2000
DOI: 10.1016/s0262-8856(99)00051-7
|View full text |Cite
|
Sign up to set email alerts
|

Face recognition by statistical analysis of feature detectors

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
4
1

Citation Types

1
9
0

Year Published

2005
2005
2014
2014

Publication Types

Select...
4
2
1

Relationship

0
7

Authors

Journals

citations
Cited by 28 publications
(10 citation statements)
references
References 6 publications
1
9
0
Order By: Relevance
“…Several regions are chosen for feature extraction. 19,20 A bank of Gabor filters is constructed by varying the center frequency ðf; φ; θÞ and the scale parameter vector ðσ x ; σ y ; σ λ Þ. The method to obtain the spectral reflectance from the image measurements is provided by Pan et al 11 Based on previous work 11 that showed that skin provides the best recognition results, we use skin regions for the extraction of spectral features.…”
Section: Featuresmentioning
confidence: 99%
“…Several regions are chosen for feature extraction. 19,20 A bank of Gabor filters is constructed by varying the center frequency ðf; φ; θÞ and the scale parameter vector ðσ x ; σ y ; σ λ Þ. The method to obtain the spectral reflectance from the image measurements is provided by Pan et al 11 Based on previous work 11 that showed that skin provides the best recognition results, we use skin regions for the extraction of spectral features.…”
Section: Featuresmentioning
confidence: 99%
“…In recent years, many methods based on Gabor filters have been introduced. The Gabor filters, whose kernels are similar to the response of the two-dimensional receptive field profiles of the mammalian simple cortical cell, exhibit the desirable characteristics of spatial locality, spatial frequency and orientation selectivity [8,9], so often act as a powerful tool to extract the main features from face images [10][11][12][13][14][15][16][17][18][19][20]. Indeed, Lades et al [10] pioneered the application of Gabor features for face recognition by proposing the dynamic link architecture (DLA).…”
Section: Introductionmentioning
confidence: 99%
“…Generally, DLA is superior to other face recognition techniques in terms of rotation invariant, but the matching process is computationally expensive. Not constructing a graph, Kalocsai et al [12] employed dozens of Gabor filters to obtain face representation by convoluting the facial landmarks with these filters. However, setting the landmarks needs manual operation.…”
Section: Introductionmentioning
confidence: 99%
“…Therefore, many sampling or compressing methods are proposed to reduce the space dimension to avoid dealing with the enormous data. In [8], each face was represented as convolution results of the face with 40 Gabor filters at 48 predetermined fiducial points, which were located at face landmarks (e.g. the eyes, nose and mouth, etc.…”
Section: Introductionmentioning
confidence: 99%