面向移动终端的农业害虫图像智能识别系统的研究与开发
邵泽中,姚青,唐健,李罕琼,杨保军,吕军,陈轶

Research and Development of the Intelligent Identification System of Agricultural Pests for Mobile Terminals
SHAO ZeZhong,YAO Qing,TANG Jian,LI HanQiong,YANG BaoJun,LÜ Jun,CHEN Yi
表2 不同CNN模型对66种农业害虫的识别结果
Table 2 Identification results of 66 species of agricultural pests by different CNN models
评价方法Evaluation measures CaffeNet GoogleNet VGG19 ResNet101 DenseNet121
平均识别率Average identification rate (%) 86.2 87.4 88.3 91.7 93.9
平均虚警率Average false alarm rate (%) 16.5 17.1 16.4 11.9 8.2