Multi-Directional Multi-Level Dual-Cross Patterns for Robust Face Recognition

By Changxing Ding, Jonghyun Choi, Dacheng Tao, Larry S. Davis. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2014

360 citations recorded by the source corpus.

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.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/82e4a7fc616c0147bc60a9cef5a99170fdc0d2a1

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

From BoW to CNN: Two Decades of Texture Representation for Texture Classification (2018, background): “Recently, although CNN based methods are beginning to dominate, LBP research remains active, as evidenced by signiﬁcant recent work [77, 219, 202, 116, 136, 251, 259, 49].”
Frankenstein: Learning Deep Face Representations Using Small Data (2016, neutral): “36 MDML-DCPs [8] 95 .”
Trunk-Branch Ensemble Convolutional Neural Networks for Video-Based Face Recognition (2016, background): “Xiv:1607.05427v2 [cs.CV] 17 May 2017 IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, VOL.X, NO.X, MONTH 2017 2 Model fusion is then performed ofﬂine at the feature [11] or score level [12]. However, the accuracy promoted by model ensembles is at the cost of signiﬁcantly increased tim”
Robust Face Recognition via Multimodal Deep Face Representation (2015, methodology): “Conventional face representations are built on local descriptors, e . g ., Local Binary Patterns (LBP) [3], Local Phase Quantization (LPQ) [4], [5], Dual-Cross Patterns (DCP) [6], and Binarised Statistical Image Features (BSIF) [7].”
Video-Based Facial Micro-Expression Analysis: A Survey of Datasets, Features and Algorithms (2021, methodology): “Ben et al. [42] proposed hot wheel patterns (HWP), HWP-TOP, and dual-cross patterns from three orthogonal planes (DCP-TOP) based on DCP [43].”