Image-Based Wheat Fungi Diseases Identification by Deep Learning

Genaev, Mikhail A.; Сколотнева, Е. С.; Gultyaeva, E. I.; Orlova, Elena A.; Bechtold, Nina P.; Afonnikov, D. A.

doi:10.3390/plants10081500

Cited by 69 publications

(27 citation statements)

References 65 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We conclude that CNNs must be applied carefully, especially when biological context is important. In contrast to similar plant classification approaches such as [7,9,19,20] our method initially extracts regions of interest learned from the images. These regions were used for classification.…”

Section: Discussionmentioning

confidence: 99%

“…The majority of plant identification studies is done by computer vision experts and a lack in interdisciplinary work [18]. In the recent plant science studies [19,20], the authors showed that explanatory factor extraction can be used for reliability investigation. Nevertheless, recent progress in the machine learning community showed, that CNNs may use image regions that happened to be related to the classification goal without any reasonable context, the so-called "clever-Hans phenomenon" [21].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Investigating Explanatory Factors of Machine Learning Models for Plant Classification

Wöber

Mehnen

Sykacek

et al. 2021

Plants

View full text Add to dashboard Cite

Recent progress in machine learning and deep learning has enabled the implementation of plant and crop detection using systematic inspection of the leaf shapes and other morphological characters for identification systems for precision farming. However, the models used for this approach tend to become black-box models, in the sense that it is difficult to trace characters that are the base for the classification. The interpretability is therefore limited and the explanatory factors may not be based on reasonable visible characters. We investigate the explanatory factors of recent machine learning and deep learning models for plant classification tasks. Based on a Daucus carota and a Beta vulgaris image data set, we implement plant classification models and compare those models by their predictive performance as well as explainability. For comparison we implemented a feed forward convolutional neuronal network as a default model. To evaluate the performance, we trained an unsupervised Bayesian Gaussian process latent variable model as well as a convolutional autoencoder for feature extraction and rely on a support vector machine for classification. The explanatory factors of all models were extracted and analyzed. The experiments show, that feed forward convolutional neuronal networks (98.24% and 96.10% mean accuracy) outperforms the Bayesian Gaussian process latent variable pipeline (92.08% and 94.31% mean accuracy) as well as the convolutional autoenceoder pipeline (92.38% and 93.28% mean accuracy) based approaches in terms of classification accuracy, even though not significant for Beta vulgaris images. Additionally, we found that the neuronal network used biological uninterpretable image regions for the plant classification task. In contrast to that, the unsupervised learning models rely on explainable visual characters. We conclude that supervised convolutional neuronal networks must be used carefully to ensure biological interpretability. We recommend unsupervised machine learning, careful feature investigation, and statistical feature analysis for biological applications.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Investigating Explanatory Factors of Machine Learning Models for Plant Classification

Wöber

Mehnen

Sykacek

et al. 2021

Plants

View full text Add to dashboard Cite

show abstract

“…The deep-learning network has been used extensively as part of the automated decision-making tool by extracting hierarchical features from input data for various agricultural tasks. As a result, this wide adoption of DL has opened new possibilities for interpreting massive amounts of data accurately for agriculture analytic systems, such as: Crop surveillance systems through remote sensing to map the land cover and crop discrimination [ 68 , 69 , 70 ]; Plant-stress-monitoring systems by implementing classification and segmentation networks to better understand the interactions between pathogens, insects, and plants, as well as to determine the causes of plant stress [ 71 , 72 , 73 , 74 , 75 ]; Disease and pest identification and quantification systems that will assist in monitoring the health condition of plants, including the nutritional status, development phase, and yield prediction [ 72 , 76 , 77 , 78 , 79 ]. …”

Section: Application Of Multiscale Deep Learningmentioning

confidence: 99%

“…Disease and pest identification and quantification systems that will assist in monitoring the health condition of plants, including the nutritional status, development phase, and yield prediction [ 72 , 76 , 77 , 78 , 79 ].…”

Section: Application Of Multiscale Deep Learningmentioning

confidence: 99%

A Review on Multiscale-Deep-Learning Applications

Elizar

Zulkifley

Muharar

et al. 2022

Sensors

View full text Add to dashboard Cite

In general, most of the existing convolutional neural network (CNN)-based deep-learning models suffer from spatial-information loss and inadequate feature-representation issues. This is due to their inability to capture multiscale-context information and the exclusion of semantic information throughout the pooling operations. In the early layers of a CNN, the network encodes simple semantic representations, such as edges and corners, while, in the latter part of the CNN, the network encodes more complex semantic features, such as complex geometric shapes. Theoretically, it is better for a CNN to extract features from different levels of semantic representation because tasks such as classification and segmentation work better when both simple and complex feature maps are utilized. Hence, it is also crucial to embed multiscale capability throughout the network so that the various scales of the features can be optimally captured to represent the intended task. Multiscale representation enables the network to fuse low-level and high-level features from a restricted receptive field to enhance the deep-model performance. The main novelty of this review is the comprehensive novel taxonomy of multiscale-deep-learning methods, which includes details of several architectures and their strengths that have been implemented in the existing works. Predominantly, multiscale approaches in deep-learning networks can be classed into two categories: multiscale feature learning and multiscale feature fusion. Multiscale feature learning refers to the method of deriving feature maps by examining kernels over several sizes to collect a larger range of relevant features and predict the input images’ spatial mapping. Multiscale feature fusion uses features with different resolutions to find patterns over short and long distances, without a deep network. Additionally, several examples of the techniques are also discussed according to their applications in satellite imagery, medical imaging, agriculture, and industrial and manufacturing systems.

show abstract

“…Convolutional neural networks (CNNs), an important subset of machine learning techniques that learn hierarchical representations and discover potentially complex patterns from the data, have made impressive advances in the computer vision field [ 4 ]. CNNs have also yielded encouraging results in agriculture [ 5 ]. Although the approaches based on traditional machine learning techniques and deep learning techniques have achieved significant success in agricultural applications, developing lightweight networks for selective harvesting robots under unstructured environments is still difficult.…”

Section: Introductionmentioning

confidence: 99%

Medicinal Chrysanthemum Detection under Complex Environments Using the MC-LCNN Model

Chen

Chang

Zhang

et al. 2022

Plants

View full text Add to dashboard Cite

Medicinal chrysanthemum detection is one of the desirable tasks of selective chrysanthemum harvesting robots. However, it is challenging to achieve accurate detection in real time under complex unstructured field environments. In this context, we propose a novel lightweight convolutional neural network for medicinal chrysanthemum detection (MC-LCNN). First, in the backbone and neck components, we employed the proposed residual structures MC-ResNetv1 and MC-ResNetv2 as the main network and embedded the custom feature extraction module and feature fusion module to guide the gradient flow. Moreover, across the network, we used a custom loss function to improve the precision of the proposed model. The results showed that under the NVIDIA Tesla V100 GPU environment, the inference speed could reach 109.28 FPS per image (416 × 416), and the detection precision (AP50) could reach 93.06%. Not only that, we embedded the MC-LCNN model into the edge computing device NVIDIA Jetson TX2 for real-time object detection, adopting a CPU–GPU multithreaded pipeline design to improve the inference speed by 2FPS. This model could be further developed into a perception system for selective harvesting chrysanthemum robots in the future.

show abstract

Image-Based Wheat Fungi Diseases Identification by Deep Learning

Cited by 69 publications

References 65 publications

Investigating Explanatory Factors of Machine Learning Models for Plant Classification

Investigating Explanatory Factors of Machine Learning Models for Plant Classification

A Review on Multiscale-Deep-Learning Applications

Medicinal Chrysanthemum Detection under Complex Environments Using the MC-LCNN Model

Contact Info

Product

Resources

About