Two Dimensional Pattern Recognition Using Spectrum Analysis And Backpropagation


The Transactions of the Korea Information Processing Society (1994 ~ 2000), Vol. 5, No. 2, pp. 342-350, Feb. 1998
10.3745/KIPSTE.1998.5.2.342,   PDF Download:

Abstract

This paper proposes a method for pattern recognition using spectrum analyzer and Backpropagation. Contour sequences obtained from 2-D images represent the Euclidean distance between the centroid and all boundary pixels of the shape, and are related to the overall shape of images. The Fast Fourier transform of contour sequence and spectrum analyzer are used as a means of feature selection and data reduction. The there dimensional spectral feature vectors are extracted by spectrum anayzer from the energy spectrum. These Spectral feature vectors are invariant to shape translation, rotation, and scale transformations The Backpropagation neural network which is combined with one hidden layer module is trained and tested with these spectral feature vectors. The experiments including 4 automobiles recognition process are presented to illustrate the high performance of this proposed method in the recognition problems of noisy shapes.


Statistics
Show / Hide Statistics

Statistics (Cumulative Counts from September 1st, 2017)
Multiple requests among the same browser session are counted as one view.
If you mouse over a chart, the values of data points will be shown.


Cite this article
[IEEE Style]
C. S. Yoon and K. S. Nak, "Two Dimensional Pattern Recognition Using Spectrum Analysis And Backpropagation," The Transactions of the Korea Information Processing Society (1994 ~ 2000), vol. 5, no. 2, pp. 342-350, 1998. DOI: 10.3745/KIPSTE.1998.5.2.342.

[ACM Style]
Cha Seung Yoon and Kim Sung Nak. 1998. Two Dimensional Pattern Recognition Using Spectrum Analysis And Backpropagation. The Transactions of the Korea Information Processing Society (1994 ~ 2000), 5, 2, (1998), 342-350. DOI: 10.3745/KIPSTE.1998.5.2.342.