关键词: 植物识别, 局部二值模式, 主成分分析, 叶片形状特征

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 considered. 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.

Key words: plant recognition, local binary pattern, principal component analysis, leaves shape features