Plant Disease Detection Using Image Processing and Machine Learning

Plant Disease Detection Using Image Processing and Machine Learning

SANDEEP R

Department of Artificial Intelligence and Data Science,

Bannari Amman Institute of Technology, Sathyamangalam, India sandeep.ad20@bitsathy.ac.in

SHANGAMESHWAR K

Department of Artificial Intelligence and Data Science,

Bannari Amman Institute of Technology, Sathyamangalam, India shangameshwar.ad20@bitsathy.ac.in

GOWTHAM S

Department of Artificial Intelligence and Data Science,

Bannari Amman Institute of Technology, Sathyamangalam, India gowtham.ad20@bitsathy.ac.in

Abstract— Agriculture acknowledges a fundamental part by temperance of the fast improvement of everybody and expanded interest in food in India. Consequently, it is expected to increase gather yield. One serious reason for low gather yield is contamination achieved by microorganisms, disease, and creatures. Plant disease examination is one of the major and fundamental errands in the piece of developing. It will in general be thwarted by using plant illness identification strategies. To screen, notice or deal with plant infections physically is an exceptionally complicated task. It requires immense extents of work, and needs absurd arranging time; thus, picture handling is used to recognize sicknesses of plants. Plant infection grouping should be possible by utilizing AI calculations which incorporate advances like dataset creation, load pictures, pre-getting ready, division, highlight extraction, preparing classifier, and arrangement. The primary target of this exploration is to build one model, which groups the solid and infected reap leaves and predicts disease of plants. In this paper, the researchers have trained a model to recognize some unique harvests and 38 diseases from the public dataset which contains 70,306 images of the diseases and healthy plant leaves that are collected under controlled conditions. This paper worked on the ResNets algorithm.

Keywords—Plant leaf disease, Deep Learning, CNN algorithm