Color and density based disease detection of leaves

Project Title

Color and density based disease detection of leaves

Project Area of Specialization Artificial IntelligenceProject Summary

Modern organic farming is gaining popularity in the agriculture of many developing countries. There are many problems arise in farming due to various environmental factors and among these plant leaf disease is considered to be the most strong factor that causes the deficit of agricultural product quality. The goal is to mitigate this issue through computer vision and machine learning technique. This project propose a technique for plant leaf disease detection and classification using K-nearest neighbor (KNN) classifier. The texture features are extracted from the leaf disease images for the classification. In this project, KNN classifier will classify the diseases like alternaria alternata, anthracnose, bacterial blight, leaf spot, and canker of various plant species. The proposed approach can successfully detect and recognize the selected diseases with higher accuracy.

Project Objectives

the objective of the project are as folows:

to create a data base for leaves

To create the disease information database

identify the suitable algorithm for classification

The enhanced accurcy achiving system. 

Project Implementation Method

The proposed method is divided into two phases: the training phase and the testing phase. The training and testing phases comprise of five fundamental stages which are image acquisition, color conversion, color segmentation, morphological operation, and feature extraction. The dataset consists of five different types of plant leaf disease image. In training phase, the extracted feature of the segmented plant leaf images are used for the training of the classifier. After the creation of the trained model the testing phase takes an input image and complete all the processing steps on the image up to feature extraction. The new features are given to the classifier model for performing the comparison to give the correct recognition of the disease. Different plant leaves images have bee tested, to be classified into five classes- alternaria alternata, anthracnose, bacterial blight, leaf spot and citrus canker affected.

Benefits of the Project

Advantage of using image processing method is that the leaf diseases can be identified at its early stage.

For improving recognition rate, most of researchers used artificial neural networks and classifiers like ANN, SVM, etc.

All methods of digital image processing save time and provide efficient result.

The image processing leaf disease detection is a cost effective method. 

Technical Details of Final Deliverable

This project propose a method which uses KNN approach to detect and classify various diseases that are present in plant leaves.

Diseases such as alternaria alternata, anthracnose, bacterial blight, leaf spot, and canker of plant leaves are considered for the experiment.

The segmentation of the disease portion will be done by using the k-nearest neighbor classifier and GLCM texture features are used for the classification.

The KNN classifier based segmentation result provides optimum accuracy in plant disease detection and the quantitative performance of the proposed algorithm is obtained by measuring the DSC, MSE and SSIM parameters. 

Further a research will be carried out the classification for many more diseases in different plant and crops. Besides for the improvement of classification accuracy neural network will be deployed.

Final Deliverable of the Project HW/SW integrated systemCore Industry AgricultureOther Industries IT Core Technology Artificial Intelligence(AI)Other Technologies OthersSustainable Development Goals Affordable and Clean EnergyRequired Resources

Item Name	Type	No. of Units	Per Unit Cost (in Rs)	Total (in Rs)
			Total in (Rs)	79850
Thesis and publication	Miscellaneous	2	5000	10000
HP LASERJET M28A MFP	Equipment	1	33450	33450
portable Photo printer for leaf sanning	Equipment	1	31400	31400
1TB Hard disk	Equipment	1	5000	5000