Tesi sul tema "Illustrations – classification"
Cita una fonte nei formati APA, MLA, Chicago, Harvard e in molti altri stili
Vedi i top-20 saggi (tesi di laurea o di dottorato) per l'attività di ricerca sul tema "Illustrations – classification".
Accanto a ogni fonte nell'elenco di riferimenti c'è un pulsante "Aggiungi alla bibliografia". Premilo e genereremo automaticamente la citazione bibliografica dell'opera scelta nello stile citazionale di cui hai bisogno: APA, MLA, Harvard, Chicago, Vancouver ecc.
Puoi anche scaricare il testo completo della pubblicazione scientifica nel formato .pdf e leggere online l'abstract (il sommario) dell'opera se è presente nei metadati.
Vedi le tesi di molte aree scientifiche e compila una bibliografia corretta.
Lefebvre, Grégoire. "Sélection et fusion de signatures visuelles parcimonieuses : application à la classification d'images naturelles". Bordeaux 2, 2007. http://www.theses.fr/2007BOR21463.
This thesis is concerned with automatic classification. The objective is to assign an identity to a test image among a set of known category. The underlying approach aim at extracting a specific set of parsimonious visual signatures, then selecting and melting discriminative information, before designing a classification scheme adapted to the context. Many methods have been proposed in order to describe visual content. One of the most effective is based on points of interest extraction and local singularity description. In the thesis, this principle is used to define next local signature and combination, based on self-organizing neural maps. A novel image information support s then proposed, being the activation of a multimodal neural model. The proposed methods focus on specific elements of one image class versus the other categories. It permits robustness to viewpoint changes, illumination variations and partial occlusions. The proposed techniques are evaluated and compared to usual methods using various international databases. These experiments show the effectiveness of the proposed approaches, in particular, in the domains of image classification, face recognition and objectionable content exclusion
Le, Saux Bertrand Honoré Henri. "Classification non exclusive et personnalisation par apprentissage : application à la navigation dans les bases d'images". Versailles-St Quentin en Yvelines, 2003. http://www.theses.fr/2003VERS0013.
Dans le cadre de la recherche d'images par le contenu, nous nous sommes intéressés aux méthodes de résumé et d'aide à la navigation pour les bases d'images. Nous avons développé une méthode de classification non-exclusive capable de catégoriser l'espace de description des images pour regrouper les images d'apparences visuelles similaires. En définissant une nouvelle fonction de Compétition Agglomérative où la compétition s'adapte à la densité des atégories, l'algorithme ARC (Adaptive Robust Competition) permet de résoudre les difficultés suivantes : * déterminer automatiquement le nombre de classes,* gérer les données bruitées diffuses,* prendre en compte les densités et les formes variables des classes. Dans un deuxième temps, nous permettons à l'utilisateur de contrôler la pertinence des classes obtenues. Un apprentissage basé sur une machine à vecteurs de support permet de personnaliser les classes d'images
Etievent, Emmanuel. "Assistance à l'indexation vidéo par analyse du mouvement". Lyon, INSA, 2002. http://theses.insa-lyon.fr/publication/2002ISAL0015/these.pdf.
Lu, Ying. "Transfer Learning for Image Classification". Thesis, Lyon, 2017. http://www.theses.fr/2017LYSEC045/document.
When learning a classification model for a new target domain with only a small amount of training samples, brute force application of machine learning algorithms generally leads to over-fitted classifiers with poor generalization skills. On the other hand, collecting a sufficient number of manually labeled training samples may prove very expensive. Transfer Learning methods aim to solve this kind of problems by transferring knowledge from related source domain which has much more data to help classification in the target domain. Depending on different assumptions about target domain and source domain, transfer learning can be further categorized into three categories: Inductive Transfer Learning, Transductive Transfer Learning (Domain Adaptation) and Unsupervised Transfer Learning. We focus on the first one which assumes that the target task and source task are different but related. More specifically, we assume that both target task and source task are classification tasks, while the target categories and source categories are different but related. We propose two different methods to approach this ITL problem. In the first work we propose a new discriminative transfer learning method, namely DTL, combining a series of hypotheses made by both the model learned with target training samples, and the additional models learned with source category samples. Specifically, we use the sparse reconstruction residual as a basic discriminant, and enhance its discriminative power by comparing two residuals from a positive and a negative dictionary. On this basis, we make use of similarities and dissimilarities by choosing both positively correlated and negatively correlated source categories to form additional dictionaries. A new Wilcoxon-Mann-Whitney statistic based cost function is proposed to choose the additional dictionaries with unbalanced training data. Also, two parallel boosting processes are applied to both the positive and negative data distributions to further improve classifier performance. On two different image classification databases, the proposed DTL consistently out performs other state-of-the-art transfer learning methods, while at the same time maintaining very efficient runtime. In the second work we combine the power of Optimal Transport and Deep Neural Networks to tackle the ITL problem. Specifically, we propose a novel method to jointly fine-tune a Deep Neural Network with source data and target data. By adding an Optimal Transport loss (OT loss) between source and target classifier predictions as a constraint on the source classifier, the proposed Joint Transfer Learning Network (JTLN) can effectively learn useful knowledge for target classification from source data. Furthermore, by using different kind of metric as cost matrix for the OT loss, JTLN can incorporate different prior knowledge about the relatedness between target categories and source categories. We carried out experiments with JTLN based on Alexnet on image classification datasets and the results verify the effectiveness of the proposed JTLN in comparison with standard consecutive fine-tuning. To the best of our knowledge, the proposed JTLN is the first work to tackle ITL with Deep Neural Networks while incorporating prior knowledge on relatedness between target and source categories. This Joint Transfer Learning with OT loss is general and can also be applied to other kind of Neural Networks
Nettl, Bruno. "Gender (and Other) Identities in Singing Style and Vocal Tone Color. Ethnomusicological Perspectices and Two Brief Illustrations". Bärenreiter Verlag, 2012. https://slub.qucosa.de/id/qucosa%3A71817.
Augereau, Olivier. "Reconnaissance et classification d’images de documents". Thesis, Bordeaux 1, 2013. http://www.theses.fr/2013BOR14764/document.
The aim of this research is to contribute to the document image classification problem. More specifically, these studies address digitizing company issues which objective is to provide the digital version of paper document with information relating to them. Given the diversity of documents, information extraction can be complex. This is why the classification and the indexing of documents are often performed manually. This research provides several solutions based on knowledge of the images that the user has. The first contribution of this thesis is a method for classifying interactively document images, where the content of documents and classes are unknown. The second contribution of this work is a new technique for document image retrieval by giving one example of researched document. This technique is based on the extraction and matching of interest points. The last contribution of this thesis is a method for classifying document images by using bags of visual words techniques
Goh, Hanlin. "Learning deep visual representations". Paris 6, 2013. http://www.theses.fr/2013PA066356.
Recent advancements in the areas of deep learning and visual information processing have presented an opportunity to unite both fields. These complementary fields combine to tackle the problem of classifying images into their semantic categories. Deep learning brings learning and representational capabilities to a visual processing model that is adapted for image classification. This thesis addresses problems that lead to the proposal of learning deep visual representations for image classification. The problem of deep learning is tackled on two fronts. The first aspect is the problem of unsupervised learning of latent representations from input data. The main focus is the integration of prior knowledge into the learning of restricted Boltzmann machines (RBM) through regularization. Regularizers are proposed to induce sparsity, selectivity and topographic organization in the coding to improve discrimination and invariance. The second direction introduces the notion of gradually transiting from unsupervised layer-wise learning to supervised deep learning. This is done through the integration of bottom-up information with top-down signals. Two novel implementations supporting this notion are explored. The first method uses top-down regularization to train a deep network of RBMs. The second method combines predictive and reconstructive loss functions to optimize a stack of encoder-decoder networks. The proposed deep learning techniques are applied to tackle the image classification problem. The bag-of-words model is adopted due to its strengths in image modeling through the use of local image descriptors and spatial pooling schemes. Deep learning with spatial aggregation is used to learn a hierarchical visual dictionary for encoding the image descriptors into mid-level representations. This method achieves leading image classification performances for object and scene images. The learned dictionaries are diverse and non-redundant. The speed of inference is also high. From this, a further optimization is performed for the subsequent pooling step. This is done by introducing a differentiable pooling parameterization and applying the error backpropagation algorithm. This thesis represents one of the first attempts to synthesize deep learning and the bag-of-words model. This union results in many challenging research problems, leaving much room for further study in this area
Blot, Michaël. "Étude de l'apprentissage et de la généralisation des réseaux profonds en classification d'images". Electronic Thesis or Diss., Sorbonne université, 2018. http://www.theses.fr/2018SORUS412.
Artificial intelligence is experiencing a resurgence in recent years. This is due to the growing ability to collect and store a considerable amount of digitized data. These huge databases allow machine learning algorithms to respond to certain tasks through supervised learning. Among the digitized data, images remain predominant in the modern environment. Huge datasets have been created. moreover, the image classification has allowed the development of previously neglected models, deep neural networks or deep learning. This family of algorithms demonstrates a great facility to learn perfectly datasets, even very large. Their ability to generalize remains largely misunderstood, but the networks of convolutions are today the undisputed state of the art. From a research and application point of view of deep learning, the demands will be more and more demanding, requiring to make an effort to bring the performances of the neuron networks to the maximum of their capacities. This is the purpose of our research, whose contributions are presented in this thesis. We first looked at the issue of training and considered accelerating it through distributed methods. We then studied the architectures in order to improve them without increasing their complexity. Finally, we particularly study the regularization of network training. We studied a regularization criterion based on information theory that we deployed in two different ways
Vuillerot, Carole. "Métrologie et évaluation fonctionnelle motrice dans les maladies neuromusculaires de l’enfance : Illustrations à partir de la Mesure de Fonction Motrice (MFM) et d’une classification en grades de sévérité d’atteinte fonctionnelle motrice (NM-Score)". Thesis, Lyon 1, 2012. http://www.theses.fr/2012LYO10081/document.
Advances in the research and treatment of childhood neuromuscular diseases have led to longer patient survivals. Evaluation is thus required not only in clinical practice for patient follow-up but also in medical research because the results of long-awaited clinical trials are beginning to emerge. A rigorous and appropriate metrology is then necessary because rough estimates or the use of improper assessment tools are no more satisfactory. We summarize here the current knowledge on the metrology applied to motor function assessment of patients with neuromuscular diseases. We propose a review of the literature on the tools available to monitor motor function with detailed analyses of their metrological properties. Developped since 1998, the Motor Function Measure presents interesting properties in terms of validity and reliability. We analyzed its sensitivity to change in different patient populations of adults and children. We then propose, the NM-Score, a classification in levels of severity of motor function decline.Validation studies have confirmed the interest of this score as well as its ease of use, validity,and reproducibility. The NM-Score is able to describe the patients precisely and discriminantly in terms of motor function for standing position and transfers, axial / proximal motor function and distal motor function. Being interested in evaluation and measurement in medicine is a sign of rigor necessary for decision-making regarding vulnerable persons with special need
Chebbi, Imen. "Modèles de stockage et d’analyse des données massives appliquées à l’imagerie satellitaire". Electronic Thesis or Diss., Paris 8, 2021. http://www.theses.fr/2021PA080106.
Our work forming part of the spatiotemporal remote sensing images, the analysis of the large volume of images is becoming more difficult with the appearance of sensors with very high spatial, spectral and temporal resolutions. In order to be able to situate our thesis in relation to the literature, we studied the main stages of the large volume data pipeline and we focused on two main contributions which are data storage and data processing. Among the objectives of our thesis is to develop a suitable architecture for our system from the perspective of storage and processing. For the implementation of this platform we developed a local master-slave cluster with several machines including one dedicated for the master node and the others for the slave nodes. The first contribution is the idea of a physical storage system that is intelligent and takes into account heterogeneous data. For this, several methods of big data storage and data representation methods based on the hadoop distributed file system (HDFS) and the benefits of Nosql allowing to store, retrieve and query massive data were investigated. We tried to adapt them to our context of satellite images based on our physical architecture and then test them with in-house satellite data collection.The second contribution of our thesis is the processing of massive satellite images after having stored them in order to classify them, where the aim is to develop an approach to classify satellite images by learning the existing truth-labels. We used deep learning techniques and more particularly the adaptation of the Unet and Vggnet algorithms based on the Apache Spark and Tensorflow platform
Goëau, Hervé. "Structuration de collections d'images par apprentissage actif crédibiliste". Phd thesis, Grenoble 1, 2009. http://www.theses.fr/2009GRE10070.
Image annotation is an essential task in professional archives exploitation. Archivsits must describe every image in order to make easier future retrieval tasks. The main difficulties are how to interpret the visual contents, how to bring together images whitch can be associated in same categories, and how to deal with the user's subjectivity. In this thesis, we use the principle of active learning in order to help a user who wants organize with accuracy image collections. From the visual content analysis, complementary active learning strategies are proposed to the user to help him to identify and put together images in relevant categories according to his oppinion. We choose to express this image classification problem with active learning by using the Transferable Belief Model (TBM), an elaboration on the Dempster-Shafer theory of evidence. The TBM allows the combination, the revision and the representation of the knowledge which can be extracted from the visual contents and the previously identified categories. Our method proposed in this theoritical framework gives a detailed modeling of the knowledge by representing explicitly cases of multi-labeling, while quantifying uncertainty (related to the semantic gap) and conflict induced by the analysis of the visual content in different modalities (colors, textures). A human-machine interface was developed in order to validate our approach on reference tests, personal images collections and professional photos from the National Audiovisual Institute. An evaluation was driven with professional users and showed very positive results in terms of utility, of usability and satisfaction
Wang, Yan. "Détection des changements à partir de photographies". Thesis, Toulouse 3, 2016. http://www.theses.fr/2016TOU30069/document.
This work deals with change detection from chronological series of photographs acquired from the ground. This context of consecutive images comparison is the one encountered in the field of integrated geography where photographic landscape observatories are widely used. These tools for analysis and decision-making consist of databases of photographic images obtained by strictly rephotographing the same scene at regular time intervals. With a large number of images, the human analysis is tedious and inaccurate. So a tool for automatically comparing pairs of landscape photographs in order to highlight changes would be a great help for exploiting photographic landscape observatories. Obviously, lighting variations, seasonality, time of day induce completely different images at the pixel level. Our goal is to design a system which would be robust to these insignificant changes and able to detect relevant changes of the scene. Numerous studies have been conducted on change detection from satellite images. But the utilization of classic digital cameras from the ground raise some specific problems like the limitation of the spectral band number and the strong variation of the depth in a same image which induces various appearance of the same object categories depending on their position in the scene. In the first part of our work, we investigate the track of automatic change detection. We propose a method lying on the registration and the over-segmentation of the images into superpixels. Then we describe each superpixel by its texture using texton histogram and its gray-level mean. A distance measure, such as Mahalanobis distance, allows to compare corresponding superpixels between two images acquired at different dates. We evaluate the performance of the proposed approach on images taken from the photographic landscape observatory produced during the construction of the French A89 highway. Among the image segmentation methods we have tested for superpixel extraction, our experiments show the relatively good behavior of Achanta segmentation method. The relevance of a change is strongly related to the intended application, we thus investigate a second track involving a user intervention. We propose an interactive change detection method based on a learning step. In order to detect changes between two images, the user designates with a selection tool some samples consisting of pixel sets in "changed" and "unchanged" areas. Each corresponding pixel pair, i.e., located at the same coordinates in the two images, is described by a 16-dimensional feature vector mainly calculated from the dissimilarity image. The latter is computed by measuring, for each corresponding pixel pair, the dissimilarity of the gray-levels of the neighbors of the two pixels. Samples selected by the user are used as learning data to train a classifier. Among the classification methods we have tried, experimental results indicate that random forests give the better results for the tested image series
Goëau, Hervé. "Structuration de collections d'images par apprentissage actif crédibiliste". Phd thesis, Université Joseph Fourier (Grenoble), 2009. http://tel.archives-ouvertes.fr/tel-00410380.
Bemme, Jens. "Illustrationen aus Dresden-Plauen". Historische Fahrräder e.V, 2020. https://slub.qucosa.de/id/qucosa%3A70920.
Peña, Plaza Carlos. "L'image dans l'image : rhétorique visuelle d'une culture mondialisée : essai d'atlas des représentations ibéro-américaines, XVIe -XVIIIe siècles". Paris, EHESS, 2014. http://www.theses.fr/2014EHES0025.
Through the study of a collection of images from the ibero-american world the thesis develops a typological and morphological study of the visual rhetoric of one of the first globalized cultures. The task consists of an articulation between the micro-historical and the macro-historical analysis, that allows to enlighten the connections between global and local, anc observe the commemorative function of those représentations of the colonial past. The approach is semiotic and iconological , but it is also anthropological. It tries to portray the diverse modalities of transformation of the images and their visual cross-breeding or hybridization in their passage from one continent to the other. The categorization and indexatioi with keywords allowed to identify certain visual framing devices of an image within the image and a séries of metaphors and symbols associated with the Eucharistie ritual. The Atlas configuration ,was the instrument used for the visualization of the results according to the basic structural oppositions identified during the process of classification
Döring, Thomas Thibault, e Thomas Fuchs. "Bildwechsel: Buchillustration in der Reformationszeit: Katalog zur gleichnamigen Ausstellung in der Bibliotheca Albertina vom 10. März bis 9. Juli 2017". Universitätsverlag, 2017. https://ul.qucosa.de/id/qucosa%3A72251.
Kluge, Tino. "Illustration of stochastic processes and the finite difference method in finance". Universitätsbibliothek Chemnitz, 2003. http://nbn-resolving.de/urn:nbn:de:bsz:ch1-200300079.
Der Vortrag zeigt Animationen von Realisierungen stochstischer Prozesse, die zur Modellierung von Groessen im Finanzbereich haeufig verwendet werden (z.B. Wechselkurse, Zinskurse, Aktienkurse). Im zweiten Teil wird die Loesung der Black-Scholes Partiellen Differentialgleichung mittels Finitem Differenzenverfahren graphisch veranschaulicht
Fuchs, Thomas, e Ulrich Johannes Schneider. "Ausstellung Bildwechsel. Buchillustration in der Reformationszeit". SLUB Dresden, 2017. https://slub.qucosa.de/id/qucosa%3A7948.
Morard, Marie-Doriane. "De la fonction à la participation : illustration par le développement et la validation de trois outils de mesure en médecine physique et de réadaptation". Thesis, Lyon, 2020. http://www.theses.fr/2020LYSES022.
Physical and Rehabilitation Medicine (PRM) has been developed around a holistic approach of the individual and the multiple consequences of impairments and disabilities resulting from a health problem. Determining these consequences requires the use of assessment, which is a concept widely used in medicine in clinical practice, therapy, research, and which is based on the use of measuring tools. The PRM vision was built on the International Classification of Functioning, Disability and Health (ICF) which is a biopsychosocial framework for the description of the health state, which can thus be used to define of the measured. The close links between PRM and ICF led us to question the different ways of developing assessment tools adapted to each of the dimensions of the ICF: function, activity and participation. We have therefore through various health states, explored these three dimensions in clinical practice using valid methods in metrology, via three measurement tools: (1) neurological function in French-speaking children with a neonatal stroke, (2) a score of physical and cognitive activity in patients hospitalized in follow-up care and rehabilitation, (3) participation of children with neuromuscular disease. The results and their interpretation stemming from this work, clearly place participation as the main criterion for actions in PRM while highlighting the importance of mastering the limits of measurement tools before taking into account their advantages
Bürger, Thomas. "Die respektlose Muse". Saechsische Landesbibliothek- Staats- und Universitaetsbibliothek Dresden, 2015. http://nbn-resolving.de/urn:nbn:de:bsz:14-qucosa-188519.