Rice Kernel Separations Using Contour Analysis and Skeleton

Abstract:

Determine the percentage of broken rice kernel is crucial for rice quality evaluation. This paper studies a digital image processing method that can effectively separate touching rice kernels in an image of rice used for quality evaluation. An alternative separation algorithm based on contour analysis and skeleton is proposed to separate touching rice kernels. The proposed algorithm can be divided into three parts, namely, pre-processing, obtaining the candidates for separation line endpoints, and analysis for separation process. In the pre-processing, the images are converted into grayscale images. Then the median filter is applied in order to remove noise. Finally the binary images are obtained using Otsu’s algorithm. The next step is to obtain the candidates for separation line endpoints from concave points on the contour of rice kernels. The final step is to draw a separation lines among the candidates using several categories based on concave analysis and skeleton. The experimental results show that the proposed algorithm can accurately separate touching rice kernels and as a result the accurate percentage of broken rice can be obtained.

• Periodical: Applied Mechanics and Materials (Volume 781)
• Pages: 515-518
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.781.515
• Online since: August 2015
• Authors: Chaladchai Siriwongkul, Pattarawit Polpinit
• Keywords: Broken Rice Kernels, Contour Analysis, Segmentation, Skeleton, Touching Rice Kernels

References

[1] C. Costa, F. Antonucci, F. Pallottino, J. Aguzzi, D.W. Sun, P. Menesatti, Shape analysis of agricultural products: a review of recent research advances and potential application to computer vision, Food Bioprocess Technol. 4 (2001) 673-692.

DOI: 10.1007/s11947-011-0556-0

[2] Y. Shao, C. Zhao, Y. Bao, Y. He, Quantification of nitrogen status in rice by least squares support vector machines and reflectance spectroscopy, Food Bioprocess Technol. 5 (2009) 100-107.

DOI: 10.1007/s11947-009-0267-y

[3] P. Lin, Y.M. Chen, Y. He, G.W. Hu, A novel matching algorithm for splitting touching rice kernels based on contour curvature analysis, Computers and Electronics in Agriculture 109 (2014) 124-133.

DOI: 10.1016/j.compag.2014.09.015

[4] P. Shatadal, D.S. Jayas, N.R. Bulley, Digital image analysis for software separation and classification of touching grains: I disconnect algorithm, Trans. ASAE 38 (1995) 635-643.

DOI: 10.13031/2013.27876

[5] N.S. Visen, N.S. Shashidhar, J. Paliwal, D.S. Jayas, AE-Automation and Emarging Technologies: Identification and Segmentation of Occluding Groups of Grain Kernels in a Grain Sample Image, J. Agric. Eng. Res. 79 (2001) 159-166.

DOI: 10.1006/jaer.2000.0690

[6] X.M. Qian, H. Zhu, C.L. Feng, P. Zhu, H. Li, W. Xin, G. Chen, An overlapping bubbles partition method in aerated water flows, Machine Learning and Cybernetics (2004) 3746-3750.

DOI: 10.1109/icmlc.2004.1380472

[7] C. Evans, M. Berman, H. Talbot, Offline fast object splitting, Tech. Rep. CMIS 04/55, CSIRO Mathematical and Information Sciences, North Ryde, NSW, Australia, (2004).

[8] G. Zhang, D.S. Jayas, N.D.G. White, Separation of touching grain kernels in an image by ellipse fitting algorithm, Biosyst. Eng. 92 (2005) 135-142.

DOI: 10.1016/j.biosystemseng.2005.06.010

[9] X. Bai, C. Sun, F. Zhou, Splitting touching cells based on concave points and ellipse fitting, Pattern Recognition 42 (2009) 2434-2446.

DOI: 10.1016/j.patcog.2009.04.003

[10] L. Yan, C.W. Park, S.R. Lee, C.Y. Lee, New separation algorithm for touching grain kernels based on contour segments and ellipse fitting, J Zhejiang Univ-Sci C (Comput & Electron) 12 (2011) 54-61.

DOI: 10.1631/jzus.c0910797

[11] N. Otsu, A threshold selection method from gray-level histograms, IEEE Trans. Syst., Man, Cybernet. 9 (1979) 62–66.

DOI: 10.1109/tsmc.1979.4310076