2010
DOI: 10.1016/j.patrec.2010.01.021
|View full text |Cite
|
Sign up to set email alerts
|

An illumination normalization model for face recognition under varied lighting conditions

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
13
0

Year Published

2013
2013
2023
2023

Publication Types

Select...
5
3

Relationship

0
8

Authors

Journals

citations
Cited by 34 publications
(13 citation statements)
references
References 25 publications
0
13
0
Order By: Relevance
“…In [42], face images are roughly partitioned into four geometrically regular parts for illumination invariant face recognition. Yet regular regions are somewhat arbitrary and difficult to conquer the non-uniform illumination problem.…”
Section: Segmentation-based Half Histogram Truncation and Stretching mentioning
confidence: 99%
“…In [42], face images are roughly partitioned into four geometrically regular parts for illumination invariant face recognition. Yet regular regions are somewhat arbitrary and difficult to conquer the non-uniform illumination problem.…”
Section: Segmentation-based Half Histogram Truncation and Stretching mentioning
confidence: 99%
“…However, optimal choice of the parameter gamma is image dependent. In [2], [3], images are partitioned into several regions, and HE and/or gamma correction are applied to each region. A disadvantage of this approach is that transitions of colors and intensities are not smooth at the boundaries between different regions.…”
Section: A Previous Workmentioning
confidence: 99%
“…In [8], an iterative adaptive smoothing method is used to estimate L, where the weights of pixels are determined as functions of gradients and inhomogeneities. To estimate L, [2], [9] suggest minimizing an objective function based on the square of the first order differential and the difference of the illumination L from the given image. The estimated illumination component is further enhanced in [9] using gamma correction.…”
Section: A Previous Workmentioning
confidence: 99%
See 1 more Smart Citation
“…The main drawbacks of the approaches mentioned above are the need of knowledge about the light source or a large volume of training data. To overcome this demerit, region-based image preprocessing methods are proposed in [5][6][7]. These methods introduced some noise to make global illumination discontinuous.…”
Section: Introductionmentioning
confidence: 99%