Review on Leaf Plant Disease Classification Using Machine Learning Techniques

International Journal of Research and Innovation in Applied Science (IJRIAS) | Volume VI, Issue XI, November 2021|ISSN 2454-6194

Review on Leaf Plant Disease Classification Using Machine Learning Techniques

U. I. Ismail^1*, M. K. Ahmed^2
1Department of Computer Science Federal University of Kashere, Gombe Nigeria
²Department of Computer Science Gombe state University, Gombe Nigeria
*Corresponding Author

Abstract: Agriculture plays a vital role in the world economy. It basically provides job opportunities for the teaming population, eradicates poverty and contributes to the growth of the economy. Hence the need for improved effort for classifying diseases in plant from its leaf is important as it leads to increase in crop yield. Machine learning methods had being used in leaves plant diseases classification. This paper reviews various techniques used for plant leaf disease classification, and found that Most of the researchers used Support Vector Machine (SVM) algorithms for plant disease classification which they concluded that (SVM) is not suitable for large dataset and it does not perform very well when the dataset has more noise, also the target class will be overlapping. To overcome this difficulties a proposed methodology with different approaches to Machine learning was suggested; Deep learning is a sort of machine learning in which a model figures out how to accomplish classification tasks in a direct way from pictures, Neural network will be train using Fine-tuning techniques on different neural networks architectures and at the end comparisons will be done to find out the best neural networks that will be the best for providing an improved solution for leaf plant disease classification by checking their performance best on their accuracy and confusion matrix.

Keywords: Plant disease, Machine learning, classification, Neural Network, Fine-tuning

I. INTRODUCTION

Agriculture is the prime income source in various countries of the world. Grounded on the significance of agriculture, farmers select their crops, paddies, and the related pesticide to restructure the development of the plant in the limited time [1]. In Nigeria, Agriculture is the basis of the economy and employs 75% of the work force. Despite the importance of petroleum as a major contributor to gross domestic product (GDP), the role of agriculture remains most significant in Nigerian economy since independence. Agriculture provides employment for most rural dwellers and it accounts for more than one third of total gross domestic product (GDP) and labour force for the majority of rural Nigerians [2]. Diseases of plants are major causes of plant damage and consequently agriculture and economic loses. Timely identification of plant disease is a critical factor to make harvest healthy and fruitful. The most common approach for identification of diseases of plants is visual observation by experts.

Read More