A CNN Approach for Corn Leaves Disease Detection to support Digital Agricultural System

Panigrahi, Kshyanaprava Panda; Sahoo, Abhaya Kumar; Das, Himansu

doi:10.1109/icoei48184.2020.9142871

Cited by 56 publications

(20 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Moreover, direction set (DS) based encoding strategy is used for segregating the neighbouring pixel to multisets pixel through pointing towards one direction and maintaining the rotational invariance. Later, encoding is carried out through set wise intensity; furthermore, it is very important to identify the dominant direction through changing the greyscale value [20] for each pixel to a given average greyscale (8).…”

Section: Figure 1 Corn Leaf Disease Typesmentioning

confidence: 99%

“…12, No. 3, June 2022: 2509-2516 2510 heavily due to plant leaf diseases [8]. Therefore, the precise identification of leaf diseases is very essential to maintain the production rate and crop yield.…”

Section: Introductionmentioning

confidence: 99%

“…A detailed study on segmentation of leaf diseases is also presented. In [8], a CNN architecture is adopted for corn leaf disease identification which enhances automation and digitalization in agriculture. Here, convolutional neural network (CNN) architecture enhances the classification accuracy of leaf diseases.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Corn leaf image classification based on machine learning techniques for accurate leaf disease detection

Noola¹,

Basavaraju²

2022

IJECE

View full text Add to dashboard Cite

<span lang="EN-GB">Corn leaf disease possesses a huge impact on the food industry and corn crop yield as corn is one of the essential and basic nutrition of human life especially to vegetarians and vegans. Hence it is obvious that the quality of corn has to be ideal, however, to achieve that it has to be protected from the several diseases. Thus, there is a high demand for an automated method, which can detect the disease in early-stage and take necessary steps. However, early disease detection possesses a huge challenge, and it is highly critical. Thus, in this research work, we focus on designing and developing enhanced-K nearest neighbour (EKNN) model by adopting the basic K nearest neighbour (KNN) model. EKNN helps in distinguishing the different class disease. Further fine and coarse features with high quality are generated to obtain the discriminative, boundary, pattern and structural related information and this information are used for classification procedure. Classification process provides the gradient-based features of high quality. Moreover, the proposed model is evaluated considering the Plant-Village dataset; also, a comparative analysis is carried out with different traditional classification model with different metrics.</span>

show abstract

Section: Figure 1 Corn Leaf Disease Typesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Corn leaf image classification based on machine learning techniques for accurate leaf disease detection

Noola¹,

Basavaraju²

2022

IJECE

View full text Add to dashboard Cite

show abstract

“…We have also compared our proposed work with other approaches like Word embeddings with Bag-of-Words, Sentence Embeddings and Mean Word Embeddings. Some of the recent research works related to convolutional neural network are shown in [8][9][10][11].…”

Section: Introductionmentioning

confidence: 99%

Convolutional Neural Networks-Based Sentence Level Classification of Crime Documents

Das

2021

Computational Intelligence in Pattern Recognition

View full text Add to dashboard Cite

The proposed work demonstrates a sentence level classification scheme for crime documents based on Convolutional Neural Networks (CNN). Unlike other existing approaches, deep convolutional neural networks give importance to the semantic meaning of the text documents, and therefore, are more reliable for classification purposes. The sentences of the reports are also known as phrases which have been vectorized using GloVe. The vectorized phrases have been fed to the CNNbased classification system. The dataset used in the proposed work provides a broad categorization of crime information. But this broad categorization resulted in skewed data that eventually caused potential difficulties while obtaining accuracy on the test data. Therefore, this data imbalance problem has been surpassed by combining the similar classes which reduced the total number of classes. Thus the dataset has been balanced and crime reports have been classified. The effectiveness of the proposed methodology has been evaluated by comparing it with other existing methods.

show abstract

“…metode Faster R-CNN memberikan nilai ratarata precision sebesar 88,7. Penggunaan CNN untuk mendeteksi penyakit pada daun juga dapat digunakan seperti yang dilakukan oleh[15]. Pada penelitian ini, CNN dan adam optimizer digunakan untuk mendeteksi penyakit pada daun tanaman jagung.…”

unclassified

Penerapan Convolutional Neural Network Deep Learning dalam Pendeteksian Citra Biji Jagung Kering

TiaraSari

Haryatmi

2021

RESTI

View full text Add to dashboard Cite

Corn kernels detection can be implemented in industry area. This can be implemented in the selection and packaging the corn kernels before it is distributed. This technique can be implemented in the selection and packaging machine to detect corn kernels accurately. Corn kernel images was used before it is implemented in real-time. The objective of this research was corn kernel detection using Convolutional Neural Network (CNN) deep learning. This technique consists of 3 main stages, the first preprocessing or normalizing the input of corn kernels image data by wrapping and cropping, both modeling and training the system, and testing. The experiment used CNN method to classify images of dry corn kernels and to determine the accuracy value. This research used 20 dry corn kernels images as testing from 80 dry corn kernels images which used in training dataset. The accuracy of detection was dependent from the size of image and position when the image was taken. The accuracy is around 80% - 100% by using 7 convolutional layers and the average of accuracy for testing data was 0,90296. The convolutional layer which implemented in CNN has the strength to detect features in the input image.

show abstract

A CNN Approach for Corn Leaves Disease Detection to support Digital Agricultural System

Cited by 56 publications

References 27 publications

Corn leaf image classification based on machine learning techniques for accurate leaf disease detection

Corn leaf image classification based on machine learning techniques for accurate leaf disease detection

Convolutional Neural Networks-Based Sentence Level Classification of Crime Documents

Penerapan Convolutional Neural Network Deep Learning dalam Pendeteksian Citra Biji Jagung Kering

Contact Info

Product

Resources

About