Multi-Directional Multi-Level Dual-Cross Patterns for Robust Face Recognition
Multi-Directional Multi-Level Dual-Cross Patterns for Robust Face Recognition
复制标题
用于可靠人脸识别的多方位多层次双交叉模式
DOI：
10.1109/tpami.2015.2462338
复制
发表时间：
2016-03-01
影响因子：
23.6
通讯作者：
Davis, Larry S.
中科院分区：
文献类型：
--
作者：
Ding, Changxing;Choi, Jonghyun;Davis, Larry S.
为了实现对光照、姿态和表情变化具有鲁棒性的无约束人脸识别，提出了一种从人脸图像中提取“多方向多级双交叉模式”（MDML-DCP）的新方法。具体而言，MDML-DCP方案利用高斯算子的一阶导数来减少光照差异的影响，然后在整体和组件级别上计算DCP特征。DCP是一种新颖的人脸图像描述符，它的灵感来自于人脸独特的纹理结构。它在计算上是高效的，并且仅使计算局部二进制模式的成本加倍，但对姿势和表情变化非常鲁棒。MDML-DCP全面而有效地将人脸图像的不变特征从多个级别编码成模式，该模式对人与人之间的差异具有高度区分性，但对人与人之间的变化具有鲁棒性。在FERET、CAS-PERL-R1、FRGC 2.0和LFW数据库上的实验结果表明DCP优于现有技术的本地描述符（例如，LBP、LTP、LPQ、POEM、tLBP和LGXP），用于人脸识别和人脸验证任务。更令人印象深刻的是，通过在一个简单的识别方案中部署MDML-DCP，在具有挑战性的LFW和FRGC 2.0数据库上实现了最佳性能。
To perform unconstrained face recognition robust to variations in illumination, pose and expression, this paper presents a new scheme to extract "Multi-Directional Multi-Level Dual-Cross Patterns" (MDML-DCPs) from face images. Specifically, the MDML-DCPs scheme exploits the first derivative of Gaussian operator to reduce the impact of differences in illumination and then computes the DCP feature at both the holistic and component levels. DCP is a novel face image descriptor inspired by the unique textural structure of human faces. It is computationally efficient and only doubles the cost of computing local binary patterns, yet is extremely robust to pose and expression variations. MDML-DCPs comprehensively yet efficiently encodes the invariant characteristics of a face image from multiple levels into patterns that are highly discriminative of inter-personal differences but robust to intra-personal variations. Experimental results on the FERET, CAS-PERL-R1, FRGC 2.0, and LFW databases indicate that DCP outperforms the state-of-the-art local descriptors (e.g., LBP, LTP, LPQ, POEM, tLBP, and LGXP) for both face identification and face verification tasks. More impressively, the best performance is achieved on the challenging LFW and FRGC 2.0 databases by deploying MDML-DCPs in a simple recognition scheme.