Dissertations / Theses on the topic 'Contextual features'

Tonal, textural and contextual properties are used in manual photointerpretation of remotely sensed data. This study has used these three attributes to produce a lithological map of semi arid northwest Argentina by semi automatic computer classification procedures of remotely sensed data. Three different types of satellite data were investigated, these were LANDSAT MSS, TM and SIR-A imagery. Supervised classification procedures using tonal features only produced poor classification results. LANDSAT MSS produced classification accuracies in the range of 40 to 60%, while accuracies of 50 to 70% were achieved using LANDSAT TM data. The addition of SIR-A data produced increases in the classification accuracy. The increased classification accuracy of TM over the MSS is because of the better discrimination of geological materials afforded by the middle infra red bands of the TM sensor. The maximum likelihood classifier consistently produced classification accuracies 10 to 15% higher than either the minimum distance to means or decision tree classifier, this improved accuracy was obtained at the cost of greatly increased processing time. A new type of classifier the spectral shape classifier, which is computationally as fast as a minimum distance to means classifier is described. However, the results for this classifier were disappointing, being lower in most cases than the minimum distance or decision tree procedures. The classification results using only tonal features were felt to be unacceptably poor, therefore textural attributes were investigated. Texture is an important attribute used by photogeologists to discriminate lithology. In the case of TM data, texture measures were found to increase the classification accuracy by up to 15%. However, in the case of the LANDSAT MSS data the use of texture measures did not provide any significant increase in the accuracy of classification. For TM data, it was found that second order texture, especially the SGLDM based measures, produced highest classification accuracy. Contextual post processing was found to increase classification accuracy and improve the visual appearance of classified output by removing isolated misclassified pixels which tend to clutter classified images. Simple contextual features, such as mode filters were found to out perform more complex features such as gravitational filter or minimal area replacement methods. Generally the larger the size of the filter, the greater the increase in the accuracy. Production rules were used to build a knowledge based system which used tonal and textural features to identify sedimentary lithologies in each of the two test sites. The knowledge based system was able to identify six out of ten lithologies correctly.

Building Information Modeling (BIM) is becoming imperative across building disciplines to improve communication and workflow from the first blueprint. Maintenance and facility management is however lagging behind in adoption and research of BIM. Utilizing research-through-design, this study explores BIM-enabled facility management and the critical practice of decision-making at the Celsius building in Uppsala. Contextual design and inquiry were applied to identify and suggest important design features that support decisions related to the task of establishing maximum room occupation. Results show that facility managers can make use of fuzzy multicriteria decision-making and expert heuristics to independently reach conclusions. Important design features were found to heavily rely on the existing building models, where context-view filtered to room capacity data in the existing BIM-system effectively supported the users’ assessment of data. The filtered, aggregated information presented in a simplified mobile format was insufficient for decision-making, suggesting that the building model was more important than initially perceived.

The Five-Factor (FFM) and job characteristics models provide parsimonious frameworks to explain personal and situational influences on work behavior. However, the two are seldom studied in concert, despite theory and empirical evidence indicating that personality traits are more valid under some job conditions than others. The purpose of my dissertation is to address the lack of systematic knowledge regarding the joint influences of personality and job characteristics by testing and extending the major propositions of the theory of purposeful work behavior (TPWB; Barrick, Mount &Li, 2013). Because the TPWB focuses only on task and social characteristics of jobs, I propose a theoretical extension to the theory whereby I examine the way traits interact with contextual characteristics (e.g., physical demands, working conditions) of jobs to influence work outcomes. Further, I extend the TPWB by examining the occupational values from the theory of work adjustment (Dawis &Lofquist, 1975), which are broader and situated at a higher taxonomic level than jobs, moderate the FFM-criterion correlations. Using a meta-analytic design, I tested the extent to which job characteristics and occupational values moderate the relationships between the FFM and job performance, contextual performance, and job satisfaction. The overall results were mixed, with some findings indicating that personality trait validities are substantially higher under conditions of congruent job characteristics, and others indicating no such moderating effects, or moderating effects in contrast to what I proposed in my hypotheses. The mixed results may be due to gravitational processes that take place when individuals select jobs. I also examined the relative importance of the job characteristics and occupational values frameworks, and found that job characteristics were more important moderators of the FFM traits than occupational values across almost all trait-criterion combinations. I discuss significant implications and limitations, along with directions for future research along the lines of furthering the study of the joint influences of person and situation on work outcomes.

Comparative research on event memory has typically focused on the binding of spatial and temporal information in memory, but much less is known about how animals remember information about the source of their memories (i.e., whether the event is something they performed themselves or whether they observed it). The purpose of the present study was to examine how rhesus monkeys (n = 8) and 3- to 4- year-old children (n = 20) remember this information along with other relevant event features (object identity, spatial location, temporal properties and contextual features) in working memory. In Experiment 1, rhesus monkeys completed five different delayed matching-to-sample tasks to assess independent encoding of these five event components. In Experiment 2, the monkeys either performed or observed an event and then had to respond to a randomly selected pair of memory tests used in the previous experiment. In Experiment 3, children were presented with the same memory task, but were given a brief demonstration to learn how to perform the task. Both children and monkeys responded to these tests using photos and shapes (for the identity and spatial tests) and icons (for the temporal, agency and context tests). The monkeys demonstrated significantly above-chance performance on the identity, spatial, temporal and agency tasks. The children were above chance on the one component the monkeys had difficulty with (context), but conversely demonstrated difficulty on the temporal memory test. There was evidence of feature integration in both monkeys and children. Specifically, the children were significantly more likely to respond correctly to the second memory test if they had also been correct on the first memory test. Two of five rhesus monkeys also showed this effect, indicating that for these individuals, the features were integrated in working memory. Implications of this research are discussed in relation to self-awareness and episodic memory research in children and nonhuman species.

Studies in Genre Analysis have been developed with the aim of exploring the typification of genres of the work environment and interpreting their funtions according to the discursive communities in which they operate. Some examples are studies carried out by Bazerman (2005) and Devitt (1991) on documents from professional contexts. In that regard, Bazerman (2005) discusses notions such as genre, genre sets, genre systems and activity systems. Language practices in professional contexts have also been the object of investigations among Brazilian research teams, for instance LAEL at PUC/SP and PUC/RJ, in efforts to understand how the participants of a communicative event interact and how their lexicogrammatical choices construe meaning. In that sense, the present study approaches the system of genres adopted in the selective process for hiring a salesperson, conducted by a cooperative company in the state of Rio Grande do Sul. This system of genres comprises several texts: Want Ad, Presentation Letter, Curriculum Vitae and Interview. The objective of this study is to investigate the system of genres for job application from the perspective of language as social practice with a focus on practices circumsbribed to the work sphere. This way, the struture of the texts within this system of genres is analyzed using the framework of Systemic-Functional Linguistics (Halliday, 1994; 2004 and Halliday & Hasan, 1989). The texts are analyzed in their organizational patterns and clauses are classified considering the type of processes, according to the System of Transitivity. Besides, the communicative purposes as welll as the characterization of the participants in the activities system are identified. Contrary to initial expectations, the interview was pointed out in the results as the most relevant genre in evaluating the applicants. Overall, the results offer an understanding of the interaction as characterized by specific aims in a particular professional sphere and can be valid for language educators, mainly those who work with Portuguese as mother tongue for instrumental purposes with a focus on professional genres.<br>Estudos em Análise de Gênero têm sido desenvolvidos a fim de explorar a tipificação de gêneros do contexto do trabalho e interpretar suas funções de acordo com as comunidades discursivas em que operam. Alguns exemplos são os estudos desenvolvidos por Bazerman (2005) e Devitt (1991) sobre documentos de contextos profissionais. Em vista disso, Bazerman (2005) discute noções sobre gênero, conjunto de gêneros, sistema de gêneros e sistema de atividades. A linguagem voltada a contextos profissionais também tem sido objeto de análise para grupos de pesquisa brasileiros, por exemplo, o do LAEL da PUC/SP e o da PUC/RJ, no sentido de compreender como os participantes de um evento comunicativo interagem e como suas escolhas léxico-gramaticais constroem significado. Assim, o tema do presente estudo diz respeito ao sistema de gêneros de um processo seletivo para contratação de vendedor autônomo, realizado em uma empresa cooperativa do interior do Rio Grande do Sul. Esse sistema de gêneros acomoda vários textos: Anúncio de Emprego, Carta de Apresentação, Curriculum Vitae e Entrevista Pessoal. O objetivo deste estudo é investigar o sistema de gêneros da seleção a emprego a partir da perspectiva de linguagem como prática social, com ênfase nas práticas relacionadas às esferas do trabalho. Desse modo, a estrutura dos exemplares desse sistema de gêneros é descrita a partir de propostas da Lingüística Sistêmico-Funcional (Halliday, 1994; 2004 e Halliday e Hasan, 1989). São identificados os padrões de organização dos textos e classificados os processos das orações, conforme o Sistema de Transitividade. E, são identificados os propósitos comunicativos e o perfil dos participantes desse sistema de atividades. Na avaliação dos candidatos, contrariando a expectativa inicial, os resultados destacam a relevância maior para a Entrevista Pessoal. Enfim, a discussão aponta à compreensão de como se dá a interação, caracterizada por propósitos específicos em uma situação profissional e pode ser válida para os profissionais da linguagem, principalmente, àqueles que trabalham com o ensino instrumental da língua materna, voltado aos gêneros do contexto empresarial.

Le traitement d’images est un axe de recherche très actif depuis des années. L’interprétation des images constitue une de ses branches les plus importantes de par ses applications socio-économiques et scientifiques. Cependant cette interprétation, comme la plupart des processus de traitements d’images, nécessite une phase de segmentation pour délimiter les régions à analyser. En fait l’interprétation est un traitement qui permet de donner un sens aux régions détectées par la phase de segmentation. Ainsi, la phase d’interprétation ne pourra analyser que les régions détectées lors de la segmentation. Bien que l’objectif de l’interprétation automatique soit d’avoir le même résultat qu’une interprétation humaine, la logique des techniques classiques de ce domaine ne marie pas celle de l’interprétation humaine. La majorité des approches classiques d’interprétation d’images séparent la phase de segmentation et celle de l’interprétation. Les images sont d’abord segmentées puis les régions détectées sont interprétées. En plus, au niveau de la segmentation les techniques classiques parcourent les images de manière séquentielle, dans l’ordre de stockage des pixels. Ce parcours ne reflète pas nécessairement le parcours de l’expert humain lors de son exploration de l’image. En effet ce dernier commence le plus souvent par balayer l’image à la recherche d’éventuelles zones d’intérêts. Dans le cas échéant, il analyse les zones potentielles sous trois niveaux de vue pour essayer de reconnaitre de quel objet s’agit-il. Premièrement, il analyse la zone en se basant sur ses caractéristiques physiques. Ensuite il considère les zones avoisinantes de celle-ci et enfin il zoome sur toute l’image afin d’avoir une vue complète tout en considérant les informations locales à la zone et celles de ses voisines. Pendant son exploration, l’expert, en plus des informations directement obtenues sur les caractéristiques physiques de l’image, fait appel à plusieurs sources d’informations qu’il fusionne pour interpréter l’image. Ces sources peuvent inclure les connaissent acquises grâce à son expérience professionnelle, les contraintes existantes entre les objets de ce type d’images, etc. L’idée de l’approche présentée ici est que simuler l’activité visuelle de l’expert permettrait une meilleure compatibilité entre les résultats de l’interprétation et ceux de l’expert. Ainsi nous retenons de cette analyse trois aspects importants du processus d’interprétation d’image que nous allons modéliser dans l’approche proposée dans ce travail : 1. Le processus de segmentation n’est pas nécessairement séquentiel comme la plus part des techniques de segmentations qu’on rencontre, mais plutôt une suite de décisions pouvant remettre en cause leurs prédécesseurs. L’essentiel étant à la fin d’avoir la meilleure classification des régions. L’interprétation ne doit pas être limitée par la segmentation. 2. Le processus de caractérisation d’une zone d’intérêt n’est pas strictement monotone i.e. que l’expert peut aller d’une vue centrée sur la zone à vue plus large incluant ses voisines pour ensuite retourner vers la vue contenant uniquement la zone et vice-versa. 3. Lors de la décision plusieurs sources d’informations sont sollicitées et fusionnées pour une meilleure certitude. La modélisation proposée de ces trois niveaux met particulièrement l’accent sur les connaissances utilisées et le raisonnement qui mène à la segmentation des images<br>Image processing has been a very active area of research for years. The interpretation of images is one of its most important branches because of its socio-economic and scientific applications. However, the interpretation, like most image processing processes, requires a segmentation phase to delimit the regions to be analyzed. In fact, interpretation is a process that gives meaning to the regions detected by the segmentation phase. Thus, the interpretation phase can only analyze the regions detected during the segmentation. Although the ultimate objective of automatic interpretation is to produce the same result as a human, the logic of classical techniques in this field does not marry that of human interpretation. Most conventional approaches to this task separate the segmentation phase from the interpretation phase. The images are first segmented and then the detected regions are interpreted. In addition, conventional techniques of segmentation scan images sequentially, in the order of pixels appearance. This way does not necessarily reflect the way of the expert during the image exploration. Indeed, a human usually starts by scanning the image for possible region of interest. When he finds a potential area, he analyzes it under three view points trying to recognize what object it is. First, he analyzes the area based on its physical characteristics. Then he considers the region's surrounding areas and finally he zooms in on the whole image in order to have a wider view while considering the information local to the region and those of its neighbors. In addition to information directly gathered from the physical characteristics of the image, the expert uses several sources of information that he merges to interpret the image. These sources include knowledge acquired through professional experience, existing constraints between objects from the images, and so on.The idea of the proposed approach, in this manuscript, is that simulating the visual activity of the expert would allow a better compatibility between the results of the interpretation and those ofthe expert. We retain from the analysis of the expert's behavior three important aspects of the image interpretation process that we will model in this work: 1. Unlike what most of the segmentation techniques suggest, the segmentation process is not necessarily sequential, but rather a series of decisions that each one may question the results of its predecessors. The main objective is to produce the best possible regions classification. 2. The process of characterizing an area of interest is not a one way process i.e. the expert can go from a local view restricted to the region of interest to a wider view of the area, including its neighbors and vice versa. 3. Several information sources are gathered and merged for a better certainty, during the decision of region characterisation. The proposed model of these three levels places particular emphasis on the knowledge used and the reasoning behind image segmentation

L’exploitation de données radiographiques, en particulier pour la reconstruction 3D du rachis de patients scoliotiques, est un prérequis à la modélisation personnalisée. Les méthodes actuelles, bien qu’assez robustes pour la routine clinique, reposent sur des ajustements manuels fastidieux. Dans ce contexte, ce travail de thèse vise à la détection automatisée de points anatomiques spécifiques des vertèbres, permettant ainsi des ajustements automatisés. Nous avons développé premièrement une méthode originale de localisation de coins de vertèbres cervicales et lombaires sur les radiographies sagittales. L’évaluation rigoureuse de cette méthode suggère sa robustesse et sa précision. Nous avons ensuite développé un algorithme pour le problème pertinent cliniquement de localisation des pédicules sur les radiographies coronales. Cet algorithme se compare favorablement aux méthodes similaires dans la littérature, qui nécessitent une saisie manuelle. Enfin, nous avons soulevé les problèmes, relativement peu étudiés, de détection, identification et segmentation des apophyses épineuses du rachis cervical dans les radiographies sagittales. Toutes les tâches mentionnées ont été réalisées grâce à une combinaison originale de descripteurs visuels et une classification multi-classe par Random Forest, menant à une nouvelle et puissante approche de localisation et de segmentation. Les méthodes proposées dans cette thèse suggèrent un grand potentiel pour être intégré à la reconstruction 3D du rachis, utilisée quotidiennement en routine clinique<br>Exploitation of spine radiographs, in particular for 3D spine shape reconstruction of scoliotic patients, is a prerequisite for personalized modelling. Current methods, even though robust enough to be used in clinical routine, still rely on tedious manual adjustments. In this context, this PhD thesis aims toward automated detection of specific vertebrae landmarks in spine radiographs, enabling automated adjustments. In the first part, we developed an original Random Forest based framework for vertebrae corner localization that was applied on sagittal radiographs of both cervical and lumbar spine regions. A rigorous evaluation of the method confirms robustness and high accuracy of the proposed method. In the second part, we developed an algorithm for the clinically-important task of pedicle localization in the thoracolumbar region on frontal radiographs. The proposed algorithm compares favourably to similar methods from the literature while relying on less manual supervision. The last part of this PhD tackled the scarcely-studied task of joint detection, identification and segmentation of spinous processes of cervical vertebrae in sagittal radiographs, with again high precision performance. All three algorithmic solutions were designed around a generic framework exploiting dedicated visual feature descriptors and multi-class Random Forest classifiers, proposing a novel solution with computational and manual supervision burdens aiming for translation into clinical use. Overall, the presented frameworks suggest a great potential of being integrated in current spine 3D reconstruction frameworks that are used in daily clinical routine

Recommender systems are an advanced form of software applications, more specifically decision-support systems, that efficiently assist the users in finding items of their interest. Recommender systems have been applied to many domains from music to e-commerce, movies to software services delivery and tourism to news by exploiting available information to predict and provide recommendations to end user. The suggestions generated by recommender systems tend to narrow down the list of items which a user may overlook due to the huge variety of similar items or users’ lack of experience in the particular domain of interest. While the performance of traditional recommender systems, which rely on relatively simpler information such as content and users’ filters, is widely accepted, their predictive capability perfomrs poorly when local context of the user and situated actions have significant role in the final decision. Therefore, acceptance and incorporation of context of the user as a significant feature and development of recommender systems utilising the premise becomes an active area of research requiring further investigation of the underlying algorithms and methodology. This thesis focuses on categorisation of contextual and non-contextual features within the domain of context-aware recommender system and their respective evaluation. Further, application of the Multilayer Perceptron Model (MLP) for generating predictions and ratings from the contextual and non-contextual features for contextual recommendations is presented with support from relevant literature and empirical evaluation. An evaluation of specifically employing artificial neural networks (ANNs) in the proposed methodology is also presented. The work emphasizes on both algorithms and methodology with three points of consideration: contextual features and ratings of particular items/movies are exploited in several representations to improve the accuracy of recommendation process using artificial neural networks (ANNs), context features are combined with user-features to further improve the accuracy of a context-aware recommender system and lastly, a combination of the item/movie features are investigated within the recommendation process. The proposed approach is evaluated on the LDOS-CoMoDa dataset and the results are compared with state-of-the-art approaches from relevant published literature.

Previous evidence has shown that older adults may have specific declines in prefrontal cortex (PFC)-mediated processes supported source memory retrieval, such as strategic retrieval and post-retrieval monitoring. This decline may manifest in the form of attenuated late-frontal ERP effects. Behavioral research suggests that explicitly integrating a target context, or source, with a stimulus during encoding will improve subsequent source memory performance for both younger and older adults. Explicit item-feature binding instructions during encoding may alleviate source memory impairments, in part, by reducing the need for strategic processing during episodic retrieval. The present ERP study investigated whether explicit direction of attention toward item-feature integration may reduce age-related deficits in source memory by alleviating the necessity of frontally-mediated strategic processing at retrieval. Results demonstrated that explicit direction of attention improved source memory accuracy for both young and older adults, but older adults benefited less than the young, indicating additional age-related deficits. ERPs revealed that explicit encoding support attenuated post-retrieval monitoring effects in the young. In the old, explicit encoding instruction resulted in earlier onset of early frontal effects, possibly related to familiarity. Results suggest explicit direction of attention toward item-source integration at encoding may improve source memory by alleviating the need for strategic retrieval, but age-related deficits persist.

abstract: Bridging semantic gap is one of the fundamental problems in multimedia computing and pattern recognition. The challenge of associating low-level signal with their high-level semantic interpretation is mainly due to the fact that semantics are often conveyed implicitly in a context, relying on interactions among multiple levels of concepts or low-level data entities. Also, additional domain knowledge may often be indispensable for uncovering the underlying semantics, but in most cases such domain knowledge is not readily available from the acquired media streams. Thus, making use of various types of contextual information and leveraging corresponding domain knowledge are vital for effectively associating high-level semantics with low-level signals with higher accuracies in multimedia computing problems. In this work, novel computational methods are explored and developed for incorporating contextual information/domain knowledge in different forms for multimedia computing and pattern recognition problems. Specifically, a novel Bayesian approach with statistical-sampling-based inference is proposed for incorporating a special type of domain knowledge, spatial prior for the underlying shapes; cross-modality correlations via Kernel Canonical Correlation Analysis is explored and the learnt space is then used for associating multimedia contents in different forms; model contextual information as a graph is leveraged for regulating interactions among high-level semantic concepts (e.g., category labels), low-level input signal (e.g., spatial/temporal structure). Four real-world applications, including visual-to-tactile face conversion, photo tag recommendation, wild web video classification and unconstrained consumer video summarization, are selected to demonstrate the effectiveness of the approaches. These applications range from classic research challenges to emerging tasks in multimedia computing. Results from experiments on large-scale real-world data with comparisons to other state-of-the-art methods and subjective evaluations with end users confirmed that the developed approaches exhibit salient advantages, suggesting that they are promising for leveraging contextual information/domain knowledge for a wide range of multimedia computing and pattern recognition problems.<br>Dissertation/Thesis<br>Ph.D. Computer Science 2011

Le traitement d’images est un axe de recherche très actif depuis des années. L’interprétation des images constitue une de ses branches les plus importantes de par ses applications socio-économiques et scientifiques. Cependant cette interprétation, comme la plupart des processus de traitements d’images, nécessite une phase de segmentation pour délimiter les régions à analyser. En fait l’interprétation est un traitement qui permet de donner un sens aux régions détectées par la phase de segmentation. Ainsi, la phase d’interprétation ne pourra analyser que les régions détectées lors de la segmentation. Bien que l’objectif de l’interprétation automatique soit d’avoir le même résultat qu’une interprétation humaine, la logique des techniques classiques de ce domaine ne marie pas celle de l’interprétation humaine. La majorité des approches classiques d’interprétation d’images séparent la phase de segmentation et celle de l’interprétation. Les images sont d’abord segmentées puis les régions détectées sont interprétées. En plus, au niveau de la segmentation les techniques classiques parcourent les images de manière séquentielle, dans l’ordre de stockage des pixels. Ce parcours ne reflète pas nécessairement le parcours de l’expert humain lors de son exploration de l’image. En effet ce dernier commence le plus souvent par balayer l’image à la recherche d’éventuelles zones d’intérêts. Dans le cas échéant, il analyse les zones potentielles sous trois niveaux de vue pour essayer de reconnaitre de quel objet s’agit-il. Premièrement, il analyse la zone en se basant sur ses caractéristiques physiques. Ensuite il considère les zones avoisinantes de celle-ci et enfin il zoome sur toute l’image afin d’avoir une vue complète tout en considérant les informations locales à la zone et celles de ses voisines. Pendant son exploration, l’expert, en plus des informations directement obtenues sur les caractéristiques physiques de l’image, fait appel à plusieurs sources d’informations qu’il fusionne pour interpréter l’image. Ces sources peuvent inclure les connaissent acquises grâce à son expérience professionnelle, les contraintes existantes entre les objets de ce type d’images, etc. L’idée de l’approche présentée ici est que simuler l’activité visuelle de l’expert permettrait une meilleure compatibilité entre les résultats de l’interprétation et ceux de l’expert. Ainsi nous retenons de cette analyse trois aspects importants du processus d’interprétation d’image que nous allons modéliser dans l’approche proposée dans ce travail : 1. Le processus de segmentation n’est pas nécessairement séquentiel comme la plus part des techniques de segmentations qu’on rencontre, mais plutôt une suite de décisions pouvant remettre en cause leurs prédécesseurs. L’essentiel étant à la fin d’avoir la meilleure classification des régions. L’interprétation ne doit pas être limitée par la segmentation. 2. Le processus de caractérisation d’une zone d’intérêt n’est pas strictement monotone i.e. que l’expert peut aller d’une vue centrée sur la zone à vue plus large incluant ses voisines pour ensuite retourner vers la vue contenant uniquement la zone et vice-versa. 3. Lors de la décision plusieurs sources d’informations sont sollicitées et fusionnées pour une meilleure certitude. La modélisation proposée de ces trois niveaux met particulièrement l’accent sur les connaissances utilisées et le raisonnement qui mène à la segmentation des images<br>Image processing has been a very active area of research for years. The interpretation of images is one of its most important branches because of its socio-economic and scientific applications. However, the interpretation, like most image processing processes, requires a segmentation phase to delimit the regions to be analyzed. In fact, interpretation is a process that gives meaning to the regions detected by the segmentation phase. Thus, the interpretation phase can only analyze the regions detected during the segmentation. Although the ultimate objective of automatic interpretation is to produce the same result as a human, the logic of classical techniques in this field does not marry that of human interpretation. Most conventional approaches to this task separate the segmentation phase from the interpretation phase. The images are first segmented and then the detected regions are interpreted. In addition, conventional techniques of segmentation scan images sequentially, in the order of pixels appearance. This way does not necessarily reflect the way of the expert during the image exploration. Indeed, a human usually starts by scanning the image for possible region of interest. When he finds a potential area, he analyzes it under three view points trying to recognize what object it is. First, he analyzes the area based on its physical characteristics. Then he considers the region's surrounding areas and finally he zooms in on the whole image in order to have a wider view while considering the information local to the region and those of its neighbors. In addition to information directly gathered from the physical characteristics of the image, the expert uses several sources of information that he merges to interpret the image. These sources include knowledge acquired through professional experience, existing constraints between objects from the images, and so on.The idea of the proposed approach, in this manuscript, is that simulating the visual activity of the expert would allow a better compatibility between the results of the interpretation and those ofthe expert. We retain from the analysis of the expert's behavior three important aspects of the image interpretation process that we will model in this work: 1. Unlike what most of the segmentation techniques suggest, the segmentation process is not necessarily sequential, but rather a series of decisions that each one may question the results of its predecessors. The main objective is to produce the best possible regions classification. 2. The process of characterizing an area of interest is not a one way process i.e. the expert can go from a local view restricted to the region of interest to a wider view of the area, including its neighbors and vice versa. 3. Several information sources are gathered and merged for a better certainty, during the decision of region characterisation. The proposed model of these three levels places particular emphasis on the knowledge used and the reasoning behind image segmentation

碩士<br>國立成功大學<br>資訊工程學系碩博士班<br>94<br>To identify landslides for disaster monitoring, FORMOSAT-2 imagery has the advantages of low cost and frequent revisit over any other satellite imagery currently available in Taiwan. However, the images with four spectral bands are not capable enough to distinguish landslides from other ground cover types, such as small river channels. This study proposes to overcome the problem of spectral incapability using the following techniques. First, we explore more discriminative features, such as texture and topographical features, in order to improve class separability. Texture features are extracted from the FORMOSAT-2 imagery itself using the log-polar wavelet packet transformation. A topographical feature ‘slope’ is derived from an auxiliary Digital Elevation Model (DEM) dataset. Second, we employ a contextual classifier because combining spectral and spatial information is helpful for homogeneous object identification. Field investigation has been conducted on several sites to validate the result of analysis. Experiments show the feasibility of our approach to landslide identification based on multispectral imagery.