This research develops a system for recognizing leaves using mobile phone with very deep convolutional neural networks. We observed that almost all leaf recognition work need to extract the features of a leaf such as diameter, length, ratio, etc. We analyzed the performance of utilizing a convolutional neural network in this system. We implement a region extraction approach to extract the image region which may contain a leaf by utilizing some image pre-processing techniques. The objective of this approach is to recognize leaves that may overlap with each other and thus contain more than one leaves. Moreover, to increase the accuracy and reduce over fitting, some data augmentation technique also employed in this research. We do several transformations and add the case where leaves are partially removed into the dataset to enlarge the capacities. We also employ a fine tuning strategy by using pre-trained model of natural images. Experimental results show that both fine tuning and data augmentation can increase and improve the performance of the proposed system.

This research develops a system for recognizing leaves using mobile phone with very deep convolutional neural networks. We observed that almost all leaf recognition work need to extract the features of a leaf such as diameter, length, ratio, etc. We analyzed the performance of utilizing a convolutional neural network in this system. We implement a region extraction approach to extract the image region which may contain a leaf by utilizing some image pre-processing techniques. The objective of this approach is to recognize leaves that may overlap with each other and thus contain more than one leaves. Moreover, to increase the accuracy and reduce over fitting, some data augmentation technique also employed in this research. We do several transformations and add the case where leaves are partially removed into the dataset to enlarge the capacities. We also employ a fine tuning strategy by using pre-trained model of natural images. Experimental results show that both fine tuning and data augmentation can increase and improve the performance of the proposed system.

[1] S. G. Wu, F. S. Bao, E. Y. Xu, Y.X. Wang, Y. F. Chang and Q. L. Xiang, “A Leaf Recognition Algorithm for Plant Classification using Probabilistic Neural Network”, IEEE International Symposium on Signal Processing And Information Technology, pp. 11-16, 2007.
[2] R. Hu, W. Jia, H. Ling, and D. Huang, “Multiscale Distance Matrix for Fast Plant Leaf Recognition,” in IEEE Transactions on Image Processing vol. 21, pp. 4667-4672, 2012.
[3] N. Kumar, P. N. Belhumeur, A. Biswas, D. W. Jacobs, W. J. Kress, I. C. Lopez and João V. B. Soares, “Leafsnap: A Computer Vision System for Automatic Plant Species Identification,” in ECCV, pp. 502-516, 2012.
[4] C. Zhao, S.S.F. Chan, W. Cham, L.M. Chu, “Plant Identification using Leaf Shapes-A Pattern Counting Approach,” in Pattern Recognition, pp. 3203-3215, 2015.
[5] O. Russakovsky, J. Deng, H. Su, J. Krause, S. Satheesh, S. Ma, Z. Huang, A. Karpathy, A. Khosla, M. Bernstein, A. C. Berg and L. Fei-Fei, “ImageNet Large Scale Visual Recognition Challenge,” in International Journal of Computer Vision, 2015.
[6] A. Krizhevsky, I. Sutskever, and G. E. Hinton, “Imagenet Classification with Deep Convolutional Neural Networks,” in Neural Information Processing Systems, pp. 1097–1105, 2012.
[7] M. D. Zeiler and R. Fergus, “Visualizing and Understanding Convolutional Networks,” in European Conference on Computer Vision, pp. 818-833, 2014.
[8] C. Zhang, P. Zhou, C. Li. and L. Liu, “A Convolutional Neural Network For Leaves Recognition using Data Augmentation,” in IEEE International Conference on Computer and Information Technology, 2015.
[9] S. H. Lee, C. S. Chan, P. Wilkin and P. Remagino, “Deep-plant: Plant Identification with Convolutional Neural Networks,” IEEE International Conference on Image Processing (ICIP), pp. 452-456, 2015.
[10] N. Otsu, “A Threshold Selection Method from Gray Level Histogram,” in IEEE Transactions on Systems, Man, and Cybernetics, vol. 9, pp. 62-66, 1979.
[11] Z. Wang, X. Sun, Y. Zhang, Z. Ying, Y. Ma, “Leaf Recognition based on PCNN”, in Neural Computing and Applications, vol. 32, pp. 899-908, 2016.
[12] Y. Jia, E. Shelhamer, J. Donahue, S. Karayev, J. Long, R. Girshick, S. Guadarrama and T. Darrell, “Caffe: Convolutional Architecture For Fast Feature Embedding,” in arXiv preprint arXiv:1408.509, 2014.
[13] K. Simonyan and A. Zisserman, “Very Deep Convolutional Networks for Large-Scale Image Recognition,” International Conference on Learning Representations, 2015.
[14] S. J. Pan, Q. Yang, "A Survey on Transfer Learning", IEEE Transaction on Knowledge. Data Engineering, vol. 22, pp. 1345-1359, 2010.
[15] J. Du, D. Huang, X. Wang and X. Gu, “Shape Recognition Based on Radial Basis Probabilistic Neural Network and Application to Plant Species Identification,” in Proceedings of the Second international conference on Advances in neural network, vol. 2, pp. 281-285, 2005.
[16] N. Tajbakhsh, J. Y. Shin, S. R. Gurudu, R. T. Hurst, C. B. Kendall, M. B. Gotway and J. Liang, “Convolutional Neural Networks for Medical Image Analysis: Full Training or Fine Tuning?”, in IEEE Transactions on Medical Imaging, vol. 35, no. 5, 2016.
[17] J.C. Caicedo, J.E. Camargo, A.K. Reyes, "Fine-tuning Deep Convolutional Networks for Plant Recognition", in CLEF, 2015.
[18] S. Dodge and L. Karam, “Understanding How Image Quality Affects Deep Neural Networks”, in arXiv preprint arXiv:1604.04004v2, 2016.
[19] Q. Yu, Y. Yang, F. Liu, Y. Z. Song, T. Xiang and T. M. Hospedales, “Sketch-a-Net: A Deep Neural Network that Beats Humans”, in International Journal of Computer Vision, 2017.
[20] B. Chu, V. Madhavan, O. Beijbom, J. Hoffman, T. Darrell. “Best Practices for Fine-Tuning Visual Classifiers to New Domains”, in ECCV Workshop on Transferring and Adapting Source Knowledge in Computer Vision (TASK-CV), 2016.
[21] J. Canny, “A Computational Approach to Edge Detection,” in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. PAMI-8, pp. 679-698, 1986.
[22] “Torch”. [Online]. Available : http://torch.ch/ . [Accessed: 5-April-2017].
[23] Theano Development Team. “Theano: A Python framework for fast computation of mathematical expressions”, in axXiv:1605.02688v1, 2016.
[24] “Tensorflow”. [Online]. Available: https://www.tensorflow.org/. [Accessed: 5-April-2017].
[25] Stanford University, “CS231n Convolutional Neural Networks for Visual Recognition”. [Online]. Available: http://cs231n.github.io/convolutional-networks/. [Accessed: 10-March-2017].
[26] P. Barre, B. C. Stover, K. F. Muller and V. Steinhage, “LeafNet: A computer vision system for automatic plant species identification”, in Ecological Informatics, vol. 40, pp. 50-56, 2017.
[27] “A Brief Report of The Heuritech Deep Learning Meetup”.[Online]. Available: https://blog.heuritech.com/2016/02/29/a-brief-report-of-the-heuritech-deep-learning-meetup-5/ [ Accessed: 12-March-2017]