Image-based disease diagnosing and predicting of the crops through the deep learning mechanism

Park, Hyeon; Eun, Jee-Sook; Kim, Se-Han

doi:10.1109/ictc.2017.8190957

Cited by 51 publications

(14 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We used a collection of plant leaves images (including both healthy and infectious leaves images for fruits and vegetables) from local farmlands and publicly available dataset known as PlantVillage [35]. We analysed around 50,000 images of plant leaves, which categorised into 25…”

Section: Dataset Preparationmentioning

confidence: 99%

Real-Time Plant Health Assessment via implementing Cloud-Based Scalable Transfer Learning on AWS DeepLens

Khan¹,

Nawaz²,

Ulhaq³

et al. 2020

Preprint

View full text Add to dashboard Cite

In the Agriculture sector, control of plant leaf diseases is crucial as it influences the quality and production of plant species with an impact on the economy of any country. Therefore, automated identification and classification of plant leaf disease at an early stage is essential to reduce economic loss and to conserve the specific species. Previously, to detect and classify plant leaf disease, various Machine Learning models have been proposed; however, they lack usability due to hardware incompatibility, limited scalability and inefficiency in practical usage. Our proposed DeepLens Classification and Detection Model (DCDM) approach deal with such limitations by introducing automated detection and classification of the leaf diseases in fruits (apple, grapes, peach and strawberry) and vegetables (potato and tomato) via scalable transfer learning on A.W.S. SageMaker and importing it on AWS DeepLens for real-time practical usability. Cloud integration provides scalability and ubiquitous access to our approach. Our experiments on extensive image data set of healthy and unhealthy leaves of fruits and vegetables showed an accuracy of 98.78% with a real-time diagnosis of plant leaves diseases. We used forty thousand images for the training of deep learning model and then evaluated it on ten thousand images. The process of testing an image for disease diagnosis and classification using AWS DeepLens on average took 0.349s, providing disease information to the user in less than a second.

show abstract

Section: Dataset Preparationmentioning

confidence: 99%

Real-Time Plant Health Assessment via implementing Cloud-Based Scalable Transfer Learning on AWS DeepLens

Khan¹,

Nawaz²,

Ulhaq³

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…SENet adds a parameter to each channel in a convolutional block so that the network can adjust the weighting of each feature map. F tr :X U, X ϵ R H'×W'×C' , Uϵ R H×W×C (1)  Where, F tr is the convolutional operator for transformation of X to U. This F tr can be the residual block or Inception block.…”

Section: Fig 5: Squeeze-and-excitation Blockmentioning

confidence: 99%

“…Illness is brought about by a pathogen which is any infection causing specialists. In a large portion of the cases, irritations or infections can be observed on the various parts of plants like: leaves, branches or stems [1].…”

Section: Introductionmentioning

confidence: 99%

Senet Cnn Based Tomato Leaf Disease Detection

Pragy¹,

Sharma²,

Sharma³

2019

IJITEE

View full text Add to dashboard Cite

Plants play important roles in the environment. Various plants are fulfilling many demands and basic requirements of the society. Saving such entities in the society is the uttermost necessity in today’s world to deal with plant degradations. Many diseases in plants are common and thus they face degradation. While mainly dealing with common plant such as tomato and potato plants, it is observed that they very often face bacterial and other diseases. A proper precaution can be made to save plant from such diseases. Thus the early prediction of such different diseases can be made, which can be a massive savings to the farmer as well as for the country economy. This paper has adapted a moderate different approach of convolutional neural network called SENet. In this approach, a hybrid process is discussed which uses the advantage of SENet and CNN layer concept for better classification. CNN is performed by using the number of layer and kernel selections. Classification of data is performed using the traditional CNN approach. In this scenario, the quick process occurrence is performed using suppression of less used information. It tries to add weight to each and every feature map in the layer. This approach is used to check, identify and detect the defects in leaf of tomato. The prime motive of the presented approach is; to obtain simple easiest method for the detection of disease in tomato leaf with use of minimal computing resources. Thus an improved, efficient algorithm can be made use in real time implementation of leaf disease prediction with high accuracy and efficiency parameters.

show abstract

“…Practical plant health assessment and an early diseases diagnosis can improve product quality and prevent production loss. Early detection and classification of crop disease are significant to secure the specific species production [24]. Various research studies have found that early detection of plant diseases is crucial as over the period, diseases start affecting the growth of their species, and their symptoms appear on the leaves [26].…”

Section: Introductionmentioning

confidence: 99%

“…As a result, they found that A.C. images performance is better than D.C. images in peach diseases detection and ratio images gave a high accuracy rate. Hyeon Park et al, [25] developed a CNN network of two convolutional and three fully connected layers, for disease detection in the strawberry plant. They worked on a small dataset of leaves images consisting of healthy leaves and a powdery mildew strawberries disease class.…”

Section: Introductionmentioning

confidence: 99%

Real-Time Plant Health Assessment via implementing Cloud-Based Scalable Transfer Learning on AWS DeepLens

Khan¹,

Nawaz²,

Ulhaq³

et al. 2020

Preprint

View full text Add to dashboard Cite

In the Agriculture sector, control of plant leaf diseases is crucial as it influences the quality and production of plant species with an impact on the economy of any country. Therefore, automated identification and classification of plant leaf disease at an early stage is essential to reduce economic loss and to conserve the specific species. Previously, to detect and classify plant leaf disease, various Machine Learning models have been proposed; however, they lack usability due to hardware incompatibility, limited scalability and inefficiency in practical usage. Our proposed DeepLens Classification and Detection Model (DCDM) approach deal with such limitations by introducing automated detection and classification of the leaf diseases in fruits (apple, grapes, peach and strawberry) and vegetables (potato and tomato) via scalable transfer learning on A.W.S. SageMaker and importing it on A.W.S. DeepLens for real-time practical usability. Cloud integration provides scalability and ubiquitous access to our approach. Our experiments on extensive image data set of healthy and unhealthy leaves of fruits and vegetables showed an accuracy of 98.78% with a real-time diagnosis of plant leaves diseases. We used forty thousand images for the training of deep learning model and then evaluated it on ten thousand images. The process of testing an image for disease diagnosis and classification using A.W.S. DeepLens on average took 0.349s, providing disease information to the user in less than a second.

show abstract

Image-based disease diagnosing and predicting of the crops through the deep learning mechanism

Cited by 51 publications

References 1 publication

Real-Time Plant Health Assessment via implementing Cloud-Based Scalable Transfer Learning on AWS DeepLens

Real-Time Plant Health Assessment via implementing Cloud-Based Scalable Transfer Learning on AWS DeepLens

Senet Cnn Based Tomato Leaf Disease Detection

Real-Time Plant Health Assessment via implementing Cloud-Based Scalable Transfer Learning on AWS DeepLens

Contact Info

Product

Resources

About