Leaf Image Recognition Using Fourier Transform Based on Ordered Sequence
There are a number of leaf recognition methods, but most of them are based on Euclidean space. In this paper, we will introduce a new description of feature for the leaf image recognition, which represents the leaf contour with the ordered sequence. For a leaf image, points on the contour represent the most important information of the leaf. Thus, by extracting serial points of the leaf contour, the unique corresponding ordered sequence can be obtained for a contour. Then, we can compute the amplitude-frequency feature by performing the Discrete Fourier transform on the ordered sequence. Since the low-frequency part of the Fourier transform represents the global information and the high-frequency part the local details, we can adopt the amplitude-frequency feature for leaf image recognition. Experimental results on the famous Swedish library and ICL library show that the proposed feature is effective for leaf image recognition.
Keywordsleaf recognition Fourier transform ordered sequence amplitude-frequency
Unable to display preview. Download preview PDF.
- 3.Leslie, E.: Auxin Is Required for Leaf Vein Pattern in Arabidopsis. American Society of Plant Biologists 121(4), 1179–1190 (1999)Google Scholar
- 6.Bhanu, B., Olivier, D.: Shape Matching of Two-Dimensional Objects. IEEE Trans. on Pattern Analysis and Machine Intelligence 6(2) (March 1984)Google Scholar
- 7.Soontom, O., Chen, Y.J.: Integer Fast Fourier Transform. IEEE Transaction on Signal Processing 50(3) (March 2002)Google Scholar
- 8.Krishna, S., Indra, G., Sangeeta, G.: SVM-BDT PNN and Fourier Moment Technique for Classification of Leaf Shape. International Journal of Signal Processing, Image Processing and Pattern Recognition 3(4) (December 2010)Google Scholar
- 9.Bao, P., Zhang, L., Wu, X.L.: Canny Edge Detection Enhancement by Scale Multiplication. IEEE Trans. on Pattern Analysis and Machine Intelligence 27(9) (2005)Google Scholar
- 10.Li, X., Shen, J.: Group Direction Difference Chain Codes for the Representation of the Border. In: Digital and Optical Shape Representation and Pattern Recognition, Orlando, FL, pp. 372–376. SPIE, Bellingham (1988)Google Scholar
- 11.Rafael, C.G., Richard, E.W.: Digital Image Processing. Prentice HallGoogle Scholar
- 12.Milan, S., Vaclav, H., Roger, B.: Image Processing Analysis and Machine Vision. Thomson Learning (2008)Google Scholar
- 13.ICL Plant Leaf Images Dataset, http://www.intelengine.cn/English/dataset