Improved accuracy of pest detection using augmentation approach with Faster R-CNN

Abstract

In agriculture, Pests are decreasing agricultural productivity. Identifying a pest is a challenging process and subject to expert opinion. Nowadays, lots of work carried out for automatic pest detection. It becomes possible because of emerging Deep Learning’s object detection architectures. This paper shows the multi-class pest detection using Faster R-CNN architecture and compared the performance results of image augmentation with focused on the accuracy performance along with small dataset. We have used Horizontal Flip and 90 Degree Rotation augmentation parameters for solving class imbalance problem. We found that trained pest detection model with augmentation options can perform better with an accuracy of 91.02% using Faster R-CNN architecture.

Pest Detection in Plants Using Convolutional Neural Network

“…Depends on specified functions, the performance of methods. Image classification is indeed a difficult procedure that must be redone if the issue and the dataset change [6,7]. This difficulty occurs in every effort to detect plant illnesses through the use of computer vision since they trust hand-made functions and algorithms for improved images.…”

“…In the case of illness detection, machine learning approaches were used on the one hand. In agriculture research projects, several of these approaches were employed, such as Artificial Neural Networks (ANN's), Decision trees, K-means or KNN [7]. One of those technique proposed widely in the field of illness diagnosis is Vector Support Machines (SVMs).…”

Machine learning approaches towards sugarcane crop disease identification

“…It is a pathway between CNN it enhances the images very quickly and sends to CNN, To enlarge the image proportion and also the angle of the picture in both Horizontal and Vertical it is used, All the experiments were performed by a high-speed Quadro P5000 which makes us easy to take photos by our phone. Let us see the drawbacks of this work, R-CNN sometimes is very slowest algorithm due to the size and quality of the image, some pests are seasonal and they are hard to identify this kind of pests, In the implementation technique, all the images are stored in an XML file which makes us difficulty to open or access the file [8].…”