Novel Watershed Algorithm for Touching Rice Image Segmentation

Abstract:

An efficient watershed algorithm is proposed in order to solve the problem that touching rice is difficult to process during consequent image segmentation. First, the binary image is ultra-eroded by using a different structuring element to form different distance image. Second, watershed image is obtained by using the watershed algorithm. Finally, the real watershed can be extracted. Compared with other watershed algorithms, the experiment results demonstrated that this method segmented out rice successfully in the touching rice image and improved the measurement accuracy, and also overcome over-segmentation effectively.

• Periodical: Advanced Materials Research (Volumes 271-273)
• Pages: 1-6
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.271-273.1
• Online since: July 2011
• Authors: Fang Jun Kuang, Wei Hong Xu, Yan Hua Wang
• Keywords: Distance Transformation, Image Segmentation, Real Watershed, Touching Rice, Ultra-Erosion, Watershed Algorithm

References

[1] P. Shatadal, D.S. Jayas, N.R. Bulley: Digital image analysis for software separation and classification of touching grains: I. Disconnect algorithm. Transactions of the ASAE. Vol. 38 (2) (1995), pp.635-643.

DOI: 10.13031/2013.27876

[2] J. C. Russ: The image processing handbook, third ed., CRC Press LLC in cooperation with IEEE Press, Boca Raton, FL, (1998), p.771.

[3] N. S. Shashidhar, D. S. Jayas, T. G. Crowe, et al: Processing of digital images of touched kernels by ellipse fitting, Canadian Agricultural Engineering. Vol. 39 (2) (1997), pp.139-142.

[4] N. S. Visen, N. S. Shashidhar, J. Paliwal, et al: Identification and segmentation of occluding groups of grain kernels in a grain sample image. Journal of Agriculture Engineering Research. Vol. 79 (2) (2001), pp.159-166.

[5] M. A. Shahin, S. J. Symons: Seed sizing from images of non-singulated grain samples, Canadian Biosystems Engineering. Vol. 47 (3) (2005), pp.49-55.

[6] Y. Ling, Y. M. Wang, M. Sun, et al: Application of watershed algorithm to paddy image segmentation, Transactions of the Chinese Society for Agricultural Machinery. Vol. 36 (3) (2005), pp.71-74.

[7] W. Wang, J. Paliwal: Separation and identification of touching kernels and dockage components in digital images, Canadian Biosystems Engineering. Vol. 48 (2006), p.7. 1-7. 7.

[8] X. M. Chen, G. Q. Guo, M. Q. Liu, On infrared image segmentation algorithm based on watershed, Journal of Optoelectronics. Laser. Vol. 112 (10) (2001), pp.1072-1075.

[9] L. Vincent, P. Soille: Watersheds in digital spaces: an efficient algorithm based on immersion simulations, IEEE Transactions on Pattern Analysis and Machine Intelligence. Vol. 13 (6) (1991), pp.583-589.

DOI: 10.1109/34.87344

[10] S. Beucher, Watershed, hierarchical segmentation and waterfall algorithm, In: J. Serra, P. Soille (Eds. ), Mathematical. Morphology and Its Applications to Image Processing, Kluwer. Academic Publishers, Netherlands, 1994, pp.171-203.

DOI: 10.1007/978-94-011-1040-2_10

[11] V. Grau, A. U. J. Mewes, M. Alcaniz, Improved watershed transform for medical image segmentation using prior information, IEEE transactions on medical imaging. Vol. 23 (4) (2004), pp.447-458.

DOI: 10.1109/tmi.2004.824224

[12] F. J. Kuang, W. H. Xu, Y. H. Wang: Research on broken rice rate detection using region labeling, Computer Engineering and Applications. Vol. 46 (12) (2010), pp.204-206.

[13] D. Y. Huang, C. H. Wang: Optimal multi-level thresholding using a two-stage Otsu optimization approach, Pattern Recognition Letters. Vol. 30 (2009), pp.275-284.

DOI: 10.1016/j.patrec.2008.10.003