Forward optical scattering for rapid microbial source tracking
Abstract
This work provides a hybrid technology based on forward optical scattering pattern for microbial source tracking instead of using conventional biomedical approaches. The scattering pattern is generated due to the diffraction of a laser beam which is directed through the bacterial colony. These scattering patterns have been proved to be consistently associated with the type of bacterial hosts. We implemented Gabor wavelets based image feature extraction method and support vector machine based pattern recognition method so as to realize automatic identification. The comparative study of several other image processing methods and pattern recognition methods is based on the accuracy and consistency of classification results. Our approach provides a consistent performance over large database. Finally, this new technology is proved to be a rapid, straightforward, accurate and economical tool for bacterial identification.
Degree
M.S.E.
Advisors
Chen, Purdue University.
Subject Area
Biomedical engineering|Electrical engineering
Off-Campus Purdue Users:
To access this dissertation, please log in to our
proxy server.