ABSTRACT:
There is no machine learning techniques have been used in an attempt to detect diseases in the banana
plant such as banana bacterial wilt (BBW) and banana black sigatoka (BBS) that have caused a huge loss to many banana growers. The study investigated various computer vision techniques which led to the development of an approach that consists of four main phases. In phase one, images of Banana leaves were acquired using
a standard digital camera. Phase two is the preprocessing phase where resizing, image enhancement and canny edge detection is done. Next phase is the segmentation phase which using morphological we have detected disease location present in leaf . Next is the feature extraction phase where extraction of leaf features and segmented image features using GLCM is done. Then comes the prominent phase were classification done Using k-nearest neighbors algorithm (k-NN) classifier as classifier. Lastly, the performance of the classifier is evaluated to determine whether a leaf is diseased or not, if diseased what type of diseased is present.

INTRODUCTION:
Banana research in India is directed towards increasing the production and productivity. However, banana cultivation continues to face several pests and diseases which affect the production and productivity. Many diseases occurring on banana leaf such as, Panama wilt, Sigatoka leaf spot, Bunchy top, Anthracnose, Mosaic, and Bacterial wilt etc. fungal diseases occurring on banana, Sigatoka leaf spot incited by MycosphaerellamusicolaR. Leachex J.L.Mulder also called as yellow Sigatoka is considered as a serious threat to world banana production.
When leaf spots become severe, it reduces the yield drastically. Integrated pest and disease management technology have been developed for the effective, ecofriendly management of major pests and diseases, which affect productivity. Improved nutrition can boost defense mechanisms which in turn results in disease reduction through direct inhibition of fungal activity.

The banana plant is prone to diseases like BlackSigatoka, Panama wilt and Mosaic etc. In BlackSigatoka, small
lesions are present parallel to the veins of the leaves. Some spots developed to form dark in color Fig 1. Yellow spots are present on the leaf surface.

In Panama wilt, the main symptoms of this disease are yellowing ad withering of leaf. This leads to entire foliage
within 2 or 3 days.
In Mosaic disease light green path is present parallel to the veins of the leaf. This leads to loss of green color of the
leaf and mosaic path may appear parallel to the vein.
OBJECTIVE:
Our objective of this paper is to develop a system which will be able to automatically detect banana leaf disease automatically and send the message to person about that disease and cure of corresponding disease.

PROBLEM STATEMENT:
Detection of disease location and reorganization of disease was curtail part of out project.
With the help of canny edge detection and morphological operation we detected disease effected region on leaf and classification is done using KNN.