The potential of automatic methods of classification
to identify leaf diseases from multispectral images
Sabine D. Bauer
•
Filip Korc
ˇ
•
Wolfgang Fo
¨
rstner
Published online: 26 January 2011
Ó Springer Science+Business Media, LLC 2011
Abstract Three methods of automatic classification of leaf diseases are described based
on high-resolution multispectral stereo images. Leaf diseases are economically important
as they can cause a loss of yield. Early and reliable detection of leaf diseases has important
practical relevance, especially in the context of precision agriculture for localized treat-
ment with fungicides. We took stereo images of single sugar beet leaves with two cameras
(RGB and multispectral) in a laboratory under well controlled illumination conditions. The
leaves were either healthy or infected with the leaf spot pathogen Cercospora beticola or
the rust fungus Uromyces betae. To fuse information from the two sensors, we generated
3-D models of the leaves. We discuss the potential of two pixelwise methods of classifi-
cation: k-nearest neighbour and an adaptive Bayes classification with minimum risk
assuming a Gaussian mixture model. The medians of pixelwise classification rates
achieved in our experiments are 91% for Cercospora beticola and 86% for Uromyces
betae. In addition, we investigated the potential of contextual classification with the so
called conditional random field method, which seemed to eliminate the typical errors of
pixelwise classification.
Keywords Pattern recognition Á Gaussian mixture model (GMM) Á Conditional random
field (CRF) Á k-nearest neighbour Á Sugar beet Á Sensor fusion
Introduction
This paper discusses the potential of three automatic methods of classification to detect leaf
diseases of sugar beet plants. Information about the spatial distribution of infected areas in
a field and possibly the distribution of the disease within a plant is a prerequisite for
precision agriculture. The spatial distribution can be obtained through costly inspection by
human experts that is usually performed on a small sample set. On the contrary, detection
S. D. Bauer (&) Á F. Korc
ˇ
Á W. Fo
¨
rstner
Department of Photogrammetry, Institute of Geodesy and Geoinformation, University of Bonn,
Nussallee 15, 53115 Bonn, Germany
e-mail: sabine.bauer@uni-bonn.de
123
Precision Agric (2011) 12:361–377
DOI 10.1007/s11119-011-9217-6
@Phil_Robichaud
@deepthiw
@JoseServera