LeafNet: A computer vision system for automatic plant species identification

Barré, Pierre; Stöver, Ben C; Müller, Kai; Steinhage, Volker

doi:10.1016/j.ecoinf.2017.05.005

Cited by 236 publications

(119 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In fact, all top methods from the LifeCLEF 2017 contest, an event that aims to evaluate the performance of state-of-the-art identification tools for biological data, were based on deep learning 21 . CNNs have already successfully been used to identify plants from images of their leaves 22,23 and digitized images of herbaria 24 . CNNs could thus prove to be useful tools for taxonomists.…”

Section: Identification and Classificationmentioning

confidence: 99%

Applications for deep learning in ecology

Christin

Hervet

Lecomte

2018

Preprint

View full text Add to dashboard Cite

A lot of hype has recently been generated around deep learning, a novel group of artificial intelligence approaches able to break accuracy records in pattern recognition. Over the course of just a few years, deep learning has revolutionized several research fields such as bioinformatics and medicine with its flexibility and ability to process large and complex datasets. As ecological datasets are becoming larger and more complex, we believe these methods can be useful to ecologists as well. In this paper, we review existing implementations and show that deep learning has been used successfully to identify species, classify animal behaviour and estimate biodiversity in large datasets like camera‐trap images, audio recordings and videos. We demonstrate that deep learning can be beneficial to most ecological disciplines, including applied contexts, such as management and conservation. We also identify common questions about how and when to use deep learning, such as what are the steps required to create a deep learning network, which tools are available to help, and what are the requirements in terms of data and computer power. We provide guidelines, recommendations and useful resources, including a reference flowchart to help ecologists get started with deep learning. We argue that at a time when automatic monitoring of populations and ecosystems generates a vast amount of data that cannot be effectively processed by humans anymore, deep learning could become a powerful reference tool for ecologists.

show abstract

Section: Identification and Classificationmentioning

confidence: 99%

Applications for deep learning in ecology

Christin

Hervet

Lecomte

2018

Preprint

View full text Add to dashboard Cite

show abstract

“…hyperspectral, chlorophyll fluorescence) in combination with machine learning methods (e.g. deep learning) which are already used in plant phenotyping (Barr et al, 2017;Pound et al, 2016) and expanding in phytopathology (Moghadam et al, 2017;Wang et al, 2017). Hence, our whole framework could benefit from a cascade detection (Zhou, 2012) of fruiting bodies with different steps involving different sensors and/or algorithms.…”

Section: Discussionmentioning

confidence: 99%

Automated image processing to support the analysis of between-year transmission of Leptosphaeria maculans in field conditions

Bousset

Palerme

Leclerc

et al. 2018

Preprint

View full text Add to dashboard Cite

Understanding the transmission of inoculum between periods where the host plants are present is central for predicting the development of plant diseases and optimising mitigation strategies. However, the production at the end of the growing period, the survival during the intercrop period, and the emergence or emission of inoculum after sowing or planting can be highly variable, difficult to assess and generally inferred indirectly from symptoms data. As a result, there is a lack of large data sets which is a major brake for the study of these epidemiological processes. Here we focus on Leptosphaeria maculans that causes the black leg of oilseed rape. After having infected leaves, at early stages of the plant, and migrating into the stem, it causes a basal stem canker before harvest. It then survives on stubble left in the field from which ascospores are emitted at the beginning of the next growing period. In this study we first developed an image processing framework to estimate the density of fruiting bodies produced on stubble. Then, we used this framework to analyse automatically a large number of stems collected in oilseed rape fields among a cultivated area. Having performed a quality assessment of the processing chain we used the output data to investigate how the potential level of inoculum may change with the source field, the considered year and the stem canker severity at harvest. Besides the insights gain into the blackleg of oilseed rape, this work shows how image-based phenotyping may support epidemiological studies by increasing substantially the precision of high throughput disease data.

show abstract

“…Latest studies in object categorization demonstrate that CNNs allow for superior results compared to state of the art traditional methods [17, 18]. Current studies on plant identification utilize CNNs and achieve significant improvements over methods developed in the decade before [19–22]. Furthermore it was empirically observed that CNNs trained for a task, e.g., object categorization in general, also achieve exceptional results on similar tasks after minor fine-tuning (transfer learning) [18].…”

Section: Introductionmentioning

confidence: 99%

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

et al. 2017

View full text Add to dashboard Cite

BackgroundAutomated 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.MethodsIn 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.ResultsThe 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.ConclusionsIn 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.

show abstract

LeafNet: A computer vision system for automatic plant species identification

Cited by 236 publications

References 10 publications

Applications for deep learning in ecology

Applications for deep learning in ecology

Automated image processing to support the analysis of between-year transmission of Leptosphaeria maculans in field conditions

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

Contact Info

Product

Resources

About