Face Verification Using the LARK Representation

Seo, Hae Jong; Milanfar, Peyman

doi:10.1109/tifs.2011.2159205

Cited by 140 publications

(62 citation statements)

References 41 publications

(67 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This is the approach of Kumar et al [18] and Wolf et al [33], who detect a small number of parts with a commercial system and then apply an affine transformation to bring the parts close to fixed locations. The aligned LFW images from [33] have been released as the LFW-a dataset, which has subsequently been used by many authors [14,23,25,28,29,35], but we desire an alignment that gives tighter correspondence between the faces.…”

Section: Related Workmentioning

confidence: 99%

Tom-vs-Pete Classifiers and Identity-Preserving Alignment for Face Verification

Berg¹,

Belhumeur²

2012

Procedings of the British Machine Vision Conference 2012

124

128

View full text Add to dashboard Cite

We propose a method of face verification that takes advantage of a reference set of faces, disjoint by identity from the test faces, labeled with identity and face part locations. The reference set is used in two ways. First, we use it to perform an "identity-preserving" alignment, warping the faces in a way that reduces differences due to pose and expression but preserves differences that indicate identity. Second, using the aligned faces, we learn a large set of identity classifiers, each trained on images of just two people. We call these "Tom-vs-Pete" classifiers to stress their binary nature. We assemble a collection of these classifiers able to discriminate among a wide variety of subjects and use their outputs as features in a same-or-different classifier on face pairs. We evaluate our method on the Labeled Faces in the Wild benchmark, achieving an accuracy of 93.10%, significantly improving on the published state of the art.

show abstract

Section: Related Workmentioning

confidence: 99%

Tom-vs-Pete Classifiers and Identity-Preserving Alignment for Face Verification

Berg¹,

Belhumeur²

2012

Procedings of the British Machine Vision Conference 2012

124

128

View full text Add to dashboard Cite

show abstract

“…rows 9 and 7. However, when used in conjunction with Cosine Methods Accuracy (%)±S E UnSupervised 1 SD-MATCHES [17] 64.1±0.62 2 GJD-BC-100 [17] 68.5±0.65 3 H-XS-40 [17] 69.5±0.48 4 LARK [18] 72.2±0.49 5 POEM [24] 75 [18] 85.1± 0.59 16 LBP + CSML [11] 85.3± 0.52 17 DML-eig combined [26] 85.7± 0.56 18 Combined b/g [25] 86 Table 2: Comparative results of our methods with (left) unsupervised and (right) supervised methods on aligned LFW View 2 dataset. similarity and PCA reduction, I-LQP * comes out as the clear winner as it gives about 4.1% better accuracy than G-LQP * while being extremely faster to compute and evaluate.…”

Section: Face Verification On Lfw Datasetmentioning

confidence: 99%

Face Recognition using Local Quantized Patterns

Hussain¹,

Napoléon²,

Jurie³

2012

Procedings of the British Machine Vision Conference 2012

165

109

View full text Add to dashboard Cite

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.

show abstract

“…Accuracy LDML [1] 0.7927±0.0060 Hybrid [29] 0.8398±0.0035 Combined b/g samples based [31] 0.8683±0.0034 *Attribute and Simile classifiers [32] 0.8529±0.0123 Single LE + holistic [30] 0.8122±0.0053 *Multiple LE + comp [30] 0.8445±0.0046 *Predict-Associate [33] 0.9057 ±0.0056 LARK + OSS [34] 0.8512 ±0.0037 DDL-PC1 0.8603 ±0.0033 DDL-PC1 (flip) 0.8710 ±0.0035…”

Section: Methodsmentioning

confidence: 99%

Discriminative Dictionary Learning with Pairwise Constraints

Guo

Jiang

Davis

2013

Computer Vision – ACCV 2012

View full text Add to dashboard Cite

Abstract. In computer vision problems such as pair matching, only binary information -'same' or 'different' label for pairs of images -is given during training. This is in contrast to classification problems, where the category labels of training images are provided. We propose a unified discriminative dictionary learning approach for both pair matching and multiclass classification tasks. More specifically, we introduce a new discriminative term called 'pairwise sparse code error' for the discriminativeness in sparse representation of pairs of signals, and then combine it with the classification error for discriminativeness in classifier construction to form a unified objective function. The solution to the new objective function is achieved by employing the efficient feature-sign search algorithm. The learned dictionary encourages feature points from a similar pair (or the same class) to have similar sparse codes. We validate the effectiveness of our approach through a series of experiments on face verification and recognition problems.

show abstract

Face Verification Using the LARK Representation

Cited by 140 publications

References 41 publications

Tom-vs-Pete Classifiers and Identity-Preserving Alignment for Face Verification

Tom-vs-Pete Classifiers and Identity-Preserving Alignment for Face Verification

Face Recognition using Local Quantized Patterns

Discriminative Dictionary Learning with Pairwise Constraints

Contact Info

Product

Resources

About