An Insect Imaging System to Automate Rice Light-Trap Pest Identification

• 作 者: YAO Qing LV Jun LIU Qing-jie D
• 机 构: College of Informatics and Electronics,State Key Laboratory of Rice Biology,Xiangshan Agriculture an
• 出 处: 农业科学学报（英文版）
• 发表日期: 2004年期
• 关键词: automatic identification imaging system rice light-trap pests SVM cross-validate
• 基金项目: The authors gratefully acknowledge the support of the National Natural Science Foundation of China;the Major Scientific and Technological Special of Zhejiang Province,China;the Ningbo Science and Tech

Identification and counting of rice light-trap pests are important to monitor rice pest population dynamics and make pest forecast.Identification and counting of rice light-trap pests manually is time-consuming,and leads to fatigue and an increase in the error rate.A rice light-trap insect imaging system is developed to automate rice pest identification.This system can capture the top and bottom images of each insect by two cameras to obtain more image features.A method is proposed for removing the background by color difference of two images with pests and non-pests.156 features including color,shape and texture features of each pest are extracted into an support vector machine (SVM) classifier with radial basis kernel function.The seven-fold cross-validation is used to improve the accurate rate of pest identification.Four species of Lepidoptera rice pests are tested and achieved 97.5％ average accurate rate.