al., 2018). However, by training DNN on artworks where the most prominent features defining specific objects are emphasized, perhaps a model can be made to be more resilient against small-scale changes in an image. In this paper, the correlation between the level of similarity to reality of images and artworks of an object and the accuracy of object detection models is investigated to test the ability of object detection models in identifying the most salient features of a particular object. The results of this report can help outline the efficacy of models only trained on real images in identifying increasingly abstract artworks that have simplified an object to its most prominent features. The experiment shows that the accuracies of models decrease as the images or illustrations provided become more abstract or simplified, which suggests the higher level features that identify a particular object are different in object detection models and humans.
7
Lefkovits, Szidónia, and László Lefkovits. "U-Net architecture variants for brain tumor segmentation of histogram corrected images." Acta Universitatis Sapientiae, Informatica 14, no. 1 (August 1, 2022): 49–74. http://dx.doi.org/10.2478/ausi-2022-0004.
Full textAbstract:
Abstract In this paper we propose to create an end-to-end brain tumor segmentation system that applies three variants of the well-known U-Net convolutional neural networks. In our results we obtain and analyse the detection performances of U-Net, VGG16-UNet and ResNet-UNet on the BraTS2020 training dataset. Further, we inspect the behavior of the ensemble model obtained as the weighted response of the three CNN models. We introduce essential preprocessing and post-processing steps so as to improve the detection performances. The original images were corrected and the different intensity ranges were transformed into the 8-bit grayscale domain to uniformize the tissue intensities, while preserving the original histogram shapes. For post-processing we apply region connectedness onto the whole tumor and conversion of background pixels into necrosis inside the whole tumor. As a result, we present the Dice scores of our system obtained for WT (whole tumor), TC (tumor core) and ET (enhanced tumor) on the BraTS2020 training dataset.
8
Lee, Hongseok, Kyungdoc Kim, Guhyun Kang, Kyu-Hwan Jung, and Sunyoung S. Lee. "Abstract 1721: Spatial distribution of immune cells as quantitative prognosis indicator in hepatocellular carcinoma." Cancer Research 82, no. 12_Supplement (June 15, 2022): 1721. http://dx.doi.org/10.1158/1538-7445.am2022-1721.
Full textAbstract:
Abstract Background: We previously demonstrated that the analysis of the tumor microenvironment (TME) in histopathology images via tissue segmentation [1] and cell density in lymphocyte-rich area [2] impacts prognosis and treatment in hepatocellular carcinoma (HCC). Few biomarker models exist to prognosticate patients with HCC via the automated analysis of TME at the cellular level. Methods: Clinical outcomes data and histopathology images of 351 patients with HCC were obtained from TCGA. We advanced a deep learning-based algorithm to analyze the tumor volume and spatial distribution of nuclei in TME. This was based on combination of two models: the PAIP2019 dataset was used for DenseNet-based HCC segmentation, which showed the performance of 0.8582 on the F1-score metric [3]; HoverNet-based cell detection model, which showed the performance of 0.654 on the binary PQ metric, annotated lymphocytes, macrophages, and neutrophils on the MonuSac dataset [4]. Results: The HCC segmentation model divided the TME into tumoral, marginal, and peritumoral areas by image processing. The marginal and peritumoral areas were defined as inner 50 um area and outer 100 um area from the estimated tumoral boundary, respectively. The ratios of neutrophils, lymphocytes, macrophages to the total cell count on marginal and peritumoral areas were calculated through integration of HCC segmentation and cell detection models. The proportions of leukocytes were subjected into Cox proportional hazard analysis. The results of Cox proportional hazard analysis calculated the proportions of macrophages and lymphocytes to other cells in the TME. The macrophage proportion on the peritumoral area was a significant prognostic indicator showing Log(hazard ratio) (-2.42 ± 2.14, p=0.026). The lymphocyte proportion on both areas of the peritumor and margins showed significant Log(hazard ratio) (-1.70 ± 1.61, p=0.042). Conclusions: The retrospective analysis of the TME using deep learning-assisted algorithm combining tissue segmentation and cell detection models reveals that the ratio of lymphocytes and macrophages in the peri-tumoral areas of HCC TME significantly impact prognosis. Further analyses in the prospective studies may provide more information about cellular biomarkers. [1] Kim et al. Cancer Res 2020 (80) (16 Supp) 2631 [2] Park et al. Journal of Clinical Oncology 39, no. 15_suppl (May 20, 2021) 4107-4107 [3] Kim, Yoo Jung, Jang, Hyungjoon, Lee, Kyoungbun et al. Medical Image Analysis 67 (2021): 101854. [4] Verma, Ruchika. IEEE Transactions on Medical Imaging 39 (2020): 1380-1391. [5] Graham, Simon. Medical Image Analysis 58 (2019): 101563. Citation Format: Hongseok Lee, Kyungdoc Kim, Guhyun Kang, Kyu-Hwan Jung, Sunyoung S. Lee. Spatial distribution of immune cells as quantitative prognosis indicator in hepatocellular carcinoma [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2022; 2022 Apr 8-13. Philadelphia (PA): AACR; Cancer Res 2022;82(12_Suppl):Abstract nr 1721.
9
Gujjunoori, Sagar, Madhu Oruganti, N. Aparna, M. Srija, and Chaitrali Dangare. "Tracking and Size Estimation of Objects in Motion based on Median of Localized Thresholding." International Journal of Engineering & Technology 7, no. 4.6 (September 25, 2018): 78. http://dx.doi.org/10.14419/ijet.v7i4.6.20241.
Full textAbstract:
Motion detection and tracking play an important role in Computer vision and Robotics. Optical flow based methods to estimate the motion are widely explored during the last decade. The motion information retrieved from these techniques has enormous applications. Video analysis based on the size, speed, and directions of objects have wider applications in computer vision, robotics and watermarking. Segmentation of moving objects based on the optical flow is very challenging. In this paper, we present a model to estimate the size of a moving object based on the optical flow technique and present localized thresholding technique. Over segmentation is reduced by the proposed local thresholding technique and use of bilateral filtering. We compare our results with Sagar et al. scheme.
10
Bougrine, Asma, Rachid Harba, Raphael Canals, Roger Ledee, Meryem Jabloun, and Alain Villeneuve. "Segmentation of Plantar Foot Thermal Images Using Prior Information." Sensors 22, no. 10 (May 18, 2022): 3835. http://dx.doi.org/10.3390/s22103835.
Full textAbstract:
Diabetic foot (DF) complications are associated with temperature variations. The occurrence of DF ulceration could be reduced by using a contactless thermal camera. The aim of our study is to provide a decision support tool for the prevention of DF ulcers. Thus, the segmentation of the plantar foot in thermal images is a challenging step for a non-constraining acquisition protocol. This paper presents a new segmentation method for plantar foot thermal images. This method is designed to include five pieces of prior information regarding the aforementioned images. First, a new energy term is added to the snake of Kass et al. in order to force its curvature to match that of the prior shape, which has a known form. Second, we defined the initial contour as the downsized prior-shape contour, which is placed inside the plantar foot surface in a vertical orientation. This choice makes the snake avoid strong false boundaries present outside the plantar region when evolving. As a result, the snake produces a smooth contour that rapidly converges to the true boundaries of the foot. The proposed method is compared to two classical prior-shape snake methods, that of Ahmed et al. and that of Chen et al. A database of 50 plantar foot thermal images was processed. The results show that the proposed method outperforms the previous two methods with a root-mean-square error of 5.12 pixels and a dice similarity coefficient of 94%. The segmentation of the plantar foot regions in the thermal images helped us to assess the point-to-point temperature differences between the two feet in order to detect hyperthermia regions. The presence of such regions is the pre-sign of ulcers in the diabetic foot. Furthermore, our method was applied to hyperthermia detection to illustrate the promising potential of thermography in the case of the diabetic foot. Associated with a friendly acquisition protocol, the proposed segmentation method is the first step for a future mobile smartphone-based plantar foot thermal analysis for diabetic foot patients.
Dissertations / Theses on the topic "Detection et segmentation des lignes"
1
Ouwayed, Nazih. "Segmentation en lignes de documents anciens : applications aux documents arabes." Thesis, Nancy 2, 2010. http://www.theses.fr/2010NAN23001/document.
Full textAbstract:
L'indexation de documents numérisés manuscrits pose le problème de la segmentation en lignes qui, si elle échoue, handicape les étapes suivantes d'extraction et de reconnaissance de mots. Dans les documents arabes anciens, s'ajoute à ce problème, la présence dans les marges, d'annotations souvent composées de lignes obliques. La détection de ces lignes est nécessaire et constitue un défi important pour l'indexation de ces documents. Ainsi, la segmentation visée dans ce travail de thèse concerne l'extraction de lignes multi-orientées. Pour ce problème, la bibliographie ne présente que des techniques rudimentaires basées essentiellement sur une projection directe de l'image du document suivant une seule direction et donc non applicable à du texte multi-orienté. Devant ce manque, nous avons proposé une approche adaptative permettant de localiser d'abord les zones d'orientation différentes, puis de s'appuyer sur chaque orientation locale pour extraire les lignes. Pendant ma thèse, j'ai développé les points suivants : - Application d'un maillage automatique en utilisant le modèle de contour actif (snake). - Préparation du signal de profil de projection en supprimant tous les pixels qui ne sont pas nécessaires dans le calcul de l'orientation. Ensuite, application de toutes les distributions d'énergie de la classe de Cohen sur le profil de projection pour trouver la meilleure distribution qui donne l'orientation. - Application de quelques règles d'extension pour trouver les zones. - Extraction des lignes en se basant sur un algorithme de suivi des composantes connexes. - Séparation de lignes se chevauchant et se connectant en utilisant la morphologie des lettres terminales arabesThe indexing of handwritten scanned documents poses the problem of lines segmentation, if it fails, disabling the following steps of words extraction and recognition. In addition, the ancient Arabic documents contain annotations in the margins, often composed of lines obliquely oriented. The detection of these lines is important as the rest and is a major challenge for the indexing of these documents. Thus, the segmentation described in this thesis involves the extraction of multi-oriented lines. For this problem, the bibliography has only rudimentary techniques based essentially on the projection of the document image along one direction, which be failed in the case of multi-oriented documents. Given this lack, we have proposed an adaptive approach that first locates the different orientation zones, then based on each local orientation to extract the lines. During my thesis, i particularly invested on the following points : - Applying an automatic paving using the active contour model (snake). - Preparation the signal of the projection profile by removing all pixels that are not needed in the orientation estimation. Then, implementation of all energy distributions of Cohen's class on the projection profile to find the best distribution that gives the orientation. - Applying some extension rules to find the oriented zones. - Extraction of lines by using an connected components follow-up algorithm. - Separation of overlapped and touched lines using the morphology of Arabic terminal letters
2
Cousty, Jean. "Lignes de partage des eaux discrètes : théorie et application à la segmentation d'images cardiaques." Phd thesis, Université de Marne la Vallée, 2007. http://tel.archives-ouvertes.fr/tel-00321885.
Full textAbstract:
La notion de clivage formalise l'idée d'ensemble frontiére dans un graphe. Fusionner deux régions, comme le requièrent certaines méthodes de segmentation d'images, pose des diffIcultés. Nous introduisons quatre classes de graphes (de fusion) dans lesquels ces diffIcultés sont progressivement supprimées. Nous montrons que l'une de ces classes est celle pour laquelle tout clivage est mince. Nous introduisons une relation d'adjacence, appelée grille de fusion parfaite, dans laquelle deux régions voisines peuvent être fusionnées, en préservant toutes les autres régions.La ligne de partage des eaux topologique (LPE) étend la notion de clivage aux graphes dont les sommets sont valués et permet de segmenter une image. Nous étendons les propriétés des clivages dans les graphes de fusion aux cas des fonctions et proposons un algorithme de LPE
monotone et linéaire dans les grilles de fusion parfaites. Grâce à la notion de graphe d'arêtes, les propriétés des LPE dans les grilles de fusion parfaites s'étendent aux graphes à arêtes valuées.
Nous étudions en profondeur les LPE dans les graphes à arêtes valuées. Les LPE peuvent y être définies en suivant l'idée intuitive de gouttes d'eau s'écoulant sur un relief topographique. Nous établissons aussi bien la consistance que l'optimalité de cette définition. De plus, nous proposons deux algorithmes linéaires qui, à notre connaissance, sont les plus efficaces pour le calcul des LPE.
En nous reposant sur ces résultats théoriques, nous proposons une méthode et développons un logiciel pour la segmentation du ventricule gauche dans des images cardiaques 3D+t par résonance magnétique. La méthode est quantitativement et qualitativement validée par comparaison avec des segmentations manuelles tracées par deux experts cardiologues.
3
Odobez, Jean-Marc. "Estimation, detection et segmentation du mouvement : une approche robuste et markovienne." Rennes 1, 1994. http://www.theses.fr/1994REN10207.
Full textAbstract:
Cette these traite de la detection et de la localisation d'objets en mouvement dans une sequence d'images acquises par une camera mobile. Nous motivons tout d'abord l'interet du probleme et rappelons diverses methodes existantes proposees pour le resoudre. L'approche que nous avons retenue pour la detection consiste a reconstruire dans un premier temps une sequence d'images, dans laquelle le deplacement apparent dans l'image induit par le mouvement de la camera a ete compense. Pour cela, nous supposons que ce deplacement peut etre decrit par un modele parametrique 2d. Le troisieme chapitre de ce memoire presente la methode robuste et multiresolution que nous avons developpee, qui permet d'estimer ce modele de mouvement parametre (dominant) dans l'image sans etre affecte par la presence d'autres mouvements (ceux des objets mobiles notamment). Le probleme pose se ramene alors a la detection des zones mal compensees dans la sequence ainsi reconstruite. Dans le chapitre quatre, nous definissons des mesures de compensation du mouvement adaptees a ce probleme. Ces mesures et leur fiabilite, calculees a differents instants, ainsi que la carte de detection a l'instant precedent, sont prises en compte au sein d'une regularisation statistique basee sur des modeles de markov multiechelles. L'algorithme que nous avons defini est relativement rapide et permet d'obtenir d'excellents resultats dans des situations complexes. Dans le chapitre cinq, l'algorithme de detection (binaire) precedent est etendu a la segmentation (gestion de n etiquettes) du mouvement dans une sequence d'images. Le schema complet que nous avons defini permet notamment de s'adapter au contenu dynamique de la scene, en creant de nouvelles regions lors de l'apparition de nouveaux objets dans la scene ou lorsque le mouvement d'une region donnee devient plus complexe
4
PENG, ANRONG. "Segmentation statistique non supervisee d'images et detection de contours par filtrage." Compiègne, 1992. http://www.theses.fr/1992COMP0512.
Full textAbstract:
Cette thèse est consacrée à deux catégories de méthodes de la segmentation d'images: la segmentation statistique non supervisée et la détection de contours par filtrage. Les contributions de ce travail reposent sur les études des deux familles de méthodes en soi et sur leur mise en parallèle. Dans la première partie, nous abordons la segmentation Bayesienne non supervisée. Des algorithmes d'estimation préalable à la segmentation contextuelle, tels que EM, ICE, SEM, sont étudiés. Puis ces estimateurs valables dans les champs stationnaires sont adaptés aux champs non stationnaires. En levant l'hypothèse de stationnarité pour le champ de classes, les segmentations contextuelles donnent des résultats nettement meilleurs dans certains cas. Après une application de diverses combinaisons des estimateurs et des segmentations à des images différemment bruitées, nous menons une comparaison des performances des estimateurs suivant des caractéristiques du bruit. Une étude de la robustesse de la segmentation contextuelle est effectuée, ce qui est utile pour le choix d'un estimateur, ainsi que pour la définition d'un compromis entre la précision de l'estimation et le temps de calcul. La deuxième partie est consacrée à la détection de contours par filtrage. Une définition des contours utilisant l'ordre de discontinuité est d'abord proposée. La méthodologie de la détection de contours d'ordre 0 (contour échelon) est généralisée aux contours de discontinuité d'ordre quelconque. Le problème de la détection de contours est ainsi réduit à la recherche d'un filtre de lissage optimal dont la forme joue un rôle important. L'accent est donc mis sur l'étude des formes de filtres de lissage existants. Un exemple de cette généralisation, la détection du contour rampe, est appliquée aux images simulées et images réelles. La troisième partie est consacrée à la mise en parallèle des deux familles de méthodes. Après une étude sur leurs profils différents et points communs du point de vue théorique, l'objectif principal est la comparaison de la qualité, tant visuelle que selon des critères objectifs, des contours obtenus par deux familles de méthodes. Les comparaisons sont effectuées également au sein d'une même famille. Des algorithmes d'estimation, ICE stationnaire et ICE non stationnaire, combinés avec les méthodes de segmentation, telles que aveugle et contextuelle, sont choisis comme représentants de la première famille. Le filtre de Shen est choisi comme représentant de la deuxième famille. Cette étude met en lumière les différences de comportement des deux familles de méthodes, et peut ainsi servir à la décision quant au choix de la méthode la plus appropriée en fonction de propriétés objectives des images.
5
Migniot, Cyrille. "Segmentation de personnes dans les images et les vidéos." Phd thesis, Université de Grenoble, 2012. http://tel.archives-ouvertes.fr/tel-00677592.
Full textAbstract:
La segmentation de personnes dans les images et les vidéos est une problématique actuellement au coeur de nombreux travaux. Nous nous intéressons à la segmentation de personnes debout. Pour cela, nous avons mis au point deux méthodes originales : La première est une continuation d'une méthode de détection efficace. On réalise une pré-segmentation en associant aux segments de contour de l'image une valeur de vraisemblance en tant qu'élément d'une silhouette humaine par une combinaison d'histogrammes de gradients orientés (HOG) et de machines à vecteurs de support (SVM) prises à l'échelle des ces segments. Une recherche d'arbre optimal dans un graphe intégrant les données de la pré-segmentation permet de reconstruire la silhouette de la personne. Enfin, une utilisation itérative de ce processus permet d'en améliorer la performance. La seconde méthode prend en compte l'interaction de l'utilisateur pour une image. Une coupe de graphe est guidée par un gabarit non binaire représentant une silhouette humaine. Nous proposons également un gabarit par parties pour s'adapter à la posture de la personne. Nous avons enfin transposé cette méthode à la segmentation de vidéos et la réalisation automatique de trimaps.
6
Sekkal, Rafiq. "Techniques visuelles pour la détection et le suivi d’objets 2D." Thesis, Rennes, INSA, 2014. http://www.theses.fr/2014ISAR0032/document.
Full textAbstract:
De nos jours, le traitement et l’analyse d’images trouvent leur application dans de nombreux domaines. Dans le cas de la navigation d’un robot mobile (fauteuil roulant) en milieu intérieur, l’extraction de repères visuels et leur suivi constituent une étape importante pour la réalisation de tâches robotiques (localisation, planification, etc.). En particulier, afin de réaliser une tâche de franchissement de portes, il est indispensable de détecter et suivre automatiquement toutes les portes qui existent dans l’environnement. La détection des portes n’est pas une tâche facile : la variation de l’état des portes (ouvertes ou fermées), leur apparence (de même couleur ou de couleur différentes des murs) et leur position par rapport à la caméra influe sur la robustesse du système. D’autre part, des tâches comme la détection des zones navigables ou l’évitement d’obstacles peuvent faire appel à des représentations enrichies par une sémantique adaptée afin d’interpréter le contenu de la scène. Pour cela, les techniques de segmentation permettent d’extraire des régions pseudo-sémantiques de l’image en fonction de plusieurs critères (couleur, gradient, texture…). En ajoutant la dimension temporelle, les régions sont alors suivies à travers des algorithmes de segmentation spatio-temporelle. Dans cette thèse, des contributions répondant aux besoins cités sont présentées. Tout d’abord, une technique de détection et de suivi de portes dans un environnement de type couloir est proposée : basée sur des descripteurs géométriques dédiés, la solution offre de bons résultats. Ensuite, une technique originale de segmentation multirésolution et hiérarchique permet d’extraire une représentation en régions pseudosémantique. Enfin, cette technique est étendue pour les séquences vidéo afin de permettre le suivi des régions à travers le suivi de leurs contours. La qualité des résultats est démontrée et s’applique notamment au cas de vidéos de couloirNowadays, image processing remains a very important step in different fields of applications. In an indoor environment, for a navigation system related to a mobile robot (electrical wheelchair), visual information detection and tracking is crucial to perform robotic tasks (localization, planning…). In particular, when considering passing door task, it is essential to be able to detect and track automatically all the doors that belong to the environment. Door detection is not an obvious task: the variations related to the door status (open or closed), their appearance (e.g. same color as the walls) and their relative position to the camera have influence on the results. On the other hand, tasks such as the detection of navigable areas or obstacle avoidance may involve a dedicated semantic representation to interpret the content of the scene. Segmentation techniques are then used to extract pseudosemantic regions based on several criteria (color, gradient, texture...). When adding the temporal dimension, the regions are tracked then using spatiotemporal segmentation algorithms. In this thesis, we first present joint door detection and tracking technique in a corridor environment: based on dedicated geometrical features, the proposed solution offers interesting results. Then, we present an original joint hierarchical and multiresolution segmentation framework able to extract a pseudo-semantic region representation. Finally, this technique is extended to video sequences to allow the tracking of regions along image sequences. Based on contour motion extraction, this solution has shown relevant results that can be successfully applied to corridor videos
7
LIAO, QINGMIN. "Detection de contours et segmentation d'images : applications a la teledetection et a la biologie marine." Rennes 1, 1994. http://www.theses.fr/1994REN10183.
Full textAbstract:
Dans le cadre de cette these, nous avons developpe une methode de detection de contours et une methode de segmentation d'images afin d'aboutir a une meilleure interpretation des images. La premiere methode permet une localisation precise et une detection de contours insensible au bruit. La precision de la localisation a ete obtenue en agrandissant le support de l'image. Pour reduire l'influence du bruit, un indice de confiance du contour tenant compte de la regularite de la surface locale et de certains criteres lies a la perception visuelle a ete etabli. La methode de segmentation basee sur une cooperation contour-region est effectuee en deux etapes: fermeture de contours et classification de parcelles. Trois methodes de modelisation de textures ont ete mises au point et testees lors de la phase de la classification. Deux applications ont ete etudiees. La premiere consiste a identifier des plantations forestieres dans une image satellitaire. Ceci a ete realise par notre approche de segmentation. La deuxieme application portait sur la classification de differentes categories d'ufs de poissons et sur l'identification de leurs stades de croissance. Pour cela, les structures biologiques significatives ont ete tout d'abord detectees ; ensuite, les parametres pertinents ont ete extraits ; enfin, les ufs de poissons ont ete identifies selon des criteres biologiques. Les methodes developpees permettent donc d'analyser les images provenant de differents types de sources et d'ameliorer considerablement les resultats de detection de contours et de segmentation d'images
8
Gresson, Régis. "Segmentation et reconstruction tridimensionnelle du foyer de microcalcifications mammaires." Vandoeuvre-les-Nancy, INPL, 1998. http://www.theses.fr/1998INPL108N.
Full textAbstract:
Les travaux présentés dans ce mémoire traitent de la segmentation et de la reconstruction tridimensionnelle du foyer de microcalcifications mammaires. Ces travaux sont scindés en deux parties. La première partie a été consacrée à la détermination d'une méthode automatique de détection et de segmentation des microcalcifications. Nous avons évalué et testé les principales méthodes de segmentation répertoriées dans la littérature (le filtrage de chan, la morphologie mathématique en niveaux de gris, la méthode par hystérésis, les méthodes fractales (classique et par les ondelettes) et la technique de multirésolution (analyse pyramidale). L'appréciation des méthodes s'est faite en fonction de quatre critères qualitatifs déterminants, à savoir : la forme et la taille du foyer, le nombre et la position des microcalcifications. Cette étude nous a permis de proposer une méthode donnant de bons résultats (92% de bonnes détections, 8% de faux négatifs et 15% de faux positifs). La deuxième partie a été consacrée à la reconstruction 3D du foyer de microcalcifications nous avons décomposé la résolution du problème en trois phases : la calibration du système de vision, la recherche de primitives de mise en correspondance des microcalcifications, et enfin la reconstruction 3D en elle même. La méthode de reconstruction 3D est basée sur la contrainte de la ligne épipolaire. Les ambigüités de positionnement ont été levées par l'utilisation de rapports de surface des microcalcifications et par l'utilisation de trois radiographies. Les résultats obtenus en reconstruction tridimensionnelle sont encourageants, car malgré un matériel de qualité discutable, nous arrivons à reconstruire le foyer avec une assez bonne précision. Nous obtenons une précision relative de 10% en x, 3% en y et de 0,5% en z. Seule l'imprécision absolue en z atteint des valeurs élevées (20%), cette imprécision n'est pas gênante puisqu'elle n'influe pas sur la forme du foyer reconstruit.
9
SADKI, MUSTAPHA. "Detection et segmentation d'objets d'interet en imagerie 2d et 3d par classification automatique des pixels et optimisation sous contraintes geometriques de contours deformables." Université Louis Pasteur (Strasbourg) (1971-2008), 1997. http://www.theses.fr/1997STR13270.
Full textAbstract:
Cette these propose une methodologie et des algorithmes de detection et de segmentation d'objets d'interet par classification automatique des pixels et optimisation sous contraintes geometriques de contours deformables, qui ont ete appliques avec succes a la detection d'anomalies en imagerie mammographique, a l'extraction automatique de stenoses dans des images tomodensitometriques 3d et a l'extraction de franges dans des images de moire inverse pour la saisie de formes 3d dans le domaine de la metrologie. Du point de vue de l'analyse d'images, l'objectif est de montrer qu'il est possible de resoudre ces problemes de vision par ordinateur, sans introduire de considerations avancees ou de connaissances specifiques du domaine d'application considere, aussi bien dans le cas de la mammographie et de la tomodensitometrique que dans celui de la saisie de formes 3d par moire, en les traitant comme des problemes de perception visuelle humaine simulables par des algorithmes de traitement d'images et d'analyse de donnees multidimensionnelles. C'est grace a cette propriete d'independance par rapport au domaine d'application que les algorithmes presentes dans cette these ont ete utilises avec succes aussi bien en imagerie mammographique, qu'en tomodensitometrique 3d par scanner x ou en metrologie de formes 3d par analyse d'images de moire inverse.
10
Bonakdar, Sakhi Omid. "Segmentation of heterogeneous document images : an approach based on machine learning, connected components analysis, and texture analysis." Phd thesis, Université Paris-Est, 2012. http://tel.archives-ouvertes.fr/tel-00912566.
Full textAbstract:
Document page segmentation is one of the most crucial steps in document image analysis. It ideally aims to explain the full structure of any document page, distinguishing text zones, graphics, photographs, halftones, figures, tables, etc. Although to date, there have been made several attempts of achieving correct page segmentation results, there are still many difficulties. The leader of the project in the framework of which this PhD work has been funded (*) uses a complete processing chain in which page segmentation mistakes are manually corrected by human operators. Aside of the costs it represents, this demands tuning of a large number of parameters; moreover, some segmentation mistakes sometimes escape the vigilance of the operators. Current automated page segmentation methods are well accepted for clean printed documents; but, they often fail to separate regions in handwritten documents when the document layout structure is loosely defined or when side notes are present inside the page. Moreover, tables and advertisements bring additional challenges for region segmentation algorithms. Our method addresses these problems. The method is divided into four parts:1. Unlike most of popular page segmentation methods, we first separate text and graphics components of the page using a boosted decision tree classifier.2. The separated text and graphics components are used among other features to separate columns of text in a two-dimensional conditional random fields framework.3. A text line detection method, based on piecewise projection profiles is then applied to detect text lines with respect to text region boundaries.4. Finally, a new paragraph detection method, which is trained on the common models of paragraphs, is applied on text lines to find paragraphs based on geometric appearance of text lines and their indentations. Our contribution over existing work lies in essence in the use, or adaptation, of algorithms borrowed from machine learning literature, to solve difficult cases. Indeed, we demonstrate a number of improvements : on separating text columns when one is situated very close to the other; on preventing the contents of a cell in a table to be merged with the contents of other adjacent cells; on preventing regions inside a frame to be merged with other text regions around, especially side notes, even when the latter are written using a font similar to that the text body. Quantitative assessment, and comparison of the performances of our method with competitive algorithms using widely acknowledged metrics and evaluation methodologies, is also provided to a large extend.(*) This PhD thesis has been funded by Conseil Général de Seine-Saint-Denis, through the FUI6 project Demat-Factory, lead by Safig SA
Book chapters on the topic "Detection et segmentation des lignes"
1
Tripathy, B. K., and P. V. S. S. R. Chandra Mouli. "Graph Based Segmentation of Digital Images." In Handbook of Research on Computational Intelligence for Engineering, Science, and Business, 182–99. IGI Global, 2013. http://dx.doi.org/10.4018/978-1-4666-2518-1.ch007.
Full textAbstract:
Image Segmentation is the process of dividing an image into semantically relevant regions. The problem is still an active area due to wide applications in object detection and recognition, image retrieval, image classification, et cetera. The problem is challenging due to its subjective nature. Many researchers addressed this problem by exploring graph theoretic principles. The key idea is the transformation of segmentation problem into graph partitioning problem by representing the image as a graph. The aim of this chapter is to study various graph based segmentation algorithms.
2
Trubuil, Alain. "Prospects in Bayesian image analysis." In Highly Structured Stochastic Systems, 326–32. Oxford University PressOxford, 2003. http://dx.doi.org/10.1093/oso/9780198510550.003.0031.
Full textAbstract:
Abstract The ideas presented by Hurn et al. offer an excellent review of the impressive work carried out by the statistical community on the Bayesian framework and its application to image analysis. Necessarily the presentation could not be exhaustive and with respect to applications, a consensus has guided the text with modelling illustrated mainly for restoration problems. My aim is to draw attention to detection, labelling, and eventually three-dimensional (3D) segmentation.
Conference papers on the topic "Detection et segmentation des lignes"
1
Zhu, Donglin, Lei Li, Rui Guo, and Shifan Zhan. "Fault Detection by Using Instance Segmentation." In International Petroleum Technology Conference. IPTC, 2021. http://dx.doi.org/10.2523/iptc-21249-ms.
Full textAbstract:
Abstract Fault detection is an important, but time-consuming task in seismic data interpretation. Traditionally, seismic attributes, such as coherency (Marfurt et al., 1998) and curvature (Al-Dossary et al., 2006) are used to detect faults. Recently, machine learning methods, such as convolution neural networks (CNNs) are used to detect faults, by applying various semantic segmentation algorithms to the seismic data (Wu et al., 2019). The most used algorithm is U-Net (Ronneberger et al., 2015), which can accurately and efficiently provide probability maps of faults. However, probabilities of faults generated by semantic segmentation algorithms are not sufficient for direct recognition of fault types and reconstruction of fault surfaces. To address this problem, we propose, for the first time, a workflow to use instance segmentation algorithm to detect different fault lines. Specifically, a modified CNN (LaneNet; Neven et al., 2018) is trained using automatically generated synthetic seismic images and corresponding labels. We then test the trained CNN using both synthetic and field collected seismic data. Results indicate that the proposed workflow is accurate and effective at detecting faults.
2
Wu, Huanyu, Yuan Zou, Qi Zhao, Chi Zhang, and Wei Yang. "Micro-CT Characterization of Lunar Regolith Using Machine Learning-Based Segmentation." In 57th U.S. Rock Mechanics/Geomechanics Symposium. ARMA, 2023. http://dx.doi.org/10.56952/arma-2023-0281.
Full textAbstract:
ABSTRACT On 17 December 2020, China's Chang’e-5 mission returned about 1.73 kg of lunar regolith from one of the youngest basalt units in northern Oceanus Procellarum. The mineralogy of the lunar surface regolith provides a wealth of information on its geological history, and the characterization of lunar regolith at high spatial resolution has been a significant goal of lunar exploration. In this study, we combine high-resolution micro-CT imaging and a state-of-the-art machine learning-based image processing approach to assess morphological and physical properties of the lunar regolith sample returned by Chang’e-5 mission. The lunar regolith sample was scanned by an X-ray micro-computed tomography (micro-CT) with a spatial resolution of 2.48 μm. A pixel-wise random forest classifier was employed to segment the volume data into regolith particles considering multiple features including intensity, edge and texture. On the basis of segmented images, the particle size distribution of the lunar regolith sample was extracted. The average density of the sample is estimated to be around 1582 kg/m3 based on a calibration of the relationship between the image intensity and material density. Particles with extremely high-density mineral phases (around 4500 kg/m3) in the sample are considered rich in metal elements such as iron and titanium. In addition, we were able to extract particles with distinguished features such as isolated pores, which implies the possible melting and solidification process related to past meteorite impacts. This study provides a workflow for micro-CT imaging-based analysis of lunar regolith. INTRODUCTION Characterization of lunar regolith is a key element in lunar base construction and in-situ resource utilization. Lunar exploration is currently the focus of deep space exploration programs around the world, including NASA's Artemis program (Creech et al., 2022) and China National Space Administration's Chang’e (CE) Project (Li et al., 2019). These exploration programs are ultimately expected to achieve a long-term human presence on the Moon. On 17 December 2020, roughly 1.73 kg of lunar regolith samples were brought back to Earth by China's CE-5 mission, which was the first-time sample return since the Apollo era around 50 years ago (Li et al., 2022). These lunar regolith samples came from a basaltic area in the northern Oceanus Procellarum (Qian et al., 2021), which is rather away from the previous nine sampling sites accomplished by NASA's Apollo missions and USSR's Lunar missions (Li et al., 2022). These samples provide us with rare opportunities to conduct experimental analysis using more precise methods in the laboratory, which has invaluable implications for deep space exploration research, compared to methods of remote detection of orbiters and in-situ investigation of lunar rovers.
3
Alamdari, Nasim, Nicholas MacKinnon, Fartash Vasefi, Reza Fazel-Rezai, Minhal Alhashim, Alireza Akhbardeh, Daniel L. Farkas, and Kouhyar Tavakolian. "Effect of Lesion Segmentation in Melanoma Diagnosis for a Mobile Health Application." In 2017 Design of Medical Devices Conference. American Society of Mechanical Engineers, 2017. http://dx.doi.org/10.1115/dmd2017-3522.
Full textAbstract:
In 2016, more than 76,380 new melanoma cases were diagnosed and 10,130 people were expected to die from skin cancer in the United States (one death per hour) [1]. A recent study demonstrates that the economic burden of skin cancer treatment is substantial and, in the United States, the cost was increased from $3.6 billion in 2002–2006 to $8.1 billion in 2007–2011 [2]. Monitoring moderate and high-risk patients and identifying melanoma in the earliest stage of disease should save lives and greatly diminish the cost of treatment. In this project, we are focused on detection and monitoring of new potential melanoma sites with medium/high risk patients. We believe those patients have a serious need and they need to be motivated to be engaged in their treatment plan. High-risk patients are more likely to be engaged with their skin health and their health care providers (physicians). Considering the high morbidity and mortality of melanoma, these patients are motivated to spend money on low-cost mobile device technology, either from their own pocket or through their health care provider if it helps reduce their risk with early detection and treatment. We believe that there is a role for mobile device imaging tools in the management of melanoma risk, if they are based on clinically validated technology that supports the existing needs of patients and the health care system. In a study issued in the British Journal of Dermatology [2] of 39 melanoma apps [2], five requested to do risk assessment, while nine mentioned images for expert review. The rest fell into the documentation and education categories. This seems like to be reliable with other dermatology apps available on the market. In a study at University of Pittsburgh [3], Ferris et al. established 4 apps with 188 clinically validated skin lesions images. From images, 60 of them were melanomas. Three of four apps tested misclassified +30% of melanomas as benign. The fourth app was more accurate and it depended on dermatologist interpretation. These results raise questions about proper use of smartphones in diagnosis and treatment of the patients and how dermatologists can effectively involve with these tools. In this study, we used a MATLAB (The MathWorks Inc., Natick, MA) based image processing algorithm that uses an RGB color dermoscopy image as an input and classifies malignant melanoma versus benign lesions based on prior training data using the AdaBoost classifier [5]. We compared the classifier accuracy when lesion boundaries are detected using supervised and unsupervised segmentation. We have found that improving the lesion boundary detection accuracy provides significant improvement on melanoma classification outcome in the patient data.
4
García Contreras, Erika, and Jorge Lira Chávez. "La percepción remota aplicada al análisis urbano-regional de la ciudad de México empleando imágenes ópticas Terra/Aster y Spot5." In International Conference Virtual City and Territory. Mexicali: Universidad Autónoma de Baja California, 2010. http://dx.doi.org/10.5821/ctv.7622.
Full textAbstract:
En la actualidad la mayor parte de la población vive en grandes urbes o megalópolis, las cuales son de gran interés para hacer estudios de ciudades empleando métodos de percepción remota. La ciudad de México es una metrópoli con una gran dinámica socio-económica, cultural y de servicios. Esta gran dinámica es una de las principales causas que ocasionan cambios en el uso de suelo urbano. En este trabajo, la investigación se centra en la detección de las estructuras urbanas de la ciudad de México, empleando imágenes ópticas Terra/Aster y Spot-5, mediante el análisis de las siguientes metodologías: a) Un modelo de textura-relieve con imágenes Terra/Aster de las bandas 3B y 3N (Lira, 2009; Cuartero et al. 2005). b) Segmentación y clasificación urbano-regional de estructuras urbanas tales como: edificios, zonas residenciales, zonas industriales, así como áreas agrícolas y áreas verdes de la ciudad de México usando operadores de texturas (Lira and Rodríguez, 2006). c) Generación de un Modelo Digital de Elevaciones empleando pares estereoscópicos del sensor SPOT-5, para la ciudad de México de fechas 2003-2006. Identificación de objetos texturales en la ciudad de México asociados a diferentes estructuras urbanas.
De lo anterior, el impacto de estudios de áreas urbanas empleando imágenes de los sensores Terra/Aster con una resolución espacial en las bandas 3B y 3N de 15m2 y Spot-5 con imágenes pancromáticas a 2.5m2 , 5m2 y 10m2 en imágenes multiespectrales, es debido a que tienen diferente resolución espacial y pueden resultar de gran interés para los urbanistas, y los arquitectos, haciendo propuestas de planeación urbano-regional y así complementar los estudios del sitio, los estudios en el cambio de uso de suelo de rural a urbano, estudios en manifestaciones de impacto ambiental, así como una segmentación precisa de las estructuras urbanas inmersas en cualquier ciudad del mundo. Nowadays most of the population lives in large cities or megalopolis, which are of great interest to perform studies of cities using remote sensing methods. Mexico City is a metropolis with a large dynamic socio-economic, cultural, and services. This great dynamics is one of the main reasons that cause changes in the use of urban land. In this work, research should focus on the detection of the urban structures in Mexico City, using optical images Terra/Aster and Spot-5, by analyzing the following methodologies: (a) A model of texture-relief Terra/Aster images of bands 3B and 3N (Lira, 2009; Cuartero et al. 2005). (b) Segmentation and urban classification of urban structures such as: buildings, residential areas, industrial areas, as well as agricultural areas and green areas of Mexico City using textures operators (Lira and Rodríguez, 2006). (c) Generation of a Digital Elevation Model using stereoscopic pairs of sensor SPOT-5, to Mexico City from 2003-2006 dates. Identification of textural objects in Mexico City associated with different urban structures. Further, the impact of urban studies using image sensors Terra/Aster with spectral bands 3B and 3N, 15m2 and Spot-5 panchromatic 2.5m2, 5m2 and 10m2 in multispectral images. This diverse resolution can be of great interest to planners, and architects, making proposals for urban planning and thus complement studies site, studies in rural land-use change to urban, manifestations of environmental impact studies as well as a precise urban structures in any city worldwide segmentation.