LE3 .A278 2014

2014

Mendivil, Franklin
Teismann, Holger

Acadia University

Master of Science

Masters

Mathematics and Statistics

Mathematics & Statistics

A novel prototype system is described towards the identi cation of indi- viduals belonging to the Panonychus ulmi (Koch) species of phytophagous mite. Identi cation takes place within the context of digital visible-light images of apple tree leaves. These mites are a pest species of economic concern and scienti c interest as a candidate for biocontrol schemes. Dig- ital images are subjected to color slicing using the Hue, Saturation, In- tensity (HSI) color model, which has been under-utilized in the litera- ture, followed by wavelet and morphological processing. Processed images are further subjected to scrutiny by 3 separate identi cation-enumeration schemes based on histogram matching under the Monge-Kantorovich met- ric, frequency-domain template matching, and principal component anal- ysis. The accuracy of results are compared to common thresholds of eco- nomic viability.

The author retains copyright in this thesis. Any substantial copying or any other actions that exceed fair dealing or other exceptions in the Copyright Act require the permission of the author.

https://scholar.acadiau.ca/islandora/object/theses:368