Leaf image segmentation method based on multifractal detrended fluctuation analysis

To identify singular regions of crop leaf affected by diseases, based on multifractal detrended fluctuation analysis (MF-DFA), an image segmentation method is proposed. In the proposed method, first, we defend a new texture descriptor: local generalized Hurst exponent, recorded as LHq based on MF-DF...

Full description

Saved in:
Bibliographic Details
Published inJournal of applied physics Vol. 114; no. 21
Main Authors Wang, Fang, Li, Jin-Wei, Shi, Wen, Liao, Gui-Ping
Format Journal Article
LanguageEnglish
Published Melville American Institute of Physics 07.12.2013
Subjects
Applied physics
Clustering
Corn
Fractals
Image segmentation
Variation
Online AccessGet full text

Cover

More Information
Summary:To identify singular regions of crop leaf affected by diseases, based on multifractal detrended fluctuation analysis (MF-DFA), an image segmentation method is proposed. In the proposed method, first, we defend a new texture descriptor: local generalized Hurst exponent, recorded as LHq based on MF-DFA. And then, box-counting dimension f(LHq) is calculated for sub-images constituted by the LHq of some pixels, which come from a specific region. Consequently, series of f(LHq) of the different regions can be obtained. Finally, the singular regions are segmented according to the corresponding f(LHq). Six kinds of corn diseases leaf's images are tested in our experiments. Both the proposed method and other two segmentation methods—multifractal spectrum based and fuzzy C-means clustering have been compared in the experiments. The comparison results demonstrate that the proposed method can recognize the lesion regions more effectively and provide more robust segmentations.
ISSN:0021-8979
1089-7550
DOI:10.1063/1.4839815