Plant Classification in Images of Natural Scenes Using Segmentations Fusion

Document Type: Original Article

Authors

1 Department of Electrical & Computer Engineering, Babol Noshirvani University of Technology, Babol, Iran

2 Department of Mathematics, Faculty of Basic Science, Babol Noshirvani University of Technology, Babol, Iran

Abstract

This paper presents a novel approach to automatic classifying and identifying of tree leaves using image segmentation fusion. With the development of mobile devices and remote access, automatic plant identification in images taken in natural scenes has received much attention. Image segmentation plays a key role in most plant identification methods, especially in complex background images. Where there are no presumptions about leaf and background, segmentation of leaves in images with complex background is very difficult. In addition, each image has special conditions, so parameters of the algorithm must be set for each image. In this paper, image segmentation fusion is used to overcome this problem. A fast method based on maximum mutual information is used to fuse the results of leaf segmentation algorithms with different parameters. Applying Tsallis entropy and g-calculus, generalized mutual information equations are derived and used to obtain the best consensus segmentation. To evaluate the proposed methods, a dataset with tree leaf images in natural scenes and complex backgrounds is used. These images were taken from Pl@ntLeaves dataset and modified so that they do not have a presumption. The experimental results show the use of Tsallis entropy and g-calculus in image segmentation fusion, improves plant species identification.

Keywords


1.     Mata-Montero, E. and Carranza-Rojas, J., “Automated plant species identification: Challenges and opportunities”, IFIP Advances in Information and Communication Technology,  Springer, Vol. 481, (2016), 26-36, doi: 10.1007/978-3-319-44447-5_3.

2.     Grand-Brochier, M., Vacavant, A., Cerutti, G., Kurtz, C., Weber, J. and Tougne, L., “Tree leaves extraction in natural images: Comparative study of preprocessing tools and segmentation methods”, IEEE Transactions on Image Processing, Vol. 24, No. 5, (2015), 1549-1560, doi: 10.1109/TIP.2015.2400214.

3.     Wäldchen, J. and Mäder, P., “Plant species identification using computer vision techniques: A systematic literature review”, Archives of Computational Methods in Engineering, Vol. 25, No. 2, (2018), 507-543, doi: 10.1007/s11831-016-9206-z.

4.     Wang, Z., Li, H., Zhu, Y. and Xu, T., “Review of plant identification based on image processing” Archives of Computational Methods in Engineering, Vol. 24, No. 3, (2017), 637-654, doi: 10.1007/s11831-016-9181-4.

5.     Zhang, S., Zhang, C. and Wang, X., “Plant species recognition based on global-local maximum margin discriminant projection”, Knowledge-Based Systems, Vol. 200, (2020), doi: 10.1016/j.knosys.2020.105998.

6.     Zhang, S., Huang, W., Huang, Y.A. and Zhang, C., “Plant Species Recognition     Methods     using      Leaf      Image:      Overview”,

Neurocomputing, (2020), doi: 10.1016/j.knosys.2020.105998.

7.     Kumar, N., Belhumeur, P.N., Biswas, A., Jacobs, D.W., Kress, W.J., Lopez, I.C. and Soares, J.V., “Leafsnap: A computer vision system for automatic plant species identification”, in European Conference on Computer Vision, Springer, (2012), doi: 10.1007/978-3-642-33709-3_36.

8.     Cerutti, G., Tougne, L., Coquin, D. and Vacavant, A., “Curvature-scale-based contour understanding for leaf margin shape recognition and species identification”, International Conference on Computer Vision Theory and Applications (2013), doi: 10.5220/0004225402770284.

9.     Nikbakhsh, N., Y. Baleghi, and H. Agahi, “Maximum mutual information and Tsallis entropy for unsupervised segmentation of tree leaves in natural scenes”, Computers and Electronics in Agriculture, Vol. 162, (2019), 440-449, doi: 10.1016/j.compag.2019.04.038.

10.   Le, T.-L., D.-T. Tran, and N.-H. Pham. “Kernel descriptor based plant leaf identification”, in 2014 4th International Conference on Image Processing Theory, Tools and Applications (IPTA), IEEE, (2014), doi: 10.1109/IPTA.2014.7001990.

11.   Saleem, G., Akhtar, M., Ahmed, N. and Qureshi, W.S.,  “Automated analysis of visual leaf shape features for plant classification”, Computers and Electronics in Agriculture,  Vol. 157, (2019), 270-280, doi: 10.1016/j.compag.2018.12.038.

12.   Kaya, A., Keceli, A.S., Catal, C., Yalic, H.Y., Temucin, H. and Tekinerdogan, B., “Analysis of transfer learning for deep neural network based plant classification models”, Computers and Electronics in Agriculture, Vol. 158, (2019), 20-29, doi: 10.1016/j.compag.2019.01.041.

13.   Hedjazi, M.A., I. Kourbane, and Y. Genc. “On identifying leaves: A comparison of CNN with classical ML methods”, in 2017 25th Signal Processing and Communications Applications Conference, IEEE, (2017), doi: 10.1109/SIU.2017.7960257.

14.   Kamilaris, A. and F.X. Prenafeta-Boldú, “Deep learning in agriculture: A survey”, Computers and Electronics in Agriculture, Vol. 147, (2018), 70-90, doi: 10.1016/j.compag.2018.02.016.

15.   Mehri-Dehnavi, H., H. Agahi, and R. Mesiar, “Pseudo-exponential distribution and its statistical applications in econophysics”, Soft Computing, Vol. 23, No. 1, (2019),  357-363, doi: 10.1007/s00500-018-3623-x.

16.   Nikbakhsh, N. and Y. Baleghi. “A New Fast Method of Image Segmentation Fusion Using Maximum Mutual Information”, in 2019 27th Iranian Conference on Electrical Engineering, IEEE, (2019), doi: 10.1109/IranianCEE.2019.8786371.

17.   Wang, H., Zhang, Y., Nie, R., Yang, Y., Peng, B. and Li, T.,  “Bayesian image segmentation fusion”, Knowledge-Based Systems, Vol. 71, (2014), 162-168, doi: 10.1016/j.knosys.2014.07.021.

18.   Arora, J., K. Khatter, and M. Tushir, “Fuzzy c-means clustering strategies: A review of distance measures”, Software Engineering, Springer, (2019), 153-162, doi: 10.1007/978-981-10-8848-3_15.

19.   Comaniciu, D. and P. Meer, “Mean shift: A robust approach toward feature space analysis”, IEEE Transactions on Pattern Analysis & Machine Intelligence, Vol. 5, (2002), 603-619, doi: 10.1109/34.1000236.

20.   Chan, T.F., B.Y. Sandberg, and L.A. Vese, “Active contours without edges for vector-valued images”, Journal of Visual Communication and Image Representation, Vol. 11, No. 2, (2000), 130-141, doi:10.1006/jvci.1999.0442.