Discrimination of Rice Weeds by Neural-network

摘要：

Rice weed control is important for decreasing the loss of rice production. The automatic discrimination method of rice weeds based on BP neural-network was proposed for spraying precisely herbicide. It mainly included image acquisition, image segmentation, feature extraction and weed discrimination. The accuracy of 90.0％ was achieved for discriminating rice and four main rice weeds (Sagittaria pygmaea Miq, Ludwigia prostrate Roxb, Monochoria vaginalis and Marsilea quadrifolia) by shape and texture features. It provided a feasible method for realizing automatic rice weed control.

关键词： rice weed discrimination image segmentation feature extraction BP neural-network weed control

作者: Deyao Fan Qing Yao Jian Tang Baojun Yang

作者单位: College of lnformatics and Electronics Zhejiang Sci-Tech University, Hangzhou, 310018, P.R. China State Key Laboratory of Rice Biology China National Rice Research Institute. 100101. P. R. China

会议类型: 国际会议

会议名称: 2010 International Conference on Image Analysis and Signal Processing(2010 图像分析与信号处理国际会议 IASP 10)

会议地点: 厦门

会议语种:英文

页码: 204-208

在线出版日期: 2010-04-12（万方平台首次上网日期，不代表论文的发表时间）