2011
DOI: 10.1109/tifs.2011.2159205
| View full text |Cite
|
Sign up to set email alerts
|

Abstract: Abstract-We present a novel face representation based on locally adaptive regression kernel (LARK) descriptors [1]. Our LARK descriptor measures a self-similarity based on "signal-induced distance" between a center pixel and surrounding pixels in a local neighborhood. By applying principal component analysis (PCA) and a logistic function to LARK consecutively, we develop a new binary-like face representation which achieves state of the art face verification performance on the challenging benchmark "Labeled Fac… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
58
0
2

Year Published

2012
2012
2022
2022

Publication Types

Select...
6
3
1

Relationship

0
10

Authors

Journals

citations
Cited by 137 publications
(60 citation statements)
references
References 41 publications
0
58
0
2
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%
“…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%
“…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%
“…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%