MANGO PLANT LEAF DISEASE DETECTION USING GLCM AND KNN  CLASSIFICATION IN NEURAL NETWORKS MERGED WITH MACHINE  LEARNING APPROACH

Fekadu, Duna Melese

dc.contributor.author	Fekadu, Duna Melese
dc.date.accessioned	2022-03-09T06:51:09Z
dc.date.available	2022-03-09T06:51:09Z
dc.date.issued	2021-10
dc.identifier.uri	http://ir.bdu.edu.et/handle/123456789/13181
dc.description.abstract	Mango plant is a perennial tree which can live more than fifty years and it is also the leading fruit produced in most parts of eastern and south-western Ethiopia both in area coverage and quantities produced. It is also a rich source of vitamins, minerals, fiber, prebiotic dietary and antioxidant compounds, thus promoting the benefits for human health. Mango is one of the most important fruit crops and more economically significant agricultural products in Ethiopia, but it is exposed to different constraint in the leaf area. The mango tree is affected by different diseases and it is very difficult to detect disease in naked eye. This study proposes to detect mango leave disease using Gray Level Co-occurrence matrix (GLCM) for the feature extraction and KNN for classification in neural networks merged with Machine learning Approaches. In this research study intends to detect the diseases of mango leaf with machine learning monitoring different symptoms of leaves. Here, trained data are produced by classification technique collecting images of leaves that were various disease affected. Then the proposed system is design to use to identify the symptom of mangoes leaf diseases by using various preprocessing techniques followed by color-based segmentation method to separate the regions of interest then features are extracted using Gray Level Co-occurrence Matrix. The system will help to detect disease without the presence of agriculturist that would save time to identify disease with machine instead of manual system. It would also ease to treat the affected mango leaf disease properly, increase the production of mango. The proposed system could successfully detect and classify the examined disease using KNN classifier the average accuracy is 81.99 % and using ANN classifier the average accuracy is 95 % achieved for Mango Anthracnose, Powdery mildew and Alternaria leaf spot disease varieties using GLCM for extracting texture feature and Classification of the input image is performed at the final stage taking KNN and ANN algorithms.	en_US
dc.language.iso	en_US	en_US
dc.subject	computer science	en_US
dc.title	MANGO PLANT LEAF DISEASE DETECTION USING GLCM AND KNN CLASSIFICATION IN NEURAL NETWORKS MERGED WITH MACHINE LEARNING APPROACH	en_US
dc.type	Thesis	en_US