The leaf identification problem : natural scene statistics and human performance
dc.contributor.advisor | Geisler, Wilson S. | en |
dc.contributor.committeeMember | Diehl, Randy L. | en |
dc.contributor.committeeMember | Cormack, Larry K. | en |
dc.contributor.committeeMember | Gilden, David L. | en |
dc.contributor.committeeMember | Cummings, Molly E. | en |
dc.creator | Ing, Almon David | en |
dc.date.accessioned | 2010-09-21T16:28:19Z | en |
dc.date.accessioned | 2010-09-21T16:28:29Z | en |
dc.date.accessioned | 2017-05-11T22:20:14Z | |
dc.date.available | 2010-09-21T16:28:19Z | en |
dc.date.available | 2010-09-21T16:28:29Z | en |
dc.date.available | 2017-05-11T22:20:14Z | |
dc.date.issued | 2010-05 | en |
dc.date.submitted | May 2010 | en |
dc.date.updated | 2010-09-21T16:28:29Z | en |
dc.description | text | en |
dc.description.abstract | For animals with advanced nervous systems, survival and reproduction can depend upon accurate perception of the environment. To understand how a perceptual system should solve a perception task, it is important to consider designs for an ideal observer, a theoretical system that solves a perception task in an optimal way given specific constraints. I studied three specific classification tasks related to the problem of identifying and segmenting leaves in foliage-rich images. In order to derive the ideal observers for these tasks, I created a database of hand-segmented leaves which served to define the ground-truth for these tasks. I also created a new method that uses the ground-truth as a basis for performing statistical inference (classification) in a nearly optimal way. This made it possible for me to approximate ideal observers by approximating an optimal classifier for each task. I also conducted psychophysical experiments to measure human performance in these tasks. The results provide information about how the human visual system should and does interpret foliage-rich images. | en |
dc.format.mimetype | application/pdf | en |
dc.identifier.uri | http://hdl.handle.net/2152/ETD-UT-2010-05-784 | en |
dc.language.iso | eng | en |
dc.subject | Vision | en |
dc.subject | Optimal classification | en |
dc.subject | Modular visual system | en |
dc.subject | Perceptual system design | en |
dc.subject | Object identification | en |
dc.title | The leaf identification problem : natural scene statistics and human performance | en |
dc.type.genre | thesis | en |