Kenaf plant pest and disease detection using faster regional based convolutional neural network

<span>Kenaf plant is a fibre whose stem bark taken to be used as raw material for making geo-textile, particleboard, pulp, fiber drain, board, and paper. The presence of pests diseases that attack causes crop production decrease. detection by farmers may challenging task. can done using artificial intelligence-based method. Convolutional neural networks (CNNs) are one the most popular network architectures have been successfully implemented image classification. However, CNN method still considered long time in process, so this was developed into namely faster regional based convolution (RCNN). As selection input features largely determines accuracy results, pre-processing procedure transform kenaf RCNN. A computational experiment proves RCNN has very short computation completing 10000 iterations 3 hours compared convolutional (CNN) 100 at same time. Furthermore, Faster gets 77.50% bounding box 96.74% while 72.96% 400 epochs. results also prove its could produce high detection. </span>