Face Recognition using Local Quantized Patterns

Abstract

This paper proposes a novel face representation based on Local Quantized Patterns (LQP). LQP is a generalization of local pattern features that makes use of vector quantization and lookup table to let local pattern features have many more pixels and/or quantization levels without sacrificing simplicity and computational efficiency. Our new LQP face representation not only outperforms any other representation on challenging face datasets but performs equally well in the intensity space and orientation space (obtained by applying gradient or Gabor Filters) and hence is intrinsically robust to illumination variations. Extensive experiments on two challenging face recognition datasets (FERET [14] and LFW [7]) show that this representation gives state-of-the-art performance (improving the earlier state-of-the-art by around 3%) without requiring neither a metric learning stage nor a costly labelled training dataset, having the comparison of two faces being made by simply computing the Cosine similarity between their LQP representations in a projected space.

Some Faces are More Equal than Others: Hierarchical Organization for Accurate and Efficient Large-Scale Identity-Based Face Retrieval

“…Locally computed features like Local Binary Patterns (LBP), Local Ternary Patterns (LTP) and Local quantized patterns (LQP) have been quite successful to address these kinds of problems [13,2,14]. One of the recent state-of-art methods [15] on Labeled Faces in the Wild (LFW) [16], the most challenging face verfication dataset, computes very high dimensional LBP (of dimension as high as 100k).…”

Face Recognition Using Local Quantized Patterns and Gabor Filters

“…In this paper perspective approach described in (Hussain, Triggs, 2012;Hussain, Napoléon, Jurie, 2012) is offered to solve many of the above mentioned problems of local Photogrammetric techniques for video surveillance, biometrics and biomedicine, 25-27 May 2015, Moscow, Russia patterns. To maintain the speed and simplicity of local pattern features and to make the process of vector quantization fast, local quantized patterns (LQP) are used.…”

Local binary pattern network: a deep learning approach for face recognition

“…Results And Analysis LBPNet still outperforms most of them; ii) some competitive methods (i.e., [24,50,52]) extract descriptors from the Gabor images ( extracted by Gabor filters from the intensity images) , which may bring advantages comparing with the regular descriptors. [54] 0.7547 GJD-BC-100 [54] 0.7392 LARK [55] 0.7830 MRF-MLBP [56] 0.8994 LFW-a + MRF Pose Adaptive Filter [57] 0.9405 PAF(3D alignment) Spartans [58] 0.9428 3D Generic Elastic Model LBPNet 0.9404 LFW-a…”

“…Such impact of high variability can be reduced by downweighting the high variance directions whereas increasing the weak ones, since the discriminative information are uniformly distributed over all directions of the data [24]. Here, we normalize all the eigenvectors by whitening, the transformation matrix is then expressed as…”

“…Therefore, techniques of dimensionality reduction are highly desired. It is a critical step in many stateof-the-art methods [22,23,24,25,26]. Linear subspace projection, as one of the widely used techniques, is introduced in 2.2…”