Analysis of Crop Disease Detection with SVM, KNN and Random Forest Classification

EasyChair Preprint 9499

Abstract

Crops square measure being affected by uneven atmospheric condition resulting in faded agricultural yield. This affects international agricultural economy. Moreover, condition becomes even worst once the crops square measure infected by any malady. Agriculture not solely provides food for the human existence; it's conjointly an enormous supply for the economy of any country. several bucks square measure being spent to safeguard the crops annually. One technique to shield the crop is early pesterer detection in order that the crop will be protected against pesterer attack. If pests square measure detected, applicable measures will be taken to shield the crop from an enormous production loss at the top. Early detection would be useful for minimizing the usage of the pesticides and would offer steerage for the choice of the pesticides. ancient technique of examination of the fields is oculus examination however it's terribly troublesome to own a close examination in massive fields. to look at the total field, several human specialists square measure required that is extremely costly and time overwhelming. Hence, associate automatic system is needed which may not solely examine the crops to observe pesterer infestation however can also classify the kind of pests on crops. The planned system determines region of interest from associate input image. The input image should undergo following stages: Image Acquisition, Image pre-processing, Image segmentation so as to get region of interest. Thus, the region of interest was with success determined.

Keyphrases: Image Acquisition, Image pre-processing, K-Nearest Neighbour, K-means rule, Random Forest, Support Vector Machine, feature extraction, image segmentation

@booklet{EasyChair:9499,
  author    = {Rupali Kale and Sanjay Shitole},
  title     = {Analysis of Crop Disease Detection with SVM, KNN and Random Forest Classification},
  howpublished = {EasyChair Preprint 9499},
  year      = {EasyChair, 2022}}