Identification of Plant-Leaf Diseases Using CNN and Transfer-Learning

Project Title

Identification of Plant-Leaf Diseases Using CNN and Transfer-Learning

Project Area of Specialization Artificial IntelligenceProject Summary

The timely identification and early prevention of crop diseases are essential for improving production. In this project, deep convolutional-neural-network (CNN) models are implemented to identify and diagnose diseases in plants from their leaves, since CNNs have achieved impressive results in the field of machine vision. Standard CNN models require a large number of parameters and higher computation cost. In this project, we replaced standard convolution with depth=separable convolution, which reduces the parameter number and computation cost. The implemented models were trained with an open dataset consisting of 14 different plant species, and 38 different categorical disease classes and healthy plant leaves. To evaluate the performance of the models, different parameters such as batch size, dropout, and different numbers of epochs were incorporated. The implemented models achieved a disease-classification accuracy rates of 98.42%, 99.11%, 97.02%, and 99.56% using InceptionV3, InceptionResNetV2, MobileNetV2, and EfficientNetB0, respectively, which were greater than that of traditional handcrafted-feature-based approaches. In comparison with other deep-learning models, the implemented model achieved better performance in terms of accuracy and it required less training time. Moreover, the MobileNetV2 architecture is compatible with mobile devices using the optimized parameter. The accuracy results in the identification of diseases showed that the deep CNN model is promising and can greatly impact the efficient identification of the diseases, and may have potential in the detection of diseases in real-time agricultural systems.

Project Objectives

To identify and diagnose diseases in plants from their leaves.

To evaluate the performance of the models, different parameters such as batch size, dropout, and different numbers of epochs were incorporated. 

Project Implementation Method

The implementation of proper techniques to identify healthy and diseased leaves helps in controlling crop loss and increasing productivity.

Shape- and Texture-Based Identification.

Deep-Learning-Based Identification.

Convolutional-Neural-Network Models.

Transfer-Learning Approach.

Dataset.

Benefits of the Project

The benefits of using transfer learning are a decrease in training time, generalization error, and computational cost of building a DL model . In this project work, we use different DL models to identify plant diseases.

Technical Details of Final Deliverable

Our approach is based on the identi?cation of diseases using a deep-learning-based transfer-learning approach. Instead of using standard convolution, we will be using depth wise separable convolution in the inception block, which reduced the number of parameters by a large margin.

The model both has higher accuracy and requires less

training time than the original architecture does

There are many developed methods in the detection and classi?cation of plant diseases using diseased leaves of plants. However, there is still no ef?cient and effective commercial

solution that can be used to identify the diseases. In our work, we will be using four different DL

models (InceptionV3, InceptionResnetV2, MobileNetV2, Ef?cientNetB0) for the detection

of plant diseases using healthy- and diseased-leaf images of plants. To train and test the

model, we will be using the standard PlantVillage dataset with 53,407 images, which were all

captured in laboratory conditions. This dataset consists of 38 different classes of different

healthy- and diseased-leaf images of 14 different species.

The required time to train the model was much less than

that of other machine-learning approaches. Moreover, the MobileNetV2 architecture is

an optimized deep convolutional neural network that limits the parameter number and

operations as much as possible, and can easily run on mobile devices.

Final Deliverable of the Project HW/SW integrated systemCore Industry AgricultureOther Industries IT , Others Core Technology Artificial Intelligence(AI)Other Technologies Augmented & Virtual RealitySustainable Development Goals Good Health and Well-Being for PeopleRequired Resources

Item Name	Type	No. of Units	Per Unit Cost (in Rs)	Total (in Rs)
			Total in (Rs)	80000
Stationary	Miscellaneous	1	5000	5000
Thesis	Miscellaneous	1	5000	5000
ESAKO Astronomical Telescope 70mm (PROFESSIONAL)	Equipment	1	22000	22000
Viewsonic Monitor for display	Equipment	1	19000	19000
4TB hard disk for storage	Equipment	1	19000	19000
Digital Camera Binoculars DT0	Equipment	2	5000	10000