The application of relative moment and wavelet moment in target obstacle recognition

For the shockproof hammers, spacers and suspension clamps and other obstacles on 500kv high-voltage transmission lines, this article constructs the relative moment and wavelet moment of the image, and based on that, using the support vector machine (SVM) to recognize and classify these three species. Experimental results show that these two features moment can both be used to classify the target, but comparatively speaking, wavelet moment has better classification accuracy and convergence rate.

[1]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[2]  Nello Cristianini,et al.  Large Margin DAGs for Multiclass Classification , 1999, NIPS.

[3]  Ming-Kuei Hu,et al.  Visual pattern recognition by moment invariants , 1962, IRE Trans. Inf. Theory.

[4]  Gérard Dreyfus,et al.  Single-layer learning revisited: a stepwise procedure for building and training a neural network , 1989, NATO Neurocomputing.

[5]  Michael Unser,et al.  On the asymptotic convergence of B-spline wavelets to Gabor functions , 1992, IEEE Trans. Inf. Theory.

[6]  Isabelle Guyon,et al.  Comparison of classifier methods: a case study in handwritten digit recognition , 1994, Proceedings of the 12th IAPR International Conference on Pattern Recognition, Vol. 3 - Conference C: Signal Processing (Cat. No.94CH3440-5).

[7]  N. Otsu.  A threshold selection method from gray level histograms , 1979 .

[8]  Chaur-Chin Chen.  Improved moment invariants for shape discrimination , 1993, Pattern Recognit..

[9]  刘伟军,et al.  United moment invariants for shape discrimination , 2003 .

[10]  Liu Weijun,et al.  United moment invariants for shape discrimination , 2003, IEEE International Conference on Robotics, Intelligent Systems and Signal Processing, 2003. Proceedings. 2003.

[11]  Jia Zhi-yong.  A study of license plate character recognition based on wavelet moment , 2005 .