计算机工程与应用2018，Vol.54Issue(2)：173-176,187,5.DOI:10.3778/j.issn.1002-8331.1608-0031
基于降维LBP与叶片形状特征的植物叶片识别方法
摘要
Abstract
In order to resolve the problem that the shape similarities and rotation of plants leaves will lower the accuracy of plant recognition,a method of recognizing plants leaves is proposed,which is based on the dimension reduction LBP algorithm and the shape features of leaves.Firstly,the LBP algorithm is used to extract high dimensional texture features of leaves.Then PCA is used to reduce the feature dimensions.At the same time,the shape features of the leaves are con-sidered. The LBP rotation invariant features are combined with the shape features effectively. In the low dimensional space,the plant can be classified and recognized by using k Nearest Neighbor method(KNN).The experimental findings prove that this method can accomplish the recognition effectively.关键词
植物识别/局部二值模式/主成分分析/叶片形状特征Key words
plant recognition/local binary pattern/principal component analysis/leaves shape features分类
信息技术与安全科学引用本文复制引用
付波,杨章,赵熙临,单治磊..基于降维LBP与叶片形状特征的植物叶片识别方法[J].计算机工程与应用,2018,54(2):173-176,187,5.基金项目
国家教育部科研项目(No.教外司留[2014]1685) （No.教外司留[2014]1685）
湖北省科技厅重大专项(No.2013AEA001) （No.2013AEA001）
国家自然科学基金(No.61072130). （No.61072130）
