Multi-Directional Multi-Level Dual-Cross Patterns for Robust Face Recognition
arXiv:1401.5311 · doi:10.1109/TPAMI.2015.2462338
Abstract
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 MDMLDCPs 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.
accepted version to IEEE TPAMI
References in corpus (2)
Cited by in corpus (21)
- Robust Face Recognition via Multimodal Deep Face Representation
- Trunk-Branch Ensemble Convolutional Neural Networks for Video-based Face Recognition
- Video-based Facial Micro-Expression Analysis: A Survey of Datasets, Features and Algorithms
- Recent Advances in Deep Learning Techniques for Face Recognition
- Personalized Age Progression with Bi-level Aging Dictionary Learning
- Multi-Fold Gabor, PCA and ICA Filter Convolution Descriptor for Face Recognition
- Local Directional Relation Pattern for Unconstrained and Robust Face Retrieval
- A Comprehensive Survey on Pose-Invariant Face Recognition
- LDOP: Local Directional Order Pattern for Robust Face Retrieval
- SCE: A manifold regularized set-covering method for data partitioning
- FacePoseNet: Making a Case for Landmark-Free Face Alignment
- Frankenstein: Learning Deep Face Representations using Small Data
- On a method for Rock Classification using Textural Features and Genetic Optimization
- KinePose: A temporally optimized inverse kinematics technique for 6DOF human pose estimation with biomechanical constraints
- Multi-Feature Fusion-based Scene Classification Framework for HSR Images
- Extended Local Binary Patterns for Efficient and Robust Spontaneous Facial Micro-Expression Recognition
- LGLG-WPCA: An Effective Texture-based Method for Face Recognition
- FusiformNet: Extracting Discriminative Facial Features on Different Levels
- Coupled Learning for Facial Deblur
- Learning Robust 3D Face Reconstruction and Discriminative Identity Representation
- Fusion of Complex Networks-based Global and Local Features for Texture Classification