2009
DOI: 10.1016/j.compag.2008.12.003
|View full text |Cite
|
Sign up to set email alerts
|

Weed image classification using Gabor wavelet and gradient field distribution

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
4
1

Citation Types

0
27
0
1

Year Published

2010
2010
2021
2021

Publication Types

Select...
5
4

Relationship

0
9

Authors

Journals

citations
Cited by 78 publications
(28 citation statements)
references
References 6 publications
0
27
0
1
Order By: Relevance
“…Automatic evaluation of the density of broad-leaved weeds in digital images of a cereal field could be done with a simple algorithm, although the result overestimated infestation in clean areas and underestimated infestation in highly infested spots (Berge et al 2008). Broad-leaved weeds, mainly dicots, can be identified among grass using color, morphological and texture features (Gebhardt and Kühlbauch 2007;Ishak et al 2009). …”
Section: Introductionmentioning
confidence: 99%
“…Automatic evaluation of the density of broad-leaved weeds in digital images of a cereal field could be done with a simple algorithm, although the result overestimated infestation in clean areas and underestimated infestation in highly infested spots (Berge et al 2008). Broad-leaved weeds, mainly dicots, can be identified among grass using color, morphological and texture features (Gebhardt and Kühlbauch 2007;Ishak et al 2009). …”
Section: Introductionmentioning
confidence: 99%
“…The name "co-occurrence matrix" is used for the resulting matrix of conditional probabilities created for all combinations of each pair of co-occurring grayscale or color values at the defi ned spatial offset and direction. In the majority of the published studies investigating the use of texture for weed detection, the images contained a monoculture (i.e., a single species per image) and classifi cation rates of 90 % or more were frequently obtained (Shearer and Holmes 1990 ;Meyer et al 1998 ;Burks et al 2002 ;Tang et al 2003 ;Ishak et al 2009 ).…”
Section: Plant Recognition: Using Texturementioning
confidence: 98%
“…Herbs identification researches based on leaves characteristics have been proposed in various techniques and systems. This is because leaves have unique characteristics, such as shape, color, texture, and the nature of the odors [2][3][4][5]. However, dealing with herbs in the same group of family is more challenging than with different family groups since their physical appearances and aroma may be similar.…”
Section: Introductionmentioning
confidence: 99%