基于DWFMT非变异特征的指纹鉴别技术

为提高指纹鉴别率，提出了一种基于DWFMT变换提取特征进行指纹鉴别的新方法。采用离散小波变换进行小波分解指纹图像后对局部边缘进行平滑，从而减少指纹图像关于形状扭曲的敏感性，而Fourier-Mellin变换产生平移、旋转和伸缩的非变异特征．利用Fourier-Mellin变换的线性性质，使众多的DWFMT特征形成非变异的参考特征以减少输入指纹图像的变化．实验结果表明，其指纹鉴别率达到96％以上，当众多DWFMT特征被使用时，鉴别率可达到99％．

Fingerprint Identification Based on DWFMT Invariant Features

A novel method of fingerprint identification based on the features extracted from the integrated discrete wavelet and the Fourier-Mellin transform(DWFMT) was proposed.Discrete Wavelet transform was used to smooth and preserve the local edges after image decomposition,making the fingerprint images less sensitive to shape distortion whilst Fourier-Mellin transform served to produce a translation,rotation and scale invariant feature.Multiple DWFMT features could be used to form a reference invariant feature through the linearity property of Fourier-Mellin Transform and hence reduce the variability of the input fingerprint images.The experiments showed the identification accuracy reached over 96% and 99% of identification rate was achieved when multiple DWFMT features were used.