No description available.

Architectural floor plans are scale-accurate 2D drawings of one level of a building, seen from above, which convey structural and semantic information related to rooms, walls, symbols, textual data, etc. They consist of lines, curves, symbols, and textual markings, showing the relationships between rooms and all physical features, required for the proper construction or renovation of the building. First, this thesis provides a thorough study of state-of-the-art on symbol spotting methods for architectural drawings, an application domain providing the document image analysis and graphic recognition communities with an interesting set of challenges linked to the sheer complexity and density of embedded information, that have yet to be resolved. Second, we propose a hybrid method that capitalizes on strengths of both vector-based and pixel-based symbol spotting techniques. In the description phase, the salient geometric constituents of a symbol are extracted by a variety of vectorization techniques, including a proposed voting-based algorithm for finding partial ellipses. This enables us to better handle local shape irregularities and boundary discontinuities, as well as partial occlusion and overlap. In the matching phase, the spatial relationship between the geometric primitives is encoded via a primitive-aware proximity graph. A statistical approach is then used to rapidly yield a coarse localization of symbols within the plan. Localization is further refined with a pixel-based step implementing a modified cross-correlation function. Experimental results on the public SESYD synthetic dataset and real-world images demonstrate that our approach clearly outperforms other popular symbol spotting approaches. Traditional on-the-fly symbol spotting methods are unable to address the semantic challenge of graphical notation variability, i.e. low intra-class symbol similarity, an issue that is particularly important in architectural floor plan analysis. The presence of occlusion and clutter, characteristic of real-world plans, along with a varying graphical symbol complexity from almost trivial to highly complex, also pose challenges to existing spotting methods. Third, we address all the above issues by leveraging recent advances in deep learning-based neural networks and adapting an object detection framework based on the YOLO (You Only Look Once) architecture. We propose a training strategy based on tiles, avoiding many issues particular to deep learning-based object detection networks related to the relatively small size of symbols compared to entire floor plans, aspect ratios, and data augmentation. Experimental results demonstrate that our method successfully detects architectural symbols with low intra-class similarity and of variable graphical complexity, even in the presence of heavy occlusion and clutter. / Graduate

Dans cette thèse, nous nous concentrons sur comment les représentations parcimonieuses peuvent aider à augmenter les performances pour réduire le bruit, extraire des régions de texte, reconnaissance des formes et localiser des symboles dans des documents graphiques. Pour ce faire, tout d'abord, nous donnons une synthèse des représentations parcimonieuses et ses applications en traitement d'images. Ensuite, nous présentons notre motivation pour l'utilisation de dictionnaires d'apprentissage avec des algorithmes efficaces pour les construire. Après avoir décrit l'idée générale des représentations parcimonieuses et du dictionnaire d'apprentissage, nous présentons nos contributions dans le domaine de la reconnaissance de symboles et du traitement des documents en les comparants aux travaux de l'état de l'art. Ces contributions s'emploient à répondre aux questions suivantes: La première question est comment nous pouvons supprimer le bruit des images où il n'existe aucune hypothèse sur le modèle de bruit sous-jacent à ces images ? La deuxième question est comment les représentations parcimonieuses sur le dictionnaire d'apprentissage peuvent être adaptées pour séparer le texte du graphique dans des documents? La troisième question est comment nous pouvons appliquer la représentation parcimonieuse à reconnaissance de symboles? Nous complétons cette thèse en proposant une approche de localisation de symboles dans les documents graphiques qui utilise les représentations parcimonieuses pour coder un vocabulaire visuel / In this thesis, we focus on how sparse representations can help to increase the performance of noise removal, text region extraction, pattern recognition and spotting symbols in graphical documents. To do that, first of all, we give a survey of sparse representations and its applications in image processing. Then, we present the motivation of building learning dictionary and efficient algorithms for constructing a learning dictionary. After describing the general idea of sparse representations and learned dictionary, we bring some contributions in the field of symbol recognition and document processing that achieve better performances compared to the state-of-the-art. These contributions begin by finding the answers to the following questions. The first question is how we can remove the noise of a document when we have no assumptions about the model of noise found in these images? The second question is how sparse representations over learned dictionary can separate the text/graphic parts in the graphical document? The third question is how we can apply the sparse representation for symbol recognition? We complete this thesis by proposing an approach of spotting symbols that use sparse representations for the coding of a visual vocabulary