Hierarchical cluster analysis of tobacco leaves from different areas based on fractal color

被引：0
|
作者：
Wei C. [1 ]
Zhang Y. [2 ]
Song Y. [1 ]
Li F. [1 ]
Xue C. [1 ]
Cai X. [1 ]
机构：
[1] Zhengzhou Tobacco Research Institute of CNTC
[2] National Engineering Research Center for Information Technology in Agriculture
来源：
Nongye Jixie Xuebao/Transactions of the Chinese Society of Agricultural Machinery | 2010年 / 41卷 / 08期
关键词：
Box-counting dimension; Color; Fractal; Hierarchical cluster analysis; Tobacco leaf;
D O I：
10.3969/j.issn.1000-1298.2010.08.037
中图分类号：
学科分类号：
摘要：
High definition digital images of tobacco leaves were obtained, which were made on removing the background and segmentation processing. All the components of tobacco leaf color, such as red, green, blue and luminance, were calculated, as new indexes quantitatively described the color distribution state of tobacco leaf surface. The box-counting dimension variation curve of every color component was plotted. A hierarchical cluster analysis was performed on tobacco leaf color with fractal dimension as parameter. The results showed that there was obvious difference in the box-counting dimension variation curve of every color component of tobacco leaves from different growing areas. Cluster analysis with fractal dimension as parameter was very well consistent with tobacco grade experts. These results indicated color fractal dimension, as characteristic index of color classification, could more accurately describe the fractal distributed features of image color.
引用
收藏
页码：178 / 183
页数：5
相关论文
共 20 条
  • [1] Zhang J., Wu S., Fang R., Et al., Computer aided quality inspecting and grading for agricultural products (2nd half) - construction and training of grading model for tobacco leaf, Transactions of the Chinese Society of Agricultural Engineering, 13, 4, pp. 179-183, (1997)
  • [2] Zhang H., Han L., Duan Z., Tobacco grading based on image features, Geomatics and Information Science of Wuhan University, 28, 3, pp. 359-362, (2003)
  • [3] Yan R., The computer-aided classification system of flue-cured tobacco, (2001)
  • [4] Li H., The research on auto-grouping model of flue-cured tobacco leaves based on digital image processing, (2007)
  • [5] Tan X., Tang Y., Chen Y., Intelligent grading of flue-cured tobacco leaves based on rough set theory, Transactions of the Chinese Society for Agricultural Machinery, 40, 6, pp. 169-174, (2009)
  • [6] Zhang F., Fang R., Cai J., Image retrieval of standard tobacco leaf database, Transactions of the Chinese Society for Agricultural Machinery, 32, 1, pp. 66-68, (2001)
  • [7] Liu H., He L., Ma W., Et al., Color features of transmittance images applied in the classification of tobacco leaves, Transactions of the Chinese Society of Agricultural Engineering, 23, 9, pp. 169-171, (2007)
  • [8] Liang W., Extraction the basicfeatures of the tobacco image application with MATLAB, (2003)
  • [9] Mandelbrot B.B., The Fractal Geometry of Nature, (1983)
  • [10] Liu J., Furuno T., The fractal estimation of wood color variation by the triangular prism surface area method, Wood Science and Technology, 36, 5, pp. 385-397, (2002)
12