Improved Multi-Scale Retinex Algorithm for Medical Image Enhancement

Meng, Qingyuan; Bian, Deqian; Guo, Ming; Lu, Fengmei; Liu, Dong-Pu

doi:10.1007/978-1-4471-2386-6_121

Cited by 11 publications

(7 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While the Retinex theory (Land and McCann, 1971) was developed to describe the human vision perception, its derived versions have led to efficient methods in contrast enhancement (Beghdadi et al ., ; Petro et al ., ). One important derivation is the Single‐Scale Retinex (SSR) (Jobson et al ., ), which is a nonlinear contrast enhancement method that belongs to the class of center/surround functions where its output is calculated from the variance between the input (center) value and an average of its surroundings (Bogdanova, ; Meng et al ., ). The basic principle of the SSR model is to estimate an illumination image by convolving the degraded image by a specific function, such as the Gaussian Surround Function (GSF).…”

Section: Proposed Tuned Brightness Controlled Single‐scale Retinexmentioning

confidence: 97%

A new algorithm for improving the low contrast of computed tomography images using tuned brightness controlled single-scale Retinex

Al-Ameen

Sulong

2015

Scanning

View full text Add to dashboard Cite

Contrast is a distinctive visual attribute that indicates the quality of an image. Computed Tomography (CT) images are often characterized as poor quality due to their low-contrast nature. Although many innovative ideas have been proposed to overcome this problem, the outcomes, especially in terms of accuracy, visual quality and speed, are falling short and there remains considerable room for improvement. Therefore, an improved version of the single-scale Retinex algorithm is proposed to enhance the contrast while preserving the standard brightness and natural appearance, with low implementation time and without accentuating the noise for CT images. The novelties of the proposed algorithm consist of tuning the standard single-scale Retinex, adding a normalized-ameliorated Sigmoid function and adapting some parameters to improve its enhancement ability. The proposed algorithm is tested with synthetically and naturally degraded low-contrast CT images, and its performance is also verified with contemporary enhancement techniques using two prevalent quality evaluation metrics-SSIM and UIQI. The results obtained from intensive experiments exhibited significant improvement not only in enhancing the contrast but also in increasing the visual quality of the processed images. Finally, the proposed low-complexity algorithm provided satisfactory results with no apparent errors and outperformed all the comparative methods.

show abstract

Section: Proposed Tuned Brightness Controlled Single‐scale Retinexmentioning

confidence: 97%

A new algorithm for improving the low contrast of computed tomography images using tuned brightness controlled single-scale Retinex

Al-Ameen

Sulong

2015

Scanning

View full text Add to dashboard Cite

show abstract

“…Retinex has taken a big part of being used in medical imaging applications [49][50][51][52][53]. In [51] Retinex was applied to be used in automatic analysis correctness of skin lesions.…”

Section: Biomedical Applicationsmentioning

confidence: 99%

Retinex theory for color image enhancement: A systematic review

Hussein

Hamodi²,

Sabri³

2019

IJECE

View full text Add to dashboard Cite

<span>A short but comprehensive review of Retinex has been presented in this paper. Retinex theory aims to explain human color perception. In addition, its derivation on modifying the reflectance components has introduced effective approaches for images contrast enhancement. In this review, the classical theory of Retinex has been covered. Moreover, advance and improved techniques of Retinex, proposed in the literature, have been addressed. Strength and weakness aspects of each technique are discussed and compared. An optimum parameter is needed to be determined to define the image degradation level. Such parameter determination would help in quantifying the amount of adjustment in the Retinex theory. Thus, a robust framework to modify the reflectance component of the Retinex theory can be developed to enhance the overall quality of color images.</span>

show abstract

“…Qingyuan et al [9] proposed an improved MSR algorithm for medical image enhancement. In this scheme, Y-component of medical image is separated into edge and non-edge area subsequent to RGB to YIQ color space conversion.…”

Section: Existing Workmentioning

confidence: 99%

Natural Color Image Enhancement Based on Modified Multiscale Retinex Algorithm and Performance Evaluation Using Wavelet Energy

Hanumantharaju

Ravishankar

Rameshbabu

2014

Advances in Intelligent Systems and Computing

View full text Add to dashboard Cite

This paper presents a new color image enhancement technique based on modified modified MultiScale Retinex (MSR) algorithm and visual quality of the enhanced images are evaluated using a new metric, namely, Wavelet Energy (WE). The color image enhancement is achieved by downsampling the value component of HSV color space converted image into three scales (normal, medium and fine) following the contrast stretching operation. These downsampled value components are enhanced using the MSR algorithm. The value component is reconstructed by averaging each pixels of the lower scale image with that of the upper scale image subsequent to upsampling the lower scale image. This process replaces dark pixel by the average pixels of both the lower scale and upper scale, while retaining the bright pixels. The quality of the reconstructed images in the proposed method is found to be good and far better then the other researchers method. The performance of the proposed scheme is evaluated using new wavelet domain based assessment criterion, referred as WE. This scheme computes the energy of both original and enhanced image in wavelet domain. The number of edge details as well as WE is less in a poor quality image compared with naturally enhanced image. Experimental results presented confirms that the proposed wavelet energy based color image quality assessment technique efficiently characterizes both the local and global details of enhanced image.

show abstract

Improved Multi-Scale Retinex Algorithm for Medical Image Enhancement

Cited by 11 publications

References 6 publications

A new algorithm for improving the low contrast of computed tomography images using tuned brightness controlled single-scale Retinex

A new algorithm for improving the low contrast of computed tomography images using tuned brightness controlled single-scale Retinex

Retinex theory for color image enhancement: A systematic review

Natural Color Image Enhancement Based on Modified Multiscale Retinex Algorithm and Performance Evaluation Using Wavelet Energy

Contact Info

Product

Resources

About