Le processus de sélection de photos dans des albums peut être considérablement amélioré à l’aide d’un critère d’évaluation automatique des qualités d’une photo. Cependant, les méthodes existantes abordent ce problème de manière indépendante, c’est à dire en évaluant chaque image séparément des autres images d'un album. Dans cette thèse, nous explorons la modélisation du contexte d’une photo via une approche de clustering de collections de photos et la possibilité d'appliquer l’information de contexte à l'évaluation d’une photo. Nous avons effectué des études subjectives permettant d’étudier la manière dont les utilisateurs regroupent et sélectionnent des photos dans un album. Ces études ont permis une estimation du niveau de l’accord entre les différents utilisateurs. Nous avons aussi étudié la manière dont le contexte influence leurs décisions. Après avoir étudié la nature des décisions des utilisateurs, nous proposons une approche informatique pour modéliser leur comportement. Tout d'abord, nous introduisons une méthode de clustering hiérarchique, qui permet de regrouper des photos similaires selon une structure de similarité à plusieurs niveaux, basée sur des descripteurs visuels. Ensuite, les informations de contexte de la photo sont utilisées pour adapter le score de la photo pré-calculé indépendamment, en utilisant les données basées sur des statistiques et une approche d'apprentissage automatique. De plus, comme la majorité des méthodes récentes d'évaluation de la photo sont basées sur des réseaux de neurones convolutionnels, nous avons exploré et visualisé les caractéristiques esthétiques apprises par ces méthodes. / An automatic photo assessment can significantly aid the process of photo selection within photo collections. However, existing computational methods approach this problem in an independent manner, by evaluating each image apart from other images in a photo album. In this thesis, we explore the modeling of photo context via a clustering approach for photo collections and the possibility of applying such context information in photo assessment. To better understand user actions within photo albums, we conduct experimental user studies, where we study how users cluster and select photos in photo collections. We estimate the level of agreement between users and investigate how the context, defined by similar photos in corresponding clusters, influences their decisions. After studying the nature of user decisions, we propose a computational approach to model user behavior. First, we introduce a hierarchical clustering method, which allows to group similar photos according to a multi-level similarity structure, based on visual descriptors. Then, the photo context information is extracted from the obtained cluster data and used to adapt a pre-computed independent photo score, using the statistics-based data and a machine learning approach. In addition, as the majority of recent methods for photo assessment are based on convolutional neural networks, we explore and visualize the aesthetic characteristics learned by such methods.

No description available.

Yes / Cardiologists use x-ray image sequences of the moving heart acquired in real-time to diagnose and treat cardiac patients. The amount of radiation used is proportional to image quality; however, exposure to radiation is damaging to patients and personnel. The amount by which radiation dose can be reduced without compromising patient care was determined. For five patient image sequences, increments of computer-generated quantum noise (white + colored) were added to the images, frame by frame using pixel-to-pixel addition, to simulate corresponding increments of dose reduction. The noise adding software was calibrated for settings used in cardiac procedures, and validated using standard objective and subjective image quality measurements. The degraded images were viewed next to corresponding original (not degraded) images in a two-alternativeforced- choice staircase psychophysics experiment. Seven cardiologists and five radiographers selected their preferred image based on visualization of the coronary arteries. The point of subjective equality, i.e., level of degradation where the observer could not perceive a difference between the original and degraded images, was calculated; for all patients the median was 33% 15% dose reduction. This demonstrates that a 33% 15% increase in image noise is feasible without being perceived, indicating potential for 33% 15% dose reduction without compromising patient care. / Funded in part by Philips Healthcare, the Netherlands. Part of this work has been performed in the project PANORAMA, co-funded by grants from Belgium, Italy, France, the Netherlands, and the United Kingdom, and the ENIAC Joint Undertaking.

Bakalauro darbe analizuojamas socialinio pedagogo įvaizdis ugdymo proceso dalyvių vertinimu. Teorinė analizė atskleidžia, jog esminiai veiksniai, skatinantys neigiamą socialinio pedagogo įvaizdį yra: mažas atlyginimas, papildomo darbo paieškos, nedidelės pastangos bei noras kelti profesijos kvalifikaciją, papildomų darbų atlikimas, kurie nėra įtraukti į socialinio pedagogo pareigybės aprašymą, kolegų ir mokyklos administracijos abejingumas socialinio pedagogo kaip specialisto veiklai. Praktinis ir mokslinis tyrimo aktualumas suponuoja tokius probleminius klausimus: Kaip ugdymo proceso dalyviai vertina socialinio pedagogo profesinį įvaizdį? Kaip skirtingi ugdymo proceso dalyviai vertina socialinio pedagogo profesinius gebėjimus, vertybines nuostatas, vizualinį (išorinį) žmogaus portretą, kvalifikacijos kėlimą, kaip profesinio įvaizdžio sudedamąsias dalis? Koks yra ryšys tarp socialinio pedagogo atliekamo vaidmens ir įvaizdžio? Bei kokios galimos įvaizdžio gerinimo galimybės? Tyrimo objektas – socialinio pedagogo profesijos įvaizdis ugdymo proceso dalyvių vertinimu. Tyrimo tikslas – atskleisti socialinio pedagogo profesijos įvaizdį ugdymo proceso dalyvių vertinimu. Tyrimo duomenys renkami naudojant anketinės apklausos raštu metodą. Anketa sudaryta taikant uždaro ir atviro tipo klausimus bei skirta ugdymo proceso dalyviams (N=102) (socialiniams pedagogams, pedagogams bei tėvams). Tyrimo duomenys buvo apdoroti SPSS (Statistical Package For Social Science) programine įranga (19... [toliau žr. visą tekstą] / The final paper presents an analysis of the image of social educators as assessed by the participants of the education process. The theoretical analysis reveals the following key factors promoting the negative image of social educators: low salaries, search for additional work, meager endeavor and desire to further develop their professional qualification, performing additional tasks not included into the social educator job description and indifference of colleagues and school administration towards the activities of social educator as a specialist. The practical and scientific relevance of the study presupposes the following research questions: How is the professional image of social educator assessed by the participants of the education process? How are the professional skills, values, visual (external) human image and qualification development of social educators as constituents of their professional image assessed by the different participants of the education process? What is the connection between the role of social educators and their image? What are the available image improvement possibilities? The research object is the professional image of social educators as assessed by the participants of the education process. The goal of the study is to reveal the professional image of social educators as assessed by the participants of the education process. The research data were gathered by using a written questionnaire-based survey. The survey was compiled from open and... [to full text]