摘要
针对油茶果采摘、脱壳后机器视觉分选效率不高的问题,提出一种多特征偏好人工免疫网络算法,该算法应用人工免疫网络的多目标优化与偏好数据库特征,提取油茶目标的颜色、形态多特征输入免疫网络进行仿真测试。试验结果表明,本文提出的多特征偏好免疫网络的识别率最高达到90%以上。相比单特征分选方法有了较大的提升,证明本文分选方法的有效性,并为农林业目标智能化分选辨识提供一种可行的方案。
In order to solve the problem of low sorting efficiency after picking and shelling of Camellia fruits in machine-vision,the paper proposes a preference artificial immune network algorithm(aiNet)with multi-features,which applies the multi-objective optimization of artificial immune network and preference database to extract the multi-features in color and shape of Camellia objects to input into the immune network for simulation test.The test results show that the multi-features preference immune network proposed in this paper is feasible.The recognition rate of the network has reached 90%,and the minimum identification time is 60 ms.Compared with the single feature sorting method,this method is more effective,which provides a feasible scheme for the intelligent sorting method of agricultural and forestry targets.
作者
李昕
陈泽君
李立君
谭季秋
吴发展
Li Xin;Chen Zejun;Li Lijun;Tan Jiqiu;Wu Fazhan(School of Mechanical Engineering,Hunan Institute of Engineering,Xiangtan,411104,China;Hunan Academy of Forestry,Changsha,410004,China;School of Mechanical and Electrical Engineering,Central South University of Forestry and Technology,Changsha,410004,China;Fengke Forestry Equipment Technology Co.Ltd.,Zhuzhou,412000,China)
出处
《中国农机化学报》
北大核心
2021年第9期187-194,共8页
Journal of Chinese Agricultural Mechanization
基金
国家重点研发计划项目(2016YFD0702100)
湖南省重点研发计划项目(2018NK2065)。