基于Gabor小波的新人脸识别算法研究.docVIP

  基于 Gabor 小波的新人脸识别算法研究# 何良华* （同济大学电子与信息工程学院计算机科学与技术系，上海 201804） 5 10 摘要：局部二元模式（Local Binary Patterns, LBP）特征和 Gabor 小波特征因其充分考虑基准 点像素周围灰度统计特性而对片状光照变化、旋转等具有较强的鲁棒性。但是，由于特征获 取的复杂性和高维性使得算法的应用平台较高。因此，本文将两种算法相结合，提出了一种 二元 Gabor 特征的提取算法，在各种 Gabor 特征图像之间进行局部二元模式计算，计算量和 特征维数降低了很多。新的特征因同时具备局部纹理和片状灰度变化信息而对光照、旋转更 加鲁棒。实验结果表明：和 LBP、Gabor 小波以及独立分量等特征相比，本文提出的特征具 有一定的优势，尤其在条件较差的情况下优势更加明显。 关键词：模式识别，Gabor 小波；局部二元模式；人脸识别 中图分类号：TP391.4 15 A New Gabor Method for Face Recognition He Lianghua (Department of Computer Science, School of Electronics and Information, Tongji University, Shanghai 201804) 20 25 30 35 40 Abstract: Because of containing enough texture information around base point, Local Binary Pattern features and Gabor features shows excellent performance under batch light varying and rotation. However, the complicated calculation and feature’s high dimension are the biggest restriction in application. Therefore, in this paper we proposed a novel method called Binary Gabor Codes based on above two methods. The key idea is calculating local binary patterns on the corresponding Gabor Magnitude Pictures (GMPs), the calculation and dimension are both decreased. Because of containing both information of local texture and block gray varying, BGC features are more overwhelming comparing with Local Binary Patterns (LBP), Gabor jets and independent component features. What’s more, Experimental results show that it has improved the recognition rate greatly, especially in bad condition. Key words: Pattern Recognition, Gabor Jets; Local Binary Patterns; Face recognition; 0 Introduction There are many challenges in automatic face recognition, such as illumination, pose and facial expression etc. Lots of methods have been proposed to get robust features in such bad conditions. The most generalized used are Gabor Wavelet (GW) [1-3] and LBP [4-5]. GW method extracts features from local information around the base point, so they contain much local block texture information. LBP method come