基于卷积神经网络的植物叶片分类

Plant Leaf Classification Based on CNN

回顾近年来国内外植物叶片分类的研究进展,指出传统方法存在的缺陷。简述卷积神经网络在图像分类的优势,为了简单高效地对植物叶片进行识别,提出一种基于卷积神经网络(Convolutional Neural Network,CNN)的植物叶片识别方法。在Swedish叶片数据集上的实验结果表明,本算法识别正确率高达99.56%,显著优于传统的叶片识别算法。

Plant plays an important role in human life, so it is necessary to build an automatic system for recognizing plant. Plant leaf classification has become a research focus for twenty years. However, conventional methods for recognizing plant leaf have va- rious drawbacks. CNN gained great success in image recognition, in order to utilize CNN to recognize plant leaf, a hierarchical model based on convolutional neural network is proposed. We applied our method to Swedish leaf dataset classification, the exper- imental results showed that the proposed method is quite effective and feasible.