International Conference on Computer Technology and Development, 3rd (ICCTD 2011)
257 Rotation Invariant Texture Classification Based on Support Vector Machine and Wavelet Transform
Download citation file:
A novel rotation invariant texture classification method based on wavelet transform and support vector machine is proposed. First the wavelet transform is adopted to do feature extraction and then classifier is designed with the SVM. Traditional texture classification method based the SVM usually uses the bitmap representation as the input; compared to this method, our strategy can improve the performance of classification, especially in the rotational case. Experimental results proved the effectiveness and efficiency of our method.