New Zealand Journal of Agricultural Research abstracts

---

Field pest identification by an improved Gabor texture segmentation scheme

Zhao Juan*

Cheng Xiao-Ping

Faculty of Computer and Information Science
Southwest University
Chongqing 400715
China

*Author for correspondence: anysun@swu.edu.cn

Abstract  Segmentation of pests is a critical step in using machine vision for field automation tasks. A new method called GaborBoostSVM is proposed in this paper. The method comprises Gabor wavelets-based feature extraction, AdaBoost-based feature selection and SVM-based pattern recognition algorithm. It performed unsupervised classification in field images into pest and background categories for real-time selective insecticide application. The results showed that the method is capable of performing texture-based pest and background classification consistently high, effectively and with high classification accuracy.

Keywords  AdaBoost; field pests; Gabor filter; image segmentation; SVM

A07083; Online publication date 21 December 2007; Received and accepted 10 August 2007

New Zealand Journal of Agricultural Research, 2007, Vol. 50: 719–723
0028–8233/07/5005–0719  © The Royal Society of New Zealand 2007

PDF file of entire paper: Print-quality (1595K) | screen-quality (396K)

---

This year's abstracts | Journal home page | All abstracts | Publishing home page