Convolutional Neural Network Application on Leaf Classification
Plants are everywhere in our lives, we can classify them by observing their features. But for ordinary people, the species we don’t know are much more than we know. So, for amateurs who are interested in botany, a system which can classify different speci
- PDF / 204,667 Bytes
- 6 Pages / 439.37 x 666.142 pts Page_size
- 1 Downloads / 256 Views
Institute of Machine Learning and Systems Biology, College of Electronics and Information Engineering, Tongji University, Caoan Road 4800, Shanghai 201804, China [email protected] 2 Department of Communication Technology, College of Electronic Information Engineering, Suzhou Vocational University, Suzhou 215104, Jiangsu, China 3 College of Mechanical and Electrical Engineering, Nanchang Institute of Technology, Nanchang 330099, Jiangxi, China
Abstract. Plants are everywhere in our lives, we can classify them by observing their features. But for ordinary people, the species we don’t know are much more than we know. So, for amateurs who are interested in botany, a system which can classify different species of leaves must be very useful, a system like that will also help students recognize the leaves they don’t know. This paper describes a system for leaf classification, which is developed with convolutional neural network technique. Previous researches in leaf identification usually use grayscale images. The main reason is that these samples mostly are green leaves. This system is trained by 1500 leaves to classify 50 kinds of plants. Compared to other research, our net use RGB images for input. And in convolutional neural network, we use PReLU instead of traditional ReLU. The experimental result shows that our method for classification gives accuracy of 94.8 %. Keywords: Convolutional neural network recognition Prelu
Leaf classification
Image
1 Introduction This paper describes a convolutional neural network (CNN) for leaf classification. CNN is an effective identification method developed in recent years, and caused widespread attention. It was found in the 1960s. Now, CNN has become one of the most efficient methods in the field of pattern classification. The invention of convolutional neural network [1] follows the discovery of visual mechanisms in animals. LeCun, et al. [2], put the back-propagation algorithm [3] into CNN in 1988. Recently, CNN has been used more widely in the field of image processing [5, 6], and it can reach a better performance than traditional methods [4] through wide verification. © Springer International Publishing Switzerland 2016 D.-S. Huang et al. (Eds.): ICIC 2016, Part I, LNCS 9771, pp. 12–17, 2016. DOI: 10.1007/978-3-319-42291-6_2
Convolutional Neural Network Application on Leaf Classification
13
The convolutional neural networks are multi-layer supervised networks which can learn features automatically from datasets. For the last few years, CNNs have achieved state-of-the-art performance in almost all important classification tasks. It can perform both feature extraction and classification under the same architecture. In recent years, we believe that its main drawback is that it requires very large amounts of training data. However, latest studies have shown that state of the art performance can be achieved with networks trained using “generic” data. AlexNet is a good convolutional neural network model for image processing. We used it for classify our leaves, got an error rate of 1
Data Loading...
