Algorithm design for smart vision sensors.

The goal of this thesis is to provide algorithm design for smart vision sensors. Two algorithms are developed in this thesis. The first one is based on the correlation analysis method for images and can be implemented to find the 2-dimensional position of a target. In particular, the problem of finding the deviations along both X and Y directions is formulated as a matching process between the saved template, which represents the reference position, and the picture of a real static target captured by a 'vision' element such as a CCD camera, through correlation analysis of the 2-D spatial shift. It is an efficient and simple method for deviation identification of target position with high noise rejection ability. Using this method, 2-D position deviation can be found very accurately with high reliability. The second algorithm, which is based on locating the critical points of a planar shape, can be applied to identifying the pattern and finding the 2-dimensional position deviation and rotation angle of a target. (Abstract shortened by UMI.)Dept. of Electrical and Computer Engineering. Paper copy at Leddy Library: Theses & Major Papers - Basement, West Bldg. / Call Number: Thesis2001 .G36. Source: Masters Abstracts International, Volume: 40-06, page: 1586. Adviser: Xiang Chen. Thesis (M.A.Sc.)--University of Windsor (Canada), 2001.

Name thesis:degree_name

M.A.Sc.

Level thesis:degree_level

Masters

Discipline thesis:degree_discipline

Electrical and Computer Engineering

Grantor

University of Windsor

Year dc:date.issued

2001

Author dc:creator

• Gao, Hongmei

Advisor dc:contributor.advisor

• Chen, Xiang

Contributors dc:contributor

• scholarship@uwindsor.ca

Licence

• http://creativecommons.org/licenses/by-nc-nd/4.0/

Language dc:language.iso

en_CA

Handle dc:identifier.uri

https://hdl.handle.net/20.500.14776/8399

OAI identifier oai:identifier

oai:uwindsor.scholaris.ca:20.500.14776/8399