LeafNet - A CNN for Plant identification

We propose a method based on a convolutional neural network (CNN) to identify plants from images of leaves. LeafNet contains three pre-trained models based on the three datasets:
  1. Flavia1
  2. Foliage2
  3. LeafSnap3

If you want to identify a leaf from an image that possibly appears in one of thhese three datasets, you can try our LeafNet. Otherwise, you can train your own LeafNet with your own dataset.


We have tested LeafNet on Ubuntu 15.10 using Python 3.4 and caffe4. Before using LeafNet, please make sure that


Download Leafnet



LeafNet: A computer vision system for automatic plant species identification


LeafNet is released under the BSD-2 Clause Licence.
Copyright (c) 2016, Pierre Barré
All rights reserved.


You have a question? Please contact us

1. Stephen Gang Wu, Forrest Sheng Bao, Eric You Xu, Yu-Xuan Wang, Yi-Fan Chang and Chiao-Liang Shiang, A Leaf Recognition Algorithm for Plant classification Using Probabilistic Neural Network, IEEE 7th International Symposium on Signal Processing and Information Technology, Dec. 2007, Cario, Egypt

2. Abdul Kadir, Lukito Edi Nugroho, Adhi Susanto, P. Insap Santosa; Experiments of Zernike Moments for Leaf Identification; Journal of Theoretical and Applied Information Technology (JATIT); Vol 41, No. 1, 2012, pp. 82-93.

3. "Leafsnap: A Computer Vision System for Automatic Plant Species Identification," Neeraj Kumar, Peter N. Belhumeur, Arijit Biswas, David W. Jacobs, W. John Kress, Ida C. Lopez, João V. B. Soares, Proceedings of the 12th European Conference on Computer Vision (ECCV), October 2012

4. Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., ... & Darrell, T. (2014, November). Caffe: Convolutional architecture for fast feature embedding. In Proceedings of the 22nd ACM international conference on Multimedia (pp. 675-678). ACM.