↓ Skip to main content

Acquiring and preprocessing leaf images for automated plant identification: understanding the tradeoff between effort and information gain

Overview of attention for article published in Plant Methods, November 2017
Altmetric Badge

About this Attention Score

  • In the top 25% of all research outputs scored by Altmetric
  • High Attention Score compared to outputs of the same age (84th percentile)
  • High Attention Score compared to outputs of the same age and source (93rd percentile)

Mentioned by

blogs
1 blog
twitter
3 X users
wikipedia
1 Wikipedia page

Citations

dimensions_citation
84 Dimensions

Readers on

mendeley
108 Mendeley
You are seeing a free-to-access but limited selection of the activity Altmetric has collected about this research output. Click here to find out more.
Title
Acquiring and preprocessing leaf images for automated plant identification: understanding the tradeoff between effort and information gain
Published in
Plant Methods, November 2017
DOI 10.1186/s13007-017-0245-8
Pubmed ID
Authors

Michael Rzanny, Marco Seeland, Jana Wäldchen, Patrick Mäder

Abstract

Automated species identification is a long term research subject. Contrary to flowers and fruits, leaves are available throughout most of the year. Offering margin and texture to characterize a species, they are the most studied organ for automated identification. Substantially matured machine learning techniques generate the need for more training data (aka leaf images). Researchers as well as enthusiasts miss guidance on how to acquire suitable training images in an efficient way. In this paper, we systematically study nine image types and three preprocessing strategies. Image types vary in terms of in-situ image recording conditions: perspective, illumination, and background, while the preprocessing strategies compare non-preprocessed, cropped, and segmented images to each other. Per image type-preprocessing combination, we also quantify the manual effort required for their implementation. We extract image features using a convolutional neural network, classify species using the resulting feature vectors and discuss classification accuracy in relation to the required effort per combination. The most effective, non-destructive way to record herbaceous leaves is to take an image of the leaf's top side. We yield the highest classification accuracy using destructive back light images, i.e., holding the plucked leaf against the sky for image acquisition. Cropping the image to the leaf's boundary substantially improves accuracy, while precise segmentation yields similar accuracy at a substantially higher effort. The permanent use or disuse of a flash light has negligible effects. Imaging the typically stronger textured backside of a leaf does not result in higher accuracy, but notably increases the acquisition cost. In conclusion, the way in which leaf images are acquired and preprocessed does have a substantial effect on the accuracy of the classifier trained on them. For the first time, this study provides a systematic guideline allowing researchers to spend available acquisition resources wisely while yielding the optimal classification accuracy.

X Demographics

X Demographics

The data shown below were collected from the profiles of 3 X users who shared this research output. Click here to find out more about how the information was compiled.
Mendeley readers

Mendeley readers

The data shown below were compiled from readership statistics for 108 Mendeley readers of this research output. Click here to see the associated Mendeley record.

Geographical breakdown

Country Count As %
Unknown 108 100%

Demographic breakdown

Readers by professional status Count As %
Student > Ph. D. Student 18 17%
Researcher 17 16%
Student > Bachelor 12 11%
Student > Master 10 9%
Student > Doctoral Student 7 6%
Other 12 11%
Unknown 32 30%
Readers by discipline Count As %
Computer Science 17 16%
Agricultural and Biological Sciences 16 15%
Engineering 15 14%
Environmental Science 8 7%
Medicine and Dentistry 3 3%
Other 11 10%
Unknown 38 35%
Attention Score in Context

Attention Score in Context

This research output has an Altmetric Attention Score of 12. This is our high-level measure of the quality and quantity of online attention that it has received. This Attention Score, as well as the ranking and number of research outputs shown below, was calculated when the research output was last mentioned on 27 August 2023.
All research outputs
#2,702,766
of 24,336,902 outputs
Outputs from Plant Methods
#137
of 1,173 outputs
Outputs of similar age
#52,301
of 335,990 outputs
Outputs of similar age from Plant Methods
#4
of 44 outputs
Altmetric has tracked 24,336,902 research outputs across all sources so far. Compared to these this one has done well and is in the 88th percentile: it's in the top 25% of all research outputs ever tracked by Altmetric.
So far Altmetric has tracked 1,173 research outputs from this source. They typically receive a little more attention than average, with a mean Attention Score of 6.5. This one has done well, scoring higher than 88% of its peers.
Older research outputs will score higher simply because they've had more time to accumulate mentions. To account for age we can compare this Altmetric Attention Score to the 335,990 tracked outputs that were published within six weeks on either side of this one in any source. This one has done well, scoring higher than 84% of its contemporaries.
We're also able to compare this research output to 44 others from the same source and published within six weeks on either side of this one. This one has done particularly well, scoring higher than 93% of its contemporaries.