Recognition of Optical Microscopy Images Based on Shape and Texture

Abstract:

Airborne pollen is the main cause of pollen allergy, so statistic of the amount and distribution of pollen in the air is important. This paper presents a method to identify airborne pollen grains in optical microscopy images. After pollen region is segmented by thresholding, global shape descriptor and Fourier descriptor are used to extract shape features, gray level co-occurrence matrix is employed to extract texture features, and finally pollen grains are classified by a k-nearest neighborhood classifier. In the experiment with 55 cases of Poaceae, 44 cases of Moraceae and 48 cases of Pinaceae, a classification rate of 82.31% can be obtained with an accuracy of 85.45%, 61.36%, and 97.91% for each family.

• Periodical: Applied Mechanics and Materials (Volumes 195-196)
• Pages: 539-543
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.195-196.539
• Online since: August 2012
• Authors: Shu Heng Zhang, Wei Yang, Lian Yun Wang, Su Zhang
• Keywords: Airborne Pollen, Fourier Descriptor, Global Shape Description, Grey Level Co-Occurrence Matrix, k-Nearest Neighbor Classifier, Microscopy Image

References

[1] E. Stillman and J. Fenley, The needs and prospects for automation in palynology, Quart. Sci. Rev., Vol. 15, p.1–7, (1996).

[2] M. Rodriguez-Damian, E. Cernadas, A. Formella, M. Fernandez-Delgado, and P. DeSa-Otero. Automatic detection and classification of grains of pollen based on shape and texture, IEEE Transactions on Systems Man and Cybernetics Part C(Applications and Reviews), Vol. 36, pp.531-542, July (2006).

DOI: 10.1109/tsmcc.2005.855426

[3] S. H. Landsmeer, E. A. Hendriks, Letty A. de Weger , Johan H. C. Reiber , Berend C. Stoel. Detection of Pollen Grains in Multifocal Optical Microscopy Images of Air Samples, Microscopy Research and Technique, Vol. 72, pp.424-430, January (2009).

DOI: 10.1002/jemt.20688

[4] Ban Wang, Ping Gao, Jie Liu, Shi-kun Zhao, Li-ming He, Yu-lu Zhang, Hong-lei Xia, Bin-feng Mo, Wei Cao, Lian-yun Wang, Airborne Pollen in Southern-West Shanghai Area, Chinese Journal of Allergy & Clinical immunology, Vol. 4, pp.168-175.

[5] Bing-Shan Qiao et al., Color atlas of air-borne pollens and plants in China, Beijing: Peking Union Med. Coll. Press, 2005. (in Chinese).

[6] N. Otsu, A threshold selection method from gray-level histograms, IEEE Trans. Syst., ManCybern., vol9, no. 1, p.62–66, January (1979).

DOI: 10.1109/tsmc.1979.4310076

[7] D. Zhang and G. Lu. A Comparative Study on Shape Retrieval Using Fourier Descriptors with Different Shape Signatures, In Proc. of International Conference on Intelligent Multimedia and Distance Education (ICIMADE01), pp.1-9, Fargo, ND, USA, June 1-3, (2001).

DOI: 10.1109/icme.2001.1237928

[8] R. M. Haralick, K. Shanmugam, and I. Dinstein, Textural features for image classification, IEEE Trans. Man Cybern., vol. 3, no. 6, p.610–621, Nov. (1973).

DOI: 10.1109/tsmc.1973.4309314

[9] Shuheng Zhang, Wei Yang, Guangshan Liao, Lianyun Wang, Su Zhang, Recognition of airborne pollen in microscopy images based on shape and texture, Computer Engineering & Design，accepted. (in Chinese).