Phase-based image matching and its application to biometric recognition
Phase-based image matching and its application to biometric recognition
复制标题
DOI：
10.1109/apsipa.2013.6694297
复制
发表时间：
2013-10
期刊：
影响因子：
--
通讯作者：
Koichi Ito;T. Aoki
中科院分区：
文献类型：
--
作者：
Koichi Ito;T. Aoki
本文提出了一种利用图像离散傅里叶变换获得相位信息的精确图像匹配技术及其在生物特征识别中的应用。生物特征识别算法大多采用计算机视觉、模式识别和图像处理技术或它们的结合。另一方面，我们的方法使用基于相位的图像匹配是基于信号处理技术。通过对指纹、虹膜、人脸、掌纹和指关节的识别实验，验证了该方法的有效性。
This paper presents an accurate image matching technique using phase information obtained by discrete Fourier transform of images and its application to biometric recognition. Most of biometric recognition algorithms employ computer vision, pattern recognition and image processing techniques or their combination. On the other hand, our approach using phase-based image matching is based on signal processing technique. Through a set of experiments for fingerprint, iris, face, palmprint and finger knuckle recognition, we demonstrate that our signal processing approach exhibits efficient performance for biometric recognition compared with the conventional approaches.