Plant Disease detection for paddy crop using Ensemble of CNNs

Acharya, Abhijit; Muvvala, Akhil; Gawali, S.Z.; Dhopavkar, Ruhi; Kadam, Rutuja; Harsola, Ashish

doi:10.1109/inocon50539.2020.9298295

Cited by 15 publications

(6 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Respectively, by increasing the width of a CNN model, the layers can learn more fine-grained features. In fact, this approach has been used in the Wide ResNet [19] model. Nonetheless, in contrast to scaling up the depth, increasing only the width inhibits the model from learning complex features.…”

Section: Utilized Cnn Modelsmentioning

confidence: 99%

Towards Improved Disease Identification With Pretrained Convolutional Neural Networks as Feature Extractors for Chili Leaf Images

Aminuddin,

Abdul Kadir,

Md Tomari

et al. 2024

Jurnal Teknologi

View full text Add to dashboard Cite

Chili is a popular crop that is widely grown due to its flavorful and spicy fruit that is nutritionally beneficial. For the benefit of economic growth, it is important to precisely assess the chili health. With the advancement of computer vision-based applications, methods such as feature descriptors have been utilized to assist farm owners in identifying chili diseases via chili leaf images. However, these feature descriptors still require the manual extraction of disease features in order to accurately identify chili diseases. In this research, pretrained Convolutional Neural Networks (CNNs) are proposed as feature extractors to identify healthy and diseased chili leaf images. Three pretrained CNN models, DenseNet-201, EfficientNet-b0, and NasNet-Mobile, are utilized for their ability to identify healthy and diseased chili leaf using five indexes: accuracy, recall, specificity, precision, and F1-score. These indexes are validated through a five-fold cross-validation method during the experiments. The experimental results show that the EfficientNet-b0 model achieved the highest identification performance, with indexes of accuracy, recall, specificity, precision, and F1-score of 97.05%, 0.97, 0.92, 0.92, and 0.94, respectively. Therefore, the use of pretrained CNNs as feature extractors has the capability to enhance the efficiency and accuracy of chili disease identification in agricultural settings.

show abstract

Section: Utilized Cnn Modelsmentioning

confidence: 99%

Towards Improved Disease Identification With Pretrained Convolutional Neural Networks as Feature Extractors for Chili Leaf Images

Aminuddin,

Abdul Kadir,

Md Tomari

et al. 2024

Jurnal Teknologi

View full text Add to dashboard Cite

show abstract

“…Later, SVM and CNN were used to classify the diseases based on the features extracted, and the results were compared. As a part of preprocessing, here researchers have resized and then enhanced the contrast of the images using a histogram equalization technique known as contrast limited adaptive histogram equalization (CLAHE) [23]. Also in the final algorithm they have combined five CNN architectures to produce the output.…”

Section: Literature Reviewmentioning

confidence: 99%

Preprocessing of leaf images using brightness preserving dynamic fuzzy histogram equalization technique

John

Joseph

2023

IJ-AI

View full text Add to dashboard Cite

Agriculture serves as the backbone of many countries. It provides food and other essential materials as per our requirement. Various kinds of diseases are affecting the agricultural crops which in turn reduce the quantity and quality of the agricultural sector. This can also lead to the decrease in food production thereby affecting the economic growth and development. Even though the symptoms and other impacts of the diseases are outwardly visible, manual identification of diseases and rectification is a tedious and time-consuming process. Therefore, detecting the diseases using an automatic computer-based model will be an effective solution. Image processing methods in conjunction with machine learning algorithms provide greater assistance in the field of plant disease detection. In the proposed work, plant leaf images of 10 crops are collected as the dataset. The images after acquisition are preprocessed using brightness preserving dynamic fuzzy histogram equalization (BPDFHE), an advanced version of histogram equalization and Gaussian filtering. The results are calculated and compared using the parameters such as peak signal to noise ratio (PSNR), structural similarity index (SSIM) and mean square error (MSE). This method performs more accurately than the existing preprocessing approaches.

show abstract

“…However, their accuracy rates largely plateaued around 92% [25,36,37]. On the other hand, several scholars utilized ResNet or networks with residual structures for rice disease detection, generally achieving higher accuracies, primarily in the vicinity of 95% [26,27,38,39]. These scholars' work attested to the superior performance of the residual structure, which is one reason we chose ResNet as our backbone network.…”

Section: Limitations Of Other Mainstream Modelsmentioning

confidence: 99%

ResViT-Rice: A Deep Learning Model Combining Residual Module and Transformer Encoder for Accurate Detection of Rice Diseases

et al. 2023

View full text Add to dashboard Cite

Rice is a staple food for over half of the global population, but it faces significant yield losses: up to 52% due to leaf blast disease and brown spot diseases, respectively. This study aimed at proposing a hybrid architecture, namely ResViT-Rice, by taking advantage of both CNN and transformer for accurate detection of leaf blast and brown spot diseases. We employed ResNet as the backbone network to establish a detection model and introduced the encoder component from the transformer architecture. The convolutional block attention module was also integrated to ResViT-Rice to further enhance the feature-extraction ability. We processed 1648 training and 104 testing images for two diseases and the healthy class. To verify the effectiveness of the proposed ResViT-Rice, we conducted comparative evaluation with popular deep learning models. The experimental result suggested that ResViT-Rice achieved promising results in the rice disease-detection task, with the highest accuracy reaching 0.9904. The corresponding precision, recall, and F1-score were all over 0.96, with an AUC of up to 0.9987, and the corresponding loss rate was 0.0042. In conclusion, the proposed ResViT-Rice can better extract features of different rice diseases, thereby providing a more accurate and robust classification output.

show abstract

Plant Disease detection for paddy crop using Ensemble of CNNs

Cited by 15 publications

References 10 publications

Towards Improved Disease Identification With Pretrained Convolutional Neural Networks as Feature Extractors for Chili Leaf Images

Towards Improved Disease Identification With Pretrained Convolutional Neural Networks as Feature Extractors for Chili Leaf Images

Preprocessing of leaf images using brightness preserving dynamic fuzzy histogram equalization technique

ResViT-Rice: A Deep Learning Model Combining Residual Module and Transformer Encoder for Accurate Detection of Rice Diseases

Contact Info

Product

Resources

About