TRIST: Tree Recognition Intelligent System

L. Onac

doi:10.24193/subbi.2019.1.01

L. Onac Department of Computer Science, Faculty of Mathematics and Computer Science, Babes-Bolyai University, Cluj-Napoca, Romania

DOI: https://doi.org/10.24193/subbi.2019.1.01

Abstract

Plant recognition represents a challenging computer vision problem due to the great variations of shape and texture among plant organs, within the same species. This paper proposes a light-weight, but reasonably deep Convolutional Neural Network architecture able to carry out this classification task. Multiple experiments were conducted with the proposed network architecture on the MEW2012 and Swedish leaf datasets. The experiments showed promising results, outperforming the current state-of-the-art systems that rely exclusively on a convolutional network for plant classification.

References

[1] H.E. Atabay. A convolutional neural network with a new architecture applied on leaf classification. IIOAB Journal, 7:326-331, 2016.
[2] I. Cugu, E. Sener, C. Erciyes, B. Balcı, E. Akın, I. ¨Onal, and A. O. Akyüz. Treelogy: A novel tree classifier utilizing deep and hand-crafted representations. arXiv preprint arXiv:1701.08291, 2017.
[3] P. Dahal. Classification and loss evaluation - softmax and cross entropy loss. https://deepnotes.io/softmax-crossentropy.
[4] C. Y. Gwo and C. H. Wei. Plant identification through images: Using feature extraction of key points on leaf contours. Applications in plant sciences, 1(11), 2013.
[5] R. H. R. Hahnloser, R. Sarpeshkar, M. A. Mahowald, R. J. Douglas, and H. S. Seung. Digital selection and analogue amplification coexist in a cortex-inspired silicon circuit. Nature, 405(6789):947, 2000.
[6] X. He, G. Wang, X. P. Zhang, L. Shang, and Z. K. Huang. Leaf classification utilizing a convolutional neural network with a structure of single connected layer. In International Conference on Intelligent Computing, pages 332–340, 2016.
[7] T. J. Jassman. Mobile leaf classification application utilizing a convolutional neural network. Master’s thesis, Appalachian State University, 2015.
[8] R. Kapur. Rohan #4: The vanishing gradient problem. https://ayearofai.com/rohan-4-the-vanishing-gradient-problem-ec68f76ffb9b.
[9] A. Karpathy. Cs231n convolutional neural networks for visual recognition. Neural networks, 1, 2016.
[10] N. Kumar, P. N. Belhumeur, A. Biswas, D. W. Jacobs, W. J. Kress, I. C. Lopez, and J.V. Soares. Leafsnap: A computer vision system for automatic plant species identification. In Computer vision–ECCV 2012, pages 502–516. Springer, 2012.
[11] Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner. Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11):2278–2324, 1998.
[12] M. E. Nilsback and A. Zisserman. An automatic visual flora: segmentation and classification of flower images. PhD thesis, Oxford University Oxford, 2009.
[13] P. Novotn`y and T. Suk. Leaf recognition of woody species in central europe. biosystems engineering, 115(4):444–452, 2013.
[14] O. Söderkvist. Computer vision classification of leaves from swedish trees. Master’s thesis, Linkoping University, 2001.
[15] N. Srivastava, G. Hinton, A. Krizhevsky, I. Sutskever, and R. Salakhutdinov. Dropout: A simple way to prevent neural networks from overfitting. The Journal of Machine Learning Research, 15(1):1929–1958, 2014.
[16] M. Sulc and J. Matas. Texture-based leaf identification. In European Conference on Computer Vision, pages 185–200. Springer, 2014.
[17] A. Wendel, S. Sternig, and M. Godec. Automated identification of tree species from images of the bark, leaves and needles. In 16th Computer Vision Winter Workshop, page 67. Citeseer, 2011.
[18] 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. In Signal Processing and Information Technology, 2007 IEEE International Symposium on, pages 11–16. IEEE, 2007.