Visual Recognition: Computational Models and Human Psychophysics

دانشگاه آزاد اسلامی اصفهان(خوراسگان)

منو

رکورد قبلی

رکورد بعدی

" Visual Recognition: Computational Models and Human Psychophysics "

Document Type	:	Latin Dissertation
Language of Document	:	English
Record Number	:	149825
Doc. No	:	ET21617
Main Entry	:	Fei-Fei Li
Title Proper	:	Visual Recognition: Computational Models and Human Psychophysics
Note	:	This document is digital این مدرک بصورت الکترونیکی می باشد
Abstract	:	Object and scene recognition is one of the most essential functionalities of human vision. It is also of fun-damental importance for machines to be able to learn and recognize meaningful objects and scenes. In thisthesis, we explore the following four aspects of object and scene recognition.It is well known that humans can be "blind" even to major aspects of natural scenes when we attendelsewhere. The only tasks that do not need attention appear to be carried out in the early stages of thevisual system. Contrary to this common belief, we show that subjects can rapidly detect animals or vehiclesin briefly presented novel natural scenes while simultaneously performing another attentionally demandingtask. By comparison, they are unable to discriminate large T's from L's, or bisected two-color disks fromtheir mirror images under the same conditions. We explore this phenonmenon further by removing colorfrom the natural scenes, or increasing the number of images peripherally. We find evidence that suggests thatfamiliarity and meaningfulness might be among the factors that determine attentional requirements for bothnatural and synthetic stimuli.So what exactly do we see when we glance at a natural scene? And does what we see change as the glancebecomes longer? We asked naive subjects to report what they saw in nearly a hundred briefly presentedphotographs. After each presentation subjects reported what they had just seen as completely as possible.Afterward, another group of sophisticated individuals who were not aware of the goals of the experimentwere instructed to score each of the descriptions produced by the subjects in the first stage. Individual scoreswere assigned to more than a hundred different attributes. Given the evaluation of the responses, we showthat within a single glance, much object and scene level information is perceived by human subjects. But therichness of our perception seems asymmetrical. Subjects tend.tested for theQ1 PC1 bus cardBoth these projects mere sofixare des elopment efforts tonards contributing to dlfferentaspects of Roboucs and lZ1echatronics projects m the Controls and Roboucs Group..
Subject	:	Electericl tess
	:	برق
electronic file name	:	TL44793.pdf
Title and statement of responsibility and	:	Visual Recognition: Computational Models and Human Psychophysics [Thesis]