Local and Global Feature Extraction for Invariant Object Recognition

Perceiving the world visually is a basic act for humans, but for computers it is still an unsolved problem. The variability present innatural environments is an obstacle for effective computer vision. The goal of invariant object recognition is to recognise objects in a digital image despite variations in, for example, pose, lighting or occlusion. In this study, invariant object recognition is considered from the viewpoint of feature extraction. Thedifferences between local and global features are studied with emphasis on Hough transform and Gabor filtering based feature extraction. The methods are examined with respect to four capabilities: generality, invariance, stability, and efficiency. Invariant features are presented using both Hough transform and Gabor filtering. A modified Hough transform technique is also presented where the distortion tolerance is increased by incorporating local information. In addition, methods for decreasing the computational costs of the Hough transform employing parallel processing and local information are introduced.

Learning Robot Motions from Visual Sensing

Learning from demonstration becomes increasingly popular as an efficient way of robot programming. Not only a scientific interest acts as an inspiration in this case but also the possibility of producing the machines that would find application in different areas of life: robots helping with daily routine at home, high performance automata in industries or friendly toys for children. One way to teach a robot to fulfill complex tasks is to start with simple training exercises, combining them to form more difficult behavior. The objective of the Master’s thesis work was to study robot programming with visual input. Dynamic movement primitives (DMPs) were chosen as a tool for motion learning and generation. Assuming a movement to be a spring system influenced by an external force, making this system move, DMPs represent the motion as a set of non-linear differential equations. During the experiments the properties of DMP, such as temporal and spacial invariance, were examined. The effect of the DMP parameters, including spring coefficient, damping factor, temporal scaling, on the trajectory generated were studied.

Det gyldne snitt : den estetiske dimensjon, en kilde til helse oget etisk anliggende

Within caring science, investigations and explorations have been carried out on the ontology of caring, and many aspects of the field have been the subject of scientific research. The main subject for this study is grounded on the human need for aesthetics. The purpose is to find how the aesthetic dimension is taken into consideration and how the aesthetic surroundings are evaluated and attended to, in the general hospitals in Norway. The theoretical perspective is founded basicly on the study of litterature from caring science and philosophy. The aim is to develop a disposition for a framework on the aesthetic surroundings in the hospitals, and to develop phenomenological and ontological knowledge and understanding of the aesthetic dimension. The study aspires to attain a deeper understanding of the aesthetic acknowledgment and of the aesthetic needs. The focus is how the aesthetic dimension can promote health and wellbeing, both for patients and for the caring staff, in the general hospitals and why the aesthetic dimension should be obligatory in `evident care¿. The study concentrates on 11 selected categories in the hospital environment, where aesthetics is of importance. The research is implemented on 5 part studies: 1. part is a study of caring science and philosophical theories about aesthetics, as a framework for the investigation. 2. part is a survey of the physical environment, in Norwegian somatic hospitals, with focus on aesthetics. This by analyzing the strategy plans for the hospitals. 3. and 4. part is questionnaires to patients and nurses to get their opinion and evaluation of the aesthetic environment in the hospitals they are connected to, and their opinion on how this influences the health and wellness for both patients and caring staff. 5. part is qualitative interviews with 16 experts, to get their opinion and evaluation of the aesthetic environment in hospitals they are or have been connected to. How would the experts like the aesthetic surroundings to be, and also their opinion on what influence they think aesthetics has on health and wellness. The main literature of caring science is rooted in K. Erikssons caring theory as well as philosophic literature; mainly I. Kant, Platon and Y. Hirn's theories on aesthetics. Various scientificresearchers of aesthetics have also been referred to. The methodological approach is a triangulation with a hermeneutic exploration, where H.G. Gadamer and Ricoeur provides the inspirational foundation. The findings and conclusions result in the development of new hypothesis for the caring science foundation and suggestions, a disposition for a framework related to future planning of the aesthetic environments in general hospitals. It might be said that a common thread arises/appears in the invariance's (invariables) that are discerned from the analysis and interpretation of the interviews and also important angles shows in the variances that crystallized. Based on the conclusions the study confirms that there is a clearconnection between health, wellness and aesthetics in the environment and that it is an ethical obligationfor those in the caring professions to be aware of and attend to the aesthetic dimension.