一种新颖的低分辨率条件下的掌纹识别方法

Palmprint recognition method under low resolution

掌纹识别是利用人的手掌图像进行身份鉴别的一种新兴生物特征识别技术。当今的掌纹识别方法存在的比较困难的问题之一就是在特征提取时受一些客观因素制约,影响后面的匹配精度。为此,提出一种改进的基于相位相关的掌纹图像匹配算法。该算法不受光照、平移的影响,对噪声也有很好的鲁棒性。在此基础上实验了该算法在不同分辨率下的表现,发现当分辨率降为原图像的十六分之一时,该算法仍然能取得较高的识别率,证明了该算法在较低分辨率下的有效性。

Palmprint identification is a new identification method of physiological biometrics by using palmprint image. Today one of the difficult problems in palmprint identification is that the matching performance is significantly influenced by many parameters in feature extraction process, which may vary depending on environmental factors. This paper gave a recognition algorithm using improved phase-based correlation image matching. The proposed algorithm was not influenced by brightness and shift, and highly robust against the noise. Based on these points, conducted a series of experiments on different resolutions to get the matching performance. Results show that when the resolution descended to sixteenth of the original, the proposed algo- rithm got high recognition rate all the same. It proves that the proposed algorithm exhibits efficient identification performance at lower resolutions.