Classification of Grape Leaves using KNN and SVM Classifiers

Classification of Grape Leaves using KNN and SVM Classifiers

Table of Contents





Abstract

As it is known, in today’s world gross domestic product (GDP) determines the prosperity of a nation. Agriculture directly adds to the GDP, subsequently, incredible endeavors are to be made for its advancement. Automation is the key to the development of agriculture as there is a lack of specialists in this field. So, automation will be a boon for farmers to prevent their plants from diseases and increase the yield. The proposed work includes applying techniques of image processing to automatically classify grape leaves in to healthy and non-healthy. Features such as color and texture are obtained from the leaf image and classifiers such as K-Nearest Neighbor (KNN) and Support Vector Machine (SVM) are used to classify the given grape leaf. It is discovered that for real-time images, KNN (for K=1) gives better accuracy compared with SVM. The accuracy of the proposed system is accomplished as 90% for the SVM classifier and 96.66% for the KNN classifier.

  • Author Keywords

    • Grape Leaves,
    • Texture,
    • Color,
    • KNN,
    • SVM,
    • Classification

Introduction

Grape development is one of the most profitable cultivating undertakings in India. The natural product is eaten new or then again converted into fluid, aged to vino, and made into raisins [1]. In India, grape efficiency is most elevated on the planet and there is an extension to raise it further. Grapes send out of India are around 539100 quintal that makes a portion of about 1.54% of all-out fare of grapes in world [2]. Grapes additionally have therapeutic properties to fix numerous infections. Grapes for the most part need a very warm and moisture-free atmosphere in the development stage and fruit maturity time. Harvests are affected by uneven climatic conditions prompting diminished rural yield [3]. The unaided eye perception of specialists is the principle approach embraced practically speaking for recognition and differentiating proof of plant sicknesses. This methodology is restrictively costly what’s more, tedious in huge farms. Indian economy is an exceptionally needy of agricultural profitability. Consequently, there is a need to distinguish the maladies toward the start and recommend answers for the farmers with the goal that most extreme damages can stay away from in order to expand the yield. In farming, advanced recognition of leaf illness is the real challenge [4]. Irresistible diseases for grape leaves that are found in India are anthracnose, rust, bacterial leaf spot, powdery mildew, black rot, and downy mildew [5].

The proposed work concentrates on the detection of unhealthy grape leaves affected by diseases and water deficiency using image processing techniques. It also depicts the accuracy of classification algorithms for grape leaves. Leaves are classified as healthy leaves or unhealthy leaves. An unhealthy leaf in this context means that leaf is affected (damaged) by some diseases or due to water deficiency. Classification algorithms like K-Nearest Neighbor (KNN) and Support Vector Machine (SVM) are used for classification purposes. Proposed work also includes the comparison of KNN and SVM classifiers in the discipline of leaf disease recognition. This would help to choose the better classification algorithm for future work. The rest part of this paper is sorted o u t as follows: Section 1 introduces the proposed work, section 2 focuses on the work done by research fellows, section 3 explains the methodology adapted for proposed work, section 4 contains a discussion on results and experiments and the final section concludes the paper.

Conclusion

This paper proposes a technique to classify the grape leaf as healthy or unhealthy. The database of 90 images of healthy and unhealthy leaves is created manually. Most relevant features to identify the damaged leaves as such texture and color are used to train and test the system. K-Nearest Neighbor and Support Vector Machine classifiers are used separately to classify grape leaves. The KNN classifier gives better accuracy than the SVM classifier. Proposed work achieved an accuracy of 96.66% for KNN and 90% for SVM. As a future work system can be trained to identify the diseases present on the grape leaves and also provide the possible solution.

About KSRA

The Kavian Scientific Research Association (KSRA) is a non-profit research organization to provide research / educational services in December 2013. The members of the community had formed a virtual group on the Viber social network. The core of the Kavian Scientific Association was formed with these members as founders. These individuals, led by Professor Siavosh Kaviani, decided to launch a scientific / research association with an emphasis on education.

KSRA research association, as a non-profit research firm, is committed to providing research services in the field of knowledge. The main beneficiaries of this association are public or private knowledge-based companies, students, researchers, researchers, professors, universities, and industrial and semi-industrial centers around the world.

Our main services Based on Education for all Spectrum people in the world. We want to make an integration between researches and educations. We believe education is the main right of Human beings. So our services should be concentrated on inclusive education.

The KSRA team partners with local under-served communities around the world to improve the access to and quality of knowledge based on education, amplify and augment learning programs where they exist, and create new opportunities for e-learning where traditional education systems are lacking or non-existent.

FULL Paper PDF file:

Classification of Grape Leaves using KNN and SVM Classifiers

Bibliography

author

A. A. Bharat and M. S. Shirdhonkar,

Year

2020

Title

Classification of Grape Leaves using KNN and SVM Classifiers,

Publish in

2020 Fourth International Conference on Computing Methodologies and Communication (ICCMC), Erode, India, 2020, pp. 745-749,

Doi

10.1109/ICCMC48092.2020.ICCMC-000139.

PDF reference and original file: Click here

+ posts

Somayeh Nosrati was born in 1982 in Tehran. She holds a Master's degree in artificial intelligence from Khatam University of Tehran.

Website | + posts

Professor Siavosh Kaviani was born in 1961 in Tehran. He had a professorship. He holds a Ph.D. in Software Engineering from the QL University of Software Development Methodology and an honorary Ph.D. from the University of Chelsea.

Website | + posts

Nasim Gazerani was born in 1983 in Arak. She holds a Master's degree in Software Engineering from UM University of Malaysia.