Title: Fruit fly image segmentation and species determination algorithm
Authors: Pei Xu; Zhen Li; Tiansheng Hong; Huina Ni
Addresses: College of Electronic Engineering, South China Agricultural University, GuangZhou, China; Key Laboratory of Key Technology for South Agricultural Machinery and Equipment, Ministry of Education, GuangZhou, China ' College of Electronic Engineering, South China Agricultural University, GuangZhou, China; Key Laboratory of Key Technology for South Agricultural Machinery and Equipment, Ministry of Education, GuangZhou, China ' College of Electronic Engineering, South China Agricultural University, GuangZhou, China; Key Laboratory of Key Technology for South Agricultural Machinery and Equipment, Ministry of Education, GuangZhou, China ' College of Electronic Engineering, South China Agricultural University, GuangZhou, China; Key Laboratory of Key Technology for South Agricultural Machinery and Equipment, Ministry of Education, GuangZhou, China
Abstract: In this study, an algorithm was developed to identify three kinds of mature fruit flies as Bactrocera dorsalis, B. cucurbitae and B. tau (Dipetra: Tephritidae) based on machine vision technology. After background region segmentation, image registration was achieved using Hough transform, and the BP neural network fruit fly identification model was established to distinguish the fruit fly in each image. Experimental results indicated that: 1) the yellow scutellum at the waist and abdomen of three different kinds of fruit fly could be used for image registration. Both B. cucurbitae and B. tau (Dipetra: Tephritidae) could be distinguished from the Bactrocera dorsalis using the vertical yellow lines in the middle of the back torso. The area rate of these lines to the whole body could be used to distinguish among the three types of fruit fly: 2) the BP neural network model accuracy was 100%, indicating satisfactory identification.
Keywords: machine vision; fruit fly; citrus orchard; Hough transform; precision agriculture.
DOI: 10.1504/IJICT.2018.090555
International Journal of Information and Communication Technology, 2018 Vol.13 No.2, pp.176 - 185
Received: 03 Dec 2014
Accepted: 26 Jun 2015
Published online: 22 Mar 2018 *