Illumination ratio image: synthesizing and recognition with varying illuminations

Zhao, Jiali; Su, Yong; Wang, Dejun; Luo, Siwei

doi:10.1016/s0167-8655(03)00113-2

Cited by 29 publications

(11 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some of which can be found in the following literatures [3], [4], [5], [6], [7], [8], [9], [10], [11]. The methods proposed in these literatures assume a Lambertian surface, that is, the assumption that light is reflected equally across the image (diffuse reflectance).…”

Section: ) Illumination Modelsmentioning

confidence: 99%

“…Likewise, [7] reconstructs a shape-specific illumination subspace that characterizes statistics of measured illumination from single images of different subjects under various lighting conditions. Zhao et al [8], generated illumination ratio images from a single frontal view image for the face recognition system to adapt to different illumination conditions. With a pre-estimated lighting attribute of a test image obtained using spherical harmonic model, [9] implemented an adaptive processing method to normalize lighting variation.…”

Section: ) Illumination Modelsmentioning

confidence: 99%

See 1 more Smart Citation

Minimizing Separability: A Comparative Analysis of Illumination Compensation Techniques in Face Recognition

Olisah¹

2017

IJITCS

View full text Add to dashboard Cite

Abstract-Feature extraction task are primarily about making sense of the discriminative features/patterns of facial information and extracting them. However, most real world face images are almost always intertwined with imaging modality problems of which illumination is a strong factor. The compensation of the illumination factor using various illumination compensation techniques has been of interest in literatures with few emphasis on the adverse effect of the techniques to the task of extracting the actual discriminative features of a sample image for recognition. In this paper, comparative analyses of illumination compensation techniques for extraction of meaningful features for recognition using a single feature extraction method is presented. More also, enhancing red, green, blue gamma encoding (rgbGE) in the log domain so as to address the separability problem within a person class that most techniques incur is proposed. From experiments using plastic surgery sample faces, it is evident that the effect illumination compensation techniques have on face images after pre-processing is highly significant to recognition accuracy.

show abstract

Section: ) Illumination Modelsmentioning

confidence: 99%

Section: ) Illumination Modelsmentioning

confidence: 99%

Minimizing Separability: A Comparative Analysis of Illumination Compensation Techniques in Face Recognition

Olisah¹

2017

IJITCS

View full text Add to dashboard Cite

show abstract

“…Zhao et al [35] synthesized 45 images per person, which are adopted for training, and a 93.3% recognition rate was achieved. Liu et al [36] reported a 98.4% recognition rate and Choi et al used shadow compensation to obtain 99.6% recognition rate [37].…”

Section: Comparative Evaluation Upon Feature Selection and Face Recogmentioning

confidence: 99%

An EDBoost algorithm towards robust face recognition in JPEG compressed domain

Qing

Jiang

2010

Image and Vision Computing

View full text Add to dashboard Cite

“…The idea of class-based image synthesis from a single view [11] has been explored for illuminationresistant face recognition [12], where different people are assumed to have the same surface normal and different albedo, and new images can be simulated with varying illumination conditions based on a sample of images in the same general class with the input image. A similar work is presented in [13] where an illumination ratio image is derived and used for lighting correction. Narasimhan and Nayar [14] addresses the problem of restoring atmospherically degraded images and presents a method to estimate the scene depth from two images captured under different time.…”

Section: Introductionmentioning

confidence: 99%

Relative gradients for image lighting correction

Hou

Yau

2010

2010 IEEE International Conference on Acoustics, Speech and Signal Processing

View full text Add to dashboard Cite

A fundamental problem in computer vision is to enhance images under various lighting conditions. This paper proposes an approach to lighting correction through reconstructing the image based on relative gradients. Compared with the absolute gradients as exemplified in the originally acquired image, the relative gradients are more stable under the variation of lighting. Extensive experiments have been carried out over images under a wide range of lighting variations. Comparisons with popular lighting correction methods are presented.

show abstract

Illumination ratio image: synthesizing and recognition with varying illuminations

Cited by 29 publications

References 9 publications

Minimizing Separability: A Comparative Analysis of Illumination Compensation Techniques in Face Recognition

Minimizing Separability: A Comparative Analysis of Illumination Compensation Techniques in Face Recognition

An EDBoost algorithm towards robust face recognition in JPEG compressed domain

Relative gradients for image lighting correction

Contact Info

Product

Resources

About