Identiﬁcation of broad-leaved dock (Rumex obtusifolius L.)
on grassland by means of digital image processing
Steffen Gebhardt Æ Ju
rgen Schellberg Æ Reiner Lock Æ
Published online: 16 May 2006
Springer Science+Business Media, LLC 2006
Abstract Digital image processing has the potential to support the identiﬁcation of plant
species required for site-speciﬁc weed control in grassland swards. The present study
focuses on the identiﬁcation of one of the most invasive and persistent weed species on
European grassland, the broad-leaved dock (Rumex obtusifolius L., R.o.), in complex
mixtures of perennial ryegrass with R.o. and other herbs.
A total of 108 digital photographs were obtained from a ﬁeld experiment under constant
recording geometry and illumination conditions. An object-oriented image classiﬁcation
was performed. Image segmentation was done by transforming the red, green, blue (RGB)
colour images to greyscale intensity images. Based on that, local homogeneity images were
calculated and a homogeneity threshold (0.97) was applied to derive binary images.
Finally, morphological opening was performed. The remaining contiguous regions were
considered to be objects. Features describing shape, colour and texture were calculated for
each of these objects. A Maximum-likelihood classiﬁcation was done to discriminate
between the weed species. In addition, rank analysis was used to test how combinations of
features inﬂuenced the classiﬁcation result.
The detection rate of R.o. varied with the training dataset used for classiﬁcation.
Average R.o. detection rates ranged from 71 to 95% for the 108 images, which included
more than 3,600 objects. Misclassiﬁcations of R.o. occurred mainly with Plantago major
(P.m.). Between 9 and 16% R.o. objects were classiﬁed incorrectly as P.m. and 17–24%
P.m. objects were misclassiﬁed as R.o. The classiﬁcation result was inﬂuenced by the
deﬁned object classes (R.o., P.m., T.o., soil, residue vs. R.o., residue). For instance, clas-
siﬁcation rates were 86–91% and 65–82% for R.o. exclusively and R.o. against the
remaining herb species, respectively.
Keywords Rumex obtusifolius Æ Weed detection Æ Digital image processing Æ Pattern
classiﬁcation Æ Precision farming
S. Gebhardt (&) Æ J. Schellberg Æ R. Lock Æ W. Ku
Institute of Crop Science and Resource Management—Crop Science and Plant Breeding,
University of Bonn, Katzenburgweg 5, D 53115 Bonn, Germany
Precision Agric (2006) 7:165–178