A Leaf Image Localization based Algorithm for Different Crops Disease Classification

In this modern era, the detection of plant disease plays a vital role in the sustainability of agricultural ecosystem. Today, India being second in farming, well-timed information related to crop is still questioning. Indian Government's farmer portal is available for pesticides, fertilisers, and farm machinery. To alleviate this problem, the paper describes a model to validate the leaf image, predicting leaf disease and notifying the farmer in an effective way on the harvest failure to stabilise farming income. For specific consideration on the validation, a data set library with predefined, uniformly scaled, regular image patterns of leaf disease, is maintained. The research suggests that farmers utilising the model can predict the breakout of leaf disease predominantly acquiring 100% yield.

Download Full-text

Coffee Disease Visualization and Classification

Plants ◽

10.3390/plants10061257 ◽

2021 ◽

Vol 10 (6) ◽

pp. 1257

Author(s):

Milkisa Yebasse ◽

Birhanu Shimelis ◽

Henok Warku ◽

Jaepil Ko ◽

Kyung Joo Cheoi

Keyword(s):

Deep Learning ◽

Plant Diseases ◽

Disease Classification ◽

Classification Problems ◽

Classification Tasks ◽

Visualization Techniques ◽

Learning Architectures ◽

Leaf Image ◽

Insight Into ◽

Naive Approach

Deep learning architectures are widely used in state-of-the-art image classification tasks. Deep learning has enhanced the ability to automatically detect and classify plant diseases. However, in practice, disease classification problems are treated as black-box methods. Thus, it is difficult to trust the model that it truly identifies the region of the disease in the image; it may simply use unrelated surroundings for classification. Visualization techniques can help determine important areas for the model by highlighting the region responsible for the classification. In this study, we present a methodology for visualizing coffee diseases using different visualization approaches. Our goal is to visualize aspects of a coffee disease to obtain insight into what the model “sees” as it learns to classify healthy and non-healthy images. In addition, visualization helped us identify misclassifications and led us to propose a guided approach for coffee disease classification. The guided approach achieved a classification accuracy of 98% compared to the 77% of naïve approach on the Robusta coffee leaf image dataset. The visualization methods considered in this study were Grad-CAM, Grad-CAM++, and Score-CAM. We also provided a visual comparison of the visualization methods.

Download Full-text

Rice disease classification based on leaf image using multilevel Support Vector Machine (SVM)

Journal of Physics Conference Series ◽

10.1088/1742-6596/1490/1/012053 ◽

2020 ◽

Vol 1490 ◽

pp. 012053

Author(s):

Dwi Ratna Sulistyaningrum ◽

Alima Rasyida ◽

Budi Setiyono

Keyword(s):

Support Vector Machine ◽

Disease Classification ◽

Support Vector ◽

Rice Disease ◽

Leaf Image

Download Full-text

Data Enhancement for Plant Disease Classification Using Generated Lesions

Applied Sciences ◽

10.3390/app10020466 ◽

2020 ◽

Vol 10 (2) ◽

pp. 466

Author(s):

Rongcheng Sun ◽

Min Zhang ◽

Kun Yang ◽

Ji Liu

Keyword(s):

Deep Learning ◽

Recognition Accuracy ◽

Lesion Size ◽

Disease Classification ◽

Generative Adversarial Network ◽

Adversarial Network ◽

Network Output ◽

Specific Shape ◽

Deep Learning Network ◽

Leaf Image

Deep learning has recently shown promising results in plant lesion recognition. However, a deep learning network requires a large amount of data for training, but because some plant lesion data is difficult to obtain and very similar in structure, we must generate complete plant lesion leaf images to augment the dataset. To solve this problem, this paper proposes a method to generate complete and scarce plant lesion leaf images to improve the recognition accuracy of the classification network. The advantages of our study include: (i) proposing a binary generator network to solve the problem of how a generative adversarial network (GAN) generates a lesion image with a specific shape and (ii) using the edge-smoothing and image pyramid algorithm to solve the problem that occurs when synthesizing a complete lesion leaf image where the synthetic edge pixels are different and the network output size is fixed but the real lesion size is random. Compared with the recognition accuracy of human experts and AlexNet, it was shown that our method can effectively expand the plant lesion dataset and improve the recognition accuracy of a classification network.

Download Full-text