Kun Zhang, Min-Rui Fei and Hui-Yu Zhou. Using Entropy Based Mean Shift Filter and Modified Watershed Transform for Grain Segmentation. International Journal of Automation and Computing, vol. 12, no. 2, pp. 199-207, 2015. https://doi.org/10.1007/s11633-014-0841-2
Citation: Kun Zhang, Min-Rui Fei and Hui-Yu Zhou. Using Entropy Based Mean Shift Filter and Modified Watershed Transform for Grain Segmentation. International Journal of Automation and Computing, vol. 12, no. 2, pp. 199-207, 2015. https://doi.org/10.1007/s11633-014-0841-2

Using Entropy Based Mean Shift Filter and Modified Watershed Transform for Grain Segmentation

doi: 10.1007/s11633-014-0841-2
Funds:

This work was supported by National Key Scientific Apparatus De-velopment of Special Item of China (No. 2012YQ15008703), Nantong Research Program of Application Foundation (No. BK2012030), and Key Project of Science and Technology Commission of Shanghai Mu-nicipality (No. 14JC1402200).

  • Received Date: 2013-09-29
  • Rev Recd Date: 2014-04-02
  • Publish Date: 2015-04-01
  • Life science research aims to continuously improve the quality and standard of human life. One of the major challenges in this area is to maintain food safety and security. A number of image processing techniques have been used to investigate the quality of food products. In this paper, we propose a new algorithm to effectively segment connected grains so that each of them can be inspected in a later processing stage. One family of the existing segmentation methods is based on the idea of watersheding, and it has shown promising results in practice. However, due to the over-segmentation issue, this technique has experienced poor performance in various applications, such as inhomogeneous background and connected targets. To solve this problem, we present a combination of two classical techniques to handle this issue. In the first step, a mean shift filter is used to eliminate the inhomogeneous background, where entropy is used to be a converging criterion. Secondly, a color gradient algorithm is used in order to detect the most significant edges, and a marked watershed transform is applied to segment cluttered objects out of the previous processing stages. The proposed framework is capable of compromising among execution time, usability, efficiency and segmentation outcome in analyzing ring die pellets. The experimental results demonstrate that the proposed approach is effectiveness and robust.

     

  • loading
  • [1]
    S. R. Delwiche, I. C. Yang, R. A. Graybosch. Multiple view image analysis of freefalling U.S. wheat grains for dam-age assessment. Computers and Electronics in Agriculture, vol. 98, pp. 62-73, 2013.
    [2]
    Y. N. Wan. Kernel handling performance of an automatic grain quality inspection system. Transaction of the Ameri-can Society of Agriculture and Biological Engineers, vol. 45, no. 2, PP. 369-377, 2002.
    [3]
    Y. Yoshioka, H. Iwata, M. Tabata, S. Ninomiya, R. Ohsawa. Chalkiness in rice: Potential for evaluation with image anal-ysis. Crop Science, vol. 47, no. 5, pp. 2113-2020, 2007.
    [4]
    H. Gao, S. Kwong, J. J. Yang, J. J. Cao. Particle swarm op-timization based on intermediate disturbance strategy algo-rithm and its application in multi-threshold image segmen-tation. Information Sciences, vol. 250, pp. 82-112, 2013.
    [5]
    A. R. Kavitha, C. Chellamuthu. Detection of brain tumour from MRI image using modified region growing and neu-ral network. The Imaging Science Journal, vol. 61, no. 7, pp. 556-567, 2013.
    [6]
    Y. Xiang, J. F. He, L. Ma, S. L. Yi, J. P. Xu. A segmenta-tion method for multiple sclerosis white matter lesions on conventional magnetic resonance imaging based on kernel fuzzy clustering. Applied Mechanics and Materials, vol. 339, pp. 361-365, 2013.
    [7]
    H. Y. Zhou, G. Schaefer, A. H. Sadka, M. E. Celebi. Anisotropic mean shift based fuzzy C-means segmentation of dermoscopy images. IEEE Journal of Selected Topics in Signal Processing, vol. 30, no. 1, pp. 26-34, 2009.
    [8]
    P. Shatadal, D. S. Jayas, N. R. Bulley. Digital image anal-ysis for software separation and classification of touching Grains: II. Classification. Transactions of the American So-ciety of Agriculture and Biological Engineers, vol. 38, no. 2, pp. 645-649, 1995.
    [9]
    N. S. Shashidhar, D. S. Jayas, T. G. Crowe, N. R. Bulley. Processing of digital images of touching kernels by ellipse fitting. Canadian Agricultural Engineering, vol. 39, no. 2, pp. 39-142, 1997.
    [10]
    E. H. Van den Berg, A. G. C. A. Meesters, J. A. M. Kenter, W. Schlager. Automated separation of touching grains in digital images of thin sections. Computers and Geosciences, vol. 28, no. 2, pp. 179-190, 2002.
    [11]
    S. Q. Yang, D. J. He. Automated identification and sepa-ration of touching rice grains with machine vision. Journal of Agricultural Mechanization Research, no. 3, pp. 62-65, 2005. (in Chinese)
    [12]
    L. Yang, O. Tuzel, P. Meer, D. J. Foran. Automatic image analysis of histopathology specimens using concave vertex graph. Medical Image Computing and Computer-Assisted Intervention, vol. 5241, pp. 833-841, 2008.
    [13]
    L. Gao, S. Y. Yang, J. Xia, S. J Wang, J. L. Liang, H. Q. Li. New marker-based watershed algorithm. Acta Electronica Sinica, vol. 11, no. 34, pp. 2018-2023, 2006. (in Chinese)
    [14]
    H. D. Cheng, X. H. Jiang, Y. Sun. Color image segmenta-tion: Advances and prospects. Pattern Recognition, vol. 34, no. 12, pp. 2259-2281, 2001.
    [15]
    C. Vincent. Watersheds in digital spaces: An efficient algo-rithm based on immersion simulation. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 13, no. 6, pp. 583-598, 1991.
    [16]
    E. Bengtsson, C. Wahlby, J. Lindblad. Robust cell im-age segmentation methods. Pattern Recognition and Image Analysis, vol. 14, no. 2, pp. 157-167, 2004.
    [17]
    F. Meyer, S. Beucher. Morphological segmentation. Journal of Visual Communication and Image Representation, vol. 1, no. 1, pp. 21-46, 1990.
    [18]
    P. He, K. L. Fang, X. H. Liu. Improved watershed algorithm based on morphology and distance transform. Applied Me-chanics and Materials, vol. 333-335, pp. 1071-1075, 2013.
    [19]
    F. Meyer. Topographic distance and watershed lines. Signal Processing, vol. 38, no. 1, pp. 113-125, 1994.
    [20]
    J. Roerdink, A. Meijster. The watershed transform: Defini-tions, algorithms and parallelization strategies. Mathemat-ical Morphology, vol. 41, no. 1-2, pp. 187-228, 2000.
    [21]
    Y. Aliyari Ghassabeh, T. Linder, G. Takahara. On some convergence properties of the subspace constrained mean shift. Pattern Recognition, vol. 46, no. 11, pp. 3140-3147, 2013.
    [22]
    R. C. Gonzalez, R. E. Woods. Digital Image Processing, 2nd ed. Electronics Industry House Publisher, pp. 172-178, 2007.
    [23]
    P. K. Parlewar, K. M. Bhurchandi. A 4-quadrant curvelet transform for denoising digital images. International Jour-nal of Automation and Computing, vol. 10, no. 3, pp. 217-226, 2013.
    [24]
    M. S. Pan, J. T. Tang, X. L. Yang. An adaptive median filter algorithm based on B-spline function. International Journal of Automation and Computing, vol. 8, no. 1, pp. 92-99, 2011.
    [25]
    F. Liu, X. Liu, B. Zhang, J. Bai. Extraction of target fluo-rescence signal from in vivo background signal using image subtraction algorithm. International Journal of Automation and Computing, vol. 9, no. 3, pp. 232-236, 2012.
    [26]
    P. E. Trahanias, A. N. Venetsanopoulos. Color edge detec-tion using vector order statistics. Color Edge Detection Us-ing Vector Order Statistics, vol. 2, no. 2, pp. 259-264, 1993.
  • 加载中

Catalog

    通讯作者: 陈斌, bchen63@163.com
    • 1. 

      沈阳化工大学材料科学与工程学院 沈阳 110142

    1. 本站搜索
    2. 百度学术搜索
    3. 万方数据库搜索
    4. CNKI搜索

    用微信扫码二维码

    分享至好友和朋友圈

    Article Metrics

    Article views (5120) PDF downloads(1118) Cited by()
    Proportional views
    Related

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return