Abstract
In this article, two are the two main characteristics that the machine learning method of plant disease detection must achieve, pace and precision. In this research, an automatic discovery and “classification” of leaf diseases “have be propose then personate the way of treatment, this method is “based “on” K-means as “a clustering “procedure” and KNN as a classifier “tool” using texture feature set, entropy, contrast, RMS, and mean. As a test phase, we utlize a collection of leaves that are possessed from the Al- Ghor area in Jordan. In our research, eight types of diseases that affect plants were identified; “they “are” Alternaria “Alternata”, “Anthracnose”, “Bacterial Blight”, “Cercospora “Leaf “Spot”, “Healthy” Leaf, cucumber mosaic virus, Graphiola phoenius and Diplocarpon rosae. The propose frame could successfully expose “detection” and “classification “of” diseases” with a precision of 100% on meduim with more than 20% speeding up over the offered path in the training stage and 95% in the testing stage.
Keyword
KNN, entropy, contrast, RMS, mean.
PDF Download (click here)
|