Share Email Print
cover

Proceedings Paper

Supervised and unsupervised learning approaches for the labeling of multivariate images
Author(s): Dominique Bertrand; Bruno Novales; Younes Chtioui
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

A multivariate numeric image can be seen as a 3-way data table: two dimensions of this table are of spatial nature whereas the other characterizes the constitutive univariate images. The process of labeling consists in assigning a qualitative group to each pixel of the original multivariate image. A supervised learning method, stepwise discriminant analysis was compared with two unsupervised methods, simple C-means clustering (CMC) and fuzzy C-means. As illustrative example, the methods were applied on multivariate images of sections of maize kernels obtained by fluorescence imaging. CMC requires the utilization of a function assessing the distance between some representative patterns and the pixel vectors. The relative interest of Euclidean distance and Mahalanobis distance was investigated. The best results were obtained by using CMC and simple Euclidean distance. In these conditions, it was possible to identify, with no a priori knowledge, the main tissues of maize.

Paper Details

Date Published: 14 January 1999
PDF: 9 pages
Proc. SPIE 3543, Precision Agriculture and Biological Quality, (14 January 1999); doi: 10.1117/12.336911
Show Author Affiliations
Dominique Bertrand, Institut National de la Recherche Agronomique (France)
Bruno Novales, Institut National de la Recherche Agronomique (France)
Younes Chtioui, Institut National de la Recherche Agronomique (United States)


Published in SPIE Proceedings Vol. 3543:
Precision Agriculture and Biological Quality
George E. Meyer; James A. DeShazer, Editor(s)

© SPIE. Terms of Use
Back to Top