Recognition of pests on crops with a random subspace classifier

Author

Roldan-Serrato, Lucero ; Baydyk, Tetyana ; Kussul, Ernst ; Escalante-Estrada, Alberto ; Gonzalez Rodriguez, Maria Teresa

Author_Institution

Centro de Cienc. Aplic. y Desarrollo Tecnol., Univ. Nac. Autonoma de Mexico (UNAM), Mexico

fYear

2015

fDate

10-12 June 2015

Firstpage

21

Lastpage

26

Abstract

The purpose of this study is to develop and test a recognition system for the Colorado potato beetle. This task is very important for localizing the beetles and reducing the pesticide volume used to protect the harvest. We employ a beetle image dataset that contains 25 images representing different beetle positions and varying numbers of beetles. These images were collected from the Internet. Our recognition system is based on a special neural network, the random subspace classifier (RSC). We calculate the brightness, contrast, and contour orientation histograms of the images and use them as features and inputs to the RSC neural classifier. In addition, we describe the RSC structure and algorithms and analyse the obtained results. We obtained the best recognition rate of 85%.

Keywords

Internet; agricultural engineering; agrochemicals; crops; image classification; image representation; neural nets; random processes; Colorado potato beetle recognition system; Internet; RSC algorithms; RSC neural classifier; RSC structure; beetle image dataset; brightness; contour orientation histograms; contrast; crops; image dataset; neural network; pest recognition; pesticide volume reduction; random subspace classifier; Agriculture; Histograms; Image recognition; Insects; Neural networks; Neurons; Training; Colorado potato beetle; Random subspace classifier (RSC); image recognition; neural network;

fLanguage

English

Publisher

ieee

Conference_Titel

Bioinspired Intelligence (IWOBI), 2015 4th International Work Conference on

Conference_Location

San Sebastian

Print_ISBN

978-1-4673-7845-1

Type

conf

DOI

10.1109/IWOBI.2015.7160138

Filename

7160138