Comparison of Machine Learning and Deep Learning Algorithms for Automatic Classification of 80 Different Pollen Species
Commenced in January 2007
Frequency: Monthly
Edition: International
Paper Count: 33035
Comparison of Machine Learning and Deep Learning Algorithms for Automatic Classification of 80 Different Pollen Species

Authors: Endrick Barnacin, Jean-Luc Henry, Jimmy Nagau, Jack Molinié

Abstract:

Palynology is a field of interest in many disciplines due to its multiple applications: chronological dating, climatology, allergy treatment, and honey characterization. Unfortunately, the analysis of a pollen slide is a complicated and time consuming task that requires the intervention of experts in the field, which are becoming increasingly rare due to economic and social conditions. In this context, the automation of this task is urgent. In this work, we compare classical feature extraction methods (Shape, GLCM, LBP, and others) and Deep Learning (CNN and Transfer Learning) to perform a recognition task over 80 regional pollen species. It has been found that the use of Transfer Learning seems to be more precise than the other approaches.

Keywords: Image segmentation, stuck particles separation, Sobel operator, thresholding.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 190

References:


[1] Erdtman, G. 1960. “The Acetolysis Method-a Revised Description.”
[2] Flenley, J. 1968. The problem of pollen recognition. In: Clowes, M.B., Penny, J.P. (eds.) Problems in Picture Interpretation, pp. 141–145. CSIRO, Canberra ()
[3] M. del, J. R., J. Cabrera-Falcn, J. Arroyo, C. M., L. Snchez-Chavez, S. T., J. B., and M. Ramrez-Bogantes. 2012. Image processing for pollen classification. In G. A. Lameed, editor, Biodiversity Enrichment in a Diverse World. InTech.
[4] I. France, A. Duller, G. Duller, and H. Lamb. A new approach to automated pollen analysis. Quaternary Science Reviews, 19(6) :537–546, 2002.
[5] P. Li, W. J. Treloar, J. R. Flenley, and L. Empson. 2004. Towards automation of palynology 2 : the use of texture measures and neural network analysis for automated identification of optical images of pollen grains. Journal of Quaternary Science, 19(8) :755–762.
[6] Y. Zhang, D. W. Fountain, R. M. Hodgson, J. R. Flenley, and S. Gunetileke. 2004. Towards automation of palynology 3 : pollen pattern recognition using gabor transforms and digital moments. Journal of Quaternary Science, 19(8) :763–768.
[7] W. J. Treloar, G. E. Taylor, and J. R. Flenley. 2004. Towards automation of palynology 1 : analysis of pollen shape and ornamentation using simple geometric measures, derived from scanning electron microscope images. Journal of Quaternary Science, 19(8) :745–754.
[8] J. R. Ticay-Rivas, M. del Pozo-Banos, C. M. Travieso, J. Arroyo-Hernandez, S. T. P´erez, J. B. Alonso, and F. Mora-Mora. 2011. Pollen classification based on geometrical, descriptors and colour features using decorrelation stretching method. In L. Iliadis, I. Maglogiannis, and H. Papadopoulos, editors, Artificial Intelligence Applications and Innovations, volume 364, pages 342–349. Springer Berlin Heidelberg. Series Title : IFIP Advances in Information and Communication Technology.
[9] N. R. Nguyen, M. Donalson-Matasci, and M. C. Shin. 2013. Improving pollen classification with less training effort. In 2013 IEEE Workshop on Applications of Computer Vision (WACV), pages 421–426. IEEE.
[10] A. Daood, E. Ribeiro, and M. Bush. 2016. Pollen recognition using a multi-layer hierarchical classifier. In 2016 23rd International Conference on Pattern Recognition (ICPR), pages 3091–3096. IEEE.
[11] K. A. Holt and K. D. Bennett. 2014. Principles and methods for automated palynology. New Phytologist, 203(3) :735–742.
[12] Vega, Gildardo Lozano. 2015. “Image-Based Detection and Classification of Allergenic Pollen.” June. http://dx.doi.org/.
[13] C. Chen, E. A. Hendriks, R. P. W. Duin, J. H. C. Reiber, P. S. Hiemstra, L. A. de Weger, and B. C. Stoel. 2006. Feasibility study on automated recognition of allergenic pollen : grass, birch and mugwort. Aerobiologia, 22(4) :275–284.
[14] C. Chudyk, H. Castaneda, R. Leger, I. Yahiaoui, and F. Boochs. 2015. Development of an automatic pollen classification system using shape, texture and aperture features. LWA.
[15] Y. Kaya, S. Mesut Pınar, M. Emre Erez, M. Fidan, and J. B. Riding. 2014. Identification of Onopordum pollen using the extreme learning machine, a type of artificial neural network. Palynology, 38(1) :129–137.
[16] R. Dell’Anna, P. Lazzeri, M. Frisanco, F. Monti, F. Malvezzi Campeggi, E. Gottardini, and M. Bersani. 2009. Pollen discrimination and classification by fourier transform infrared (FT-IR) microspectroscopy and machine learning. Analytical and Bioanalytical Chemistry, 394(5) :1443–1452.
[17] S. Kawashima, B. Clot, T. Fujita, Y. Takahashi, and K. Nakamura. 2007. An algorithm and a device for counting airborne pollen automatically using laser optics. Atmospheric Environment, 41(36) :7987–7993.
[18] O. Ronneberger, Q. Wang, and H. Burkhardt. 2007.3d invariants with high robustness to local deformations for automated pollen recognition. In F. A. Hamprecht, C. Schn¨orr, and B. J¨ahne, editors, Pattern Recognition, volume 4713, pages 425–435. Springer Berlin Heidelberg, Series Title : Lecture Notes in Computer Science.
[19] R. Haralick. 1979. Statistical and structural approaches to texture. Proceedings of the IEEE, 67(5) :786–804.
[20] Ojala, T., M. Pietikainen, and D. Harwood. 1994. “Performance Evaluation of Texture Measures with Classification Based on Kullback Discrimination of Distributions.” In Proceedings of 12th International Conference on Pattern Recognition, 1:582–85 vol.1.
[21] A. Daood, E. Ribeiro, and M. Bush. Pollen grain recognition using deep learning. In G. Bebis, R. Boyle, B. Parvin, D. Koracin, F. Porikli, S. Skaff, A. Entezari, J. Min, D. Iwai, A. Sadagic, C. Scheidegger, and T. Isenberg. 2016. Advances in Visual Computing - 12th International Symposium, ISVC 2016, Las Vegas, NV, USA, December 12-14, 2016, Proceedings, Part I, volume 10072 of Lecture Notes in Computer Science, pages 321–330. Springer.
[22] A. Daood, E. Ribeiro, and M. Bush. Classifying pollen using robust sequence alignment of sparse z-stack volumes. In G. Bebis, R. Boyle, B. Parvin, D. Koracin, F. Porikli, S. Skaff, A. Entezari, J. Min, D. Iwai, A. Sadagic, C. Scheidegger, and T. Isenberg. 2016. Advances in Visual Computing - 12th International Symposium, ISVC 2016, Las Vegas, NV, USA, December 12-14, 2016, Proceedings, Part I, volume 10072 of Lecture Notes in Computer Science, pages 331–340. Springer.
[23] V. Sevillano, K. Holt, and J. L. Aznarte. 2020. Precise automatic classification of 46 different pollen types with convolutional neural networks. bioRxiv.
[24] Joblove, George H., and Donald Greenberg. 1978. “Color Spaces for Computer Graphics.” SIGGRAPH Comput. Graph. 12 (3): 20–25.
[25] Otsu, Nobuyuki. 1979. “A Threshold Selection Method from Gray-Level Histograms.” IEEE Transactions on Systems, Man, and Cybernetics 9 (1): 62–66.
[26] R. C. Gonzalez and R. E. Woods. 2008. Digital image processing. Prentice Hall, 3rd ed edition.
[27] Hu, Ming-Kuei. 1962. “Visual Pattern Recognition by Moment Invariants.” IRE Transactions on Information Theory 8 (2): 179–87.
[28] Fogel, I., and D. Sagi. 1989. “Gabor Filters as Texture Discriminator.” Biological Cybernetics 61 (2): 103–13.
[29] Goodfellow, Ian, Yoshua Bengio, and Aaron Courville. 2016. “Deep Learning“. MIT Press.
[30] Hall, Mark Andrew. 1999. “Correlation-based feature selection for machine learning.“
[31] D. P. Kingma and J. Ba. Adam. 2014. A Method for Stochastic Optimization. arXiv e-prints.
[32] Zoph, Barret, Vijay Vasudevan, Jonathon Shlens, and Quoc V. Le. 2017. “Learning Transferable Architectures for Scalable Image Recognition.” arXiv (cs.CV). arXiv. http://arxiv.org/abs/1707.07012.