Paper cut-out patterns recognition based on wavelet transform and SVD
Fangyuan Qin · Jisuanji gongcheng yu sheji · 2010
Aiming at the problems of the traditional paper cut-out art for computer creation,after analyzing the characteristics of paper cut-out art,a method of paper cut-out patterns recognition based on wavelet transform and singular value decomposition is proposed.The paper cut-out image normalized and binaryzation are discomposed in low frequency component by tow-dimension discrete wavelet,then distilled the singular value from low frequency component,after reducing dimension processing and making unitary dealing the characteristic vector of the image is obtained.The eigenvector is applied to nearest neighbor classifier to recognition.Experiments show that this method are efftive in diminishing the disturbing of the noise and recognizing paper cut-cut patterns of exaggerative deformations.