Investigating the relationship between image enhancement and image compression in the context of the multi-scale retinex

Rahman, Zia-ur; Jobson, Daniel J.; Woodell, Glenn A.

doi:10.1016/j.jvcir.2010.12.006

Cited by 33 publications

(17 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This section will describe the effective processing of shadow in the image, for face location. In past studies, the equalization process was adopted in order to process images with different lighting and direction 10,11 . This paper adopts the easier and quicker method of adaptive smoothing 10 .…”

Section: Adaptive Smoothingmentioning

confidence: 99%

Face Localization and Detection Based on Symmetry Detection and Texture Features

Lin

Cai²,

Liao³

2012

ijecs

View full text Add to dashboard Cite

This study refers mainly to the characteristics of symmetry and texture features in order to correctly locate a face within an image. Since we target facial expression and illumination variation in a facial image, this first requires an equalization process of adaptive smoothing of the shadows of the face caused by varying illumination. Following this, for symmetry axis detection, the study will address: Gradient Detection, Image Width and Location of Symmetry Axes, Symmetry Axes for Gradient Histogram (SAGH) and Selection; Weight is also added to strengthen symmetry characteristics. In order to verify the accuracy of the method, this study will use 6 experimental methods, namely SAGH, SAPG, WSAGH, WSAPG, WSAGH for no adaptive smoothing, and WSAPG for no adaptive smoothing. The image database used for this experiment is the Yale Face Database, with facial images that are subjected to different illumination, masked by shelters and displaying varying facial expressions. The experiment results show that the WSAPG method is the most accurate; achieving a 96.36% LM value, with the lowest GM value; it was the most successful at locating a face in the image. Hopefully it will be applied to enhancing current face recognition technology. 192 International Journal of Electronic Commerce Studies

show abstract

Section: Adaptive Smoothingmentioning

confidence: 99%

Face Localization and Detection Based on Symmetry Detection and Texture Features

Lin

Cai²,

Liao³

2012

ijecs

View full text Add to dashboard Cite

show abstract

“…Path-based retinex [21] methods are the simplest, but they usually necessitate high computational complexity. Jobson et al had proposed the multi-scale retinex (MSR) [22,23] algorithm and the color restored multi-scale retinex (CRMSR) [24] algorithm. Partial differential equation (PDE) was introduced to the retinex algorithm in 1974 [25].…”

Section: Introductionmentioning

confidence: 99%

Non-uniform illumination endoscopic imaging enhancement via anti-degraded model and L 1 L 2-based variational retinex

Rao

Luo

et al. 2017

J Wireless Com Network

View full text Add to dashboard Cite

In this paper, we propose a novel image enhancement algorithm via anti-degraded model and L 1 L 2 -based variational retinex (AD-L 1 L 2 VR) for non-uniform illumination endoscopic images. Firstly, a haze-free endoscopic image is obtained by an anti-degraded model named dark channel prior (DCP). For getting a more accurate transmission map, it is refined by using a guided image filtering. Secondly, the haze-free endoscopic image is decomposed into detail and naturalness components by light filtering. Thirdly, a logarithmic Laplacian-based gamma correction (LLGC) is added to the naturalness component for preventing color cast and uneven lighting. Fourthly, we assume that the error between the detail component of the haze-free image and the product of associated reflectance and background illumination follows Gaussian-Laplacian distribution. So, the associated reflectance component can be obtained by using the proposed L 1 L 2 -based variational retinex (L 1 L 2 VR) model. Finally, the recombination of modified naturalness component and associated reflectance component become the final result. Experimental results demonstrate that the proposed algorithm reveals more details in the background regions as well as other interesting areas and can mostly prevent the color cast. It has a better performance on increasing diagnosis and reducing misdiagnosis than other existing enhancement methods.

show abstract

“…To overcome this problem, many modified Retinex theories have been proposed. Retinex algorithms are basically categorized into path-based methods [12][13][14], center-/ surround-based methods [15][16][17][18], recursive methods [19][20][21], PDE-based methods [22][23][24], and variational methods [11,[25][26][27][28][29][30]. Path-based Retinex methods are the simplest, but they usually necessitate high computational complexity.…”

Section: Introductionmentioning

confidence: 99%

“…For the center-/surround-based methods, Gaussian filtering is usually used as a low pass filter to estimate the illumination. In order to get better performance for RGB images, Jobson et al had put forward multi-scale Retinex (MSR) [16,17] algorithm and color restored multiscale Retinex (CRMSR) [18] algorithm. These algorithms are easy to implement but too many parameters need to be manually set.…”

Section: Introductionmentioning

confidence: 99%

Mission-critical monitoring based on surround suppression variational Retinex enhancement for non-uniform illumination images

Rao

Wang

2017

J Wireless Com Network

View full text Add to dashboard Cite

In this letter, a surround suppression variational Retinex enhancement algorithm (SSVR) is proposed for non-uniform illumination images. Instead of a gradient module, a surround suppression mechanism is used to provide spatial information in order to constrain the total variation regularization strength of the illumination and reflectance. The proposed strategy preserves the boundary areas in the illumination so that halo artifacts are prevented. It also preserves textural details in the reflectance to prevent from illumination compression, which further contributes to the contrast enhancement in the resulting image. In addition, strong regularization strength is enforced to eliminate uneven intensities in the homogeneous areas. The split Bregman optimization algorithm is employed to solve the proposed model. Finally, after decomposition, a contrast gain is added to reflectance for contrast enhancement, and a Laplacianbased gamma correction is added to illumination for prevent color cast. The recombination of the modified reflectance and illumination become the final result. Experimental results demonstrate that the proposed SSVR algorithm performs better than other methods.

show abstract

Investigating the relationship between image enhancement and image compression in the context of the multi-scale retinex

Cited by 33 publications

References 27 publications

Face Localization and Detection Based on Symmetry Detection and Texture Features

Face Localization and Detection Based on Symmetry Detection and Texture Features

Non-uniform illumination endoscopic imaging enhancement via anti-degraded model and L 1 L 2-based variational retinex

Mission-critical monitoring based on surround suppression variational Retinex enhancement for non-uniform illumination images

Contact Info

Product

Resources

About