Abstract
Automated identification of herbarium species is of great interest as quite a number of these collections are still unidentified while others need to be updated following recent taxonomic knowledge. One challenging task in automated identification process of these species is the existence of visual noise such as plant information labels, color codes and other scientific annotations which are mostly placed at different locations on the herbarium mounting sheet. This kind of noise needs to be removed before applying different species identification models as it can significantly affect the models’ performance. In this work we propose the use of deep learning semantic segmentation model as a method for removing the background noise from herbarium images. Two different semantic segmentation models, namely DeepLab version three plus (DeepLabv3+) and the Full- Resolution Residual Networks (FRNN-A), were applied and evaluated in this study. The results indicate that FRNN-A performed slightly better with a mean Intersection of Union (IoU) of 99.2% compared to 98.1% mean IoU attained by DeepLabv3+ model on the test set. The pixel -wise accuracy for two classes (herbarium specimen and background) was found to be 99.5% and 99.7%, respectively using FRNN-A model while the DeepLabv3+ was able to segment herbarium specimen and the rest of the background with a pixel-wise accuracy of 98.4% and 99.6%, respectively. This work evidently suggests that deep learning semantic segmentation could be successfully applied as a pre-processing step in removing visual noise existing in herbarium images before applying different classification models.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
J. Wäldchen, M. Rzanny, M. Seeland, and P. Mäder, “Automated plant species identification—Trends and future directions,” PLoS Comput. Biol., vol. 14, no. 4, pp. 1–19, 2018.
M. Rzanny, M. Seeland, J. Wäldchen, and P. Mäder, “Acquiring and preprocessing leaf images for automated plant identification: Understanding the tradeoff between effort and information gain,” Plant Methods, vol. 13, no. 1, pp. 1–11, 2017.
A. Taneja, P. Ranjan, and A. Ujjlayan, “A performance study of image segmentation techniques,” 2015 4th Int. Conf. Reliab. Infocom Technol. Optim. Trends Futur. Dir. ICRITO 2015, pp. 1–6, 2015.
D. Corney, J. Y. Clark, H. L. Tang, and P. Wilkin, “Automatic extraction of leaf characters from herbarium specimens,” Taxon, vol. 61, no. 1, pp. 231–244, 2012.
J. Carranza-Rojas, H. Goeau, P. Bonnet, E. Mata-Montero, and A. Joly, “Going deeper in the automated identification of Herbarium specimens,” BMC Evol. Biol., vol. 17, no. 1, p. 181, 2017.
F. Lateef and Y. Ruichek, “Survey on Semantic Segmentation using Deep Learning Techniques,” Neurocomputing, 2019.
S. Younis et al., “Taxon and trait recognition from digitized herbarium specimens using deep convolutional neural networks,” Bot. Lett., vol. 165, no. 3–4, pp. 377–383, 2018.
G. Polgar, T. U. Grafe, H. Y. K. Pang, A. Brahim, D. Cicuzza, and J. W. F. Slik, “The universiti Brunei darussalam biological collections: History, present assets, and future development,” Raffles Bull. Zool., vol. 66, no. May, pp. 320–336, 2018.
C. Zhang, S. Bengio, M. Hardt, B. Recht, and O. Vinyals, “Understanding deep learning requires rethinking generalization,” 2016.
L. C. Chen, Y. Zhu, G. Papandreou, F. Schroff, and H. Adam, “Encoder-decoder with atrous separable convolution for semantic image segmentation,” Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics), vol. 11211 LNCS, pp. 833–851, 2018.
M. Everingham, S. M. A. Eslami, L. Van Gool, C. K. I. Williams, J. Winn, and A. Zisserman, “The pascal visual object classes challenge: A retrospective,” Int. J. Comput. Vis., vol. 111, no. 1, pp. 98–136, 2015.
T. Pohlen, A. Hermans, M. Mathias, and B. Leibe, “Full-resolution residual networks for semantic segmentation in street scenes,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 4151–4160.
J. Yosinski, J. Clune, Y. Bengio, and H. Lipson, “How transferable are features in deep neural networks?,” in Advances in Neural Information Processing Systems 27, Z. Ghahramani, M. Welling, C. Cortes, N. D. Lawrence, and K. Q. Weinberger, Eds. Curran Associates, Inc., 2014, pp. 3320–3328.
J. D. Dignam, P. L. Martin, B. S. Shastry, and R. G. Roeder, “TensorFlow: A System for Large-Scale Machine Learning,” USENIX Symp. Oper. Syst. Des. Implement., vol. 101, no. C, pp. 582–598, 2016.
Acknowledgement
We acknowledge Universiti Brunei Darussalam for sponsoring this research under the research grant UBD/RSCH/1.4/FICBF(b)/2018/011.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Hussein, B.R., Malik, O.A., Ong, WH., Slik, J.W.F. (2020). Semantic Segmentation of Herbarium Specimens Using Deep Learning Techniques. In: Alfred, R., Lim, Y., Haviluddin, H., On, C. (eds) Computational Science and Technology. Lecture Notes in Electrical Engineering, vol 603. Springer, Singapore. https://doi.org/10.1007/978-981-15-0058-9_31
Download citation
DOI: https://doi.org/10.1007/978-981-15-0058-9_31
Publisher Name: Springer, Singapore
Print ISBN: 978-981-15-0057-2
Online ISBN: 978-981-15-0058-9
eBook Packages: EngineeringEngineering (R0)