scispace - formally typeset
Search or ask a question
Proceedings Article•DOI•

Wavelet-based contrast enhancement of dark images using dynamic stochastic resonance

Rajlaxmi Chouhan1, Rajib Kumar Jha2, Prabir Kumar Biswas1•
Indian Institute of Technology Kharagpur1, Indian Institutes of Information Technology2
16 Dec 2012-pp 73
TL;DR: The proposed dynamic stochastic resonance (DSR) technique has been proposed for contrast enhancement of dark and low contrast images in discrete wavelet transform (DWT) domain and is found to give noteworthy performance in terms of contrast enhancement, perceptual quality, as well as colorfulness.
Abstract: In this paper, a dynamic stochastic resonance (DSR)-based technique has been proposed for contrast enhancement of dark and low contrast images in discrete wavelet transform (DWT) domain. Traditionally, the performance of a stochastic resonance (SR)-based system is improved by addition of external noise. However, in the proposed DSR-based approach, the internal noise of an image has been utilized for the purpose of contrast enhancement. The degradation due to inadequate illumination is treated as noise, and is used to produce a noise-induced transition of the image from a low-contrast state to a high-contrast state. Stochastic resonance is induced in the approximation and detail coefficients in an iterative fashion, producing an increase in variance and mean of the coefficient distribution. Optimal output response is ensured by selection of optimal of bistable system parameters. An iterative algorithm is followed to achieve target value of performance metrics, such as relative contrast enhancement factor (F), perceptual quality measures (PQM), and color enhancement factor (CEF), at minimum iteration count. When compared with the existing SR-based and non SR-based enhancement techniques in spatial and frequency domains, the proposed technique is found to give noteworthy performance in terms of contrast enhancement, perceptual quality, as well as colorfulness.
Citations
More filters
Journal Article•DOI•
Iris tissue recognition based on GLDM feature extraction and hybrid MLPNN-ICA classifier

[...]

Neda Ahmadi1, Gholamreza Akbarizadeh1•
Shahid Chamran University of Ahvaz1
01 Apr 2020-Neural Computing and Applications
TL;DR: A new method of feature extraction and classification based on gray-level difference method and hybrid MLPNN-ICA classifier is proposed, which is implemented on CASIA-Iris V3 dataset and UCI machine learning repository datasets.
Abstract: The use of iris tissue for identification is an accurate and reliable system for identifying people. This method consists of four main processing stages, namely segmentation, normalization, feature extraction, and matching. In this study, a new method of feature extraction and classification based on gray-level difference method and hybrid MLPNN-ICA classifier is proposed. For experimental results, our study is implemented on CASIA-Iris V3 dataset and UCI machine learning repository datasets.

40 citations

Journal Article•DOI•
Enhancement of dark images using dynamic stochastic resonance with anisotropic diffusion

[...]

Nidhi Gupta1, Rajib Kumar Jha2•
Indian Institutes of Information Technology1, Indian Institute of Technology Patna2
01 Mar 2016-Journal of Electronic Imaging
TL;DR: The method increases mean and variance of the image by the optimum iterations on low coefficients of images, which improves contrast and brightness, respectively, and simultaneously, edges also become sharper.
Abstract: Image enhancement techniques are intended to improve the quality of an image without any kind of distortion or degradation. The literature is rich enough in this area, but there also exist some limitations. A technique is proposed for image enhancement by combining anisotropic diffusion with dynamic stochastic resonance in discrete wavelet transform domain. The method increases mean and variance of the image by the optimum iterations on low coefficients of images, which improves contrast and brightness, respectively, and simultaneously, edges also become sharper. It is well demonstrated by performing on various test images. Specifically, the adaptation and efficiency of the proposed technique for medical images are shown, because generally medical images appear contaminated with noise in terms of low illumination.

23 citations

Proceedings Article•DOI•
Localized image enhancement

[...]

Saumik Bhattacharya1, Sumana Gupta1, Venkatesh K. Subramanian1•
Indian Institute of Technology Kanpur1
08 May 2014
TL;DR: This work proposes a fast algorithm to increase the contrast of an image locally using singular value decomposition (SVD) approach and attempts to define some parameters which can give clues related to the progress of the enhancement process.
Abstract: Image enhancement is a well established field in image processing. The main objective of image enhancement is to increase the perceptual information contained in an image for better representation using some intermediate steps, like, contrast enhancement, debluring, denoising etc. Among them, contrast enhancement is especially important as human eyes are more sensitive to luminance than the chrominance components of an image. Most of the contrast enhancement algorithms proposed till now are global methods. The major drawback of this global approach is that in practical scenarios, the contrast of an image does not deteriorate uniformly and the outputs of the enhancement techniques reach saturation at proper contrast points. That leads to information loss. In fact, to the best of our knowledge, no non-reference perceptual measure of image quality has yet been proposed to measure localized enhancement. We propose a fast algorithm to increase the contrast of an image locally using singular value decomposition (SVD) approach and attempt to define some parameters which can give clues related to the progress of the enhancement process.

21 citations

Cites background or methods from "Wavelet-based contrast enhancement ..."

  • ..., fail to preserve the color information of the image and thus an image processed with these techniques looks very synthetic [9], [10]....

    [...]

  • ...[13] R. K. Jha, R.Chouhan and P. K. Biswas, Noise-induced contrast enhancement of dark images using non-dynamic stochastic resonance, NCC’12, 2012, p. 1-5....

    [...]

  • ...have been defined such that the improvement can be measured using the processed image and the input image [9], [10], [18], [19]....

    [...]

  • ...2) Several perceptual measures have been proposed by different authors to calculate the quality of the enhanced images [9], [10], [12], [17]....

    [...]

  • ...For convenience, a brief description of the parameter selections of different techniques have been stated as follows: CLAHE has been implemented using the in-built function provided by MATLAB; gamma correction has been implemented by selecting the optimal value of gamma between 1 to 2, whichever gives the maximum F for globally degraded image and maximum ce for partially degraded images; multiscale retinex has been implemented using the MATLAB algorithm as given by Funt et al. [21]; NDSR has been developed using gaussian noise and standard deviation ranging 1− 20; DSR has been implemented using the optimal values for resonance as described by Jha and Chouhan [10]....

    [...]

Journal Article•DOI•
A fast and efficient computer aided diagnostic system to detect tumor from brain magnetic resonance imaging

[...]

Nidhi Gupta1, Pritee Khanna1•
Indian Institute of Information Technology, Design and Manufacturing, Jabalpur1
01 Jun 2015-International Journal of Imaging Systems and Technology
TL;DR: A simple and efficient CAD (computer‐aided diagnostic) system is proposed for tumor detection from brain magnetic resonance imaging (MRI) that is well adaptive and fast, and it is compared with well‐known existing techniques, like k‐mean, fuzzy c‐means, etc.
Abstract: In this work, a simple and efficient CAD computer-aided diagnostic system is proposed for tumor detection from brain magnetic resonance imaging MRI. Poor contrast MR images are preprocessed by using morphological operations and DSR dynamic stochastic resonance technique. The appropriate segmentation of MR images plays an important role in yielding the correct detection of tumor. On examination of three views of brain MRI, it was visible that the region of interest ROI lies in the middle and its size ranges from 240 × 240 mm2 to 280 × 280 mm2. The proposed system makes effective use of this information and identifies four blocks from the desired ROI through block-based segmentation. Texture and shape features are extracted for each block of all MRIs in the training set. The range of these feature values defines the threshold to distinguish tumorous and nontumorous MRIs. Features of each block of an MRI view are checked against the threshold. For a particular feature, if a block is found tumorous in a view, then the other views are also checked for the presence of tumor. If corresponding blocks in all the views are found to be tumorous, then the MRI is classified as tumorous. This selective block processing technique improves computational efficiency of the system. The proposed technique is well adaptive and fast, and it is compared with well-known existing techniques, like k-means, fuzzy c-means, etc. The performance analysis based on accuracy and precision parameters emphasizes the effectiveness and efficiency of the proposed work.

20 citations

Cites methods from "Wavelet-based contrast enhancement ..."

  • ...Enhancement: Image enhancement is done by using DSR (explained in the DSR section) in Discrete Wavelet Transform (DWT) domain (Chouhan et al., 2012)....

    [...]

Journal Article•DOI•
Dynamic stochastic resonance-based grayscale logo extraction in hybrid SVD-DCT domain

[...]

Rajib Kumar Jha1, Rajlaxmi Chouhan2•
Indian Institute of Technology Patna1, Indian Institute of Technology Kharagpur2
01 May 2014-Journal of The Franklin Institute-engineering and Applied Mathematics
TL;DR: A novel dynamic stochastic resonance (DSR)-based technique for robust extraction of a grayscale logo from a tampered watermarked image and suggests that remarkable improvement of robustness is achieved by using DSR on singular values of DCT.
Abstract: This paper presents a novel dynamic stochastic resonance (DSR)-based technique for robust extraction of a grayscale logo from a tampered watermarked image. The watermark embedding is done on the singular values (SV) of the discrete cosine transform (DCT) coefficients of the cover image. DSR is then strategically applied during the logo extraction process where the SV of DCT coefficients are tuned following a double-well potential model by utilizing the noise introduced during attacks. The resilience of this technique has been tested in the presence of various noises, geometrical distortions, enhancement, compression, filtering and watermarking attacks. The proposed DSR-based technique for logo extraction gives noteworthy robustness without any significant trade-off in perceptual transparency of the watermarked image. A maximization approach has been adopted for the selection of bistable double-well parameters to establish noise-enhanced resonance. When compared with existing watermark extraction techniques based in SVD, DCT, SVD-DCT domains, as well as with their combination with DSR, the results suggest that remarkable improvement of robustness is achieved by using DSR on singular values of DCT.

15 citations

References
More filters
Journal Article•DOI•
Digital Color Image Enhancement Based On The Saturation Component

[...]

Robin N. Strickland1, Cheol-Sung Kim1, William F. McDonnell1•
University of Arizona1
01 Jul 1987-Optical Engineering
TL;DR: It is shown that color saturation, as well as luminance, can play an important role in achieving good image enhancement and limitations to luminance and saturation processing caused by poor quantization of the RGB tristimulus images are discussed.
Abstract: Much of the work done in digital image processing has been limited in application to black-and-white images, this being especially true of enhancement and restoration. The extension to color image processing is not trivial; a suitable color space must be selected for a given application, and then a good processing strategy must be devised. In fact, we doubt that any of the available color spaces will meet the needs of all types of image processing. Many color image processing strategies require that only a luminance component be actually processed. In image restoration, for example, good results are achievable by processing only the Y component of the popular NTSC transformation from RGB to YIQ components. In this paper we show that color saturation, as well as luminance, can play an important role in achieving good image enhancement. The technique proposed is simple to implement and is based on the observation that the saturation component often contains high frequency components that are not present in the luminance component. Contrast and sharpness enhancement techniques are discussed; the computer processing algorithms are restricted to those that preserve the natural appearance of the scene. We also discuss limitations to luminance and saturation processing caused by poor quantization of the RGB tristimulus images.

131 citations

"Wavelet-based contrast enhancement ..." refers background in this paper

  • ...Many algorithms available in literature have been designed for both colored and grayscale images in block DCT domain [2], [17], [11], [18]....

    [...]

Journal Article•DOI•
Magnetic resonance image enhancement using stochastic resonance in Fourier domain

[...]

V. P. Subramanyam Rallabandi1, Prasun Kumar Roy1•
National Brain Research Centre1
01 Nov 2010-Magnetic Resonance Imaging
TL;DR: The proposed stochastic resonance (SR)-based transform in Fourier space for the enhancement of magnetic resonance images of brain lesions can restore the original image from noisy image and optimally enhance the edges or boundaries of the tissues, and enables improved diagnosis over conventional methods.
Abstract: Objective In general, low-field MRI scanners such as the 0.5- and 1-T ones produce images that are poor in quality. The motivation of this study was to lessen the noise and enhance the signal such that the image quality is improved. Here, we propose a new approach using stochastic resonance (SR)-based transform in Fourier space for the enhancement of magnetic resonance images of brain lesions, by utilizing an optimized level of Gaussian fluctuation that maximizes signal-to-noise ratio (SNR). Materials and Methods We acquired the T1-weighted MR image of the brain in DICOM format. We processed the original MR image using the proposed SR procedure. We then tested our approach on about 60 patients of different age groups with different lesions, such as arteriovenous malformation, benign lesion and malignant tumor, and illustrated the image enhancement by using just-noticeable difference visually as well as by utilizing the relative enhancement factor quantitatively. Results Our method can restore the original image from noisy image and optimally enhance the edges or boundaries of the tissues, clarify indistinct structural brain lesions without producing ringing artifacts, as well as delineate the edematous area, active tumor zone, lesion heterogeneity or morphology, and vascular abnormality. The proposed technique improves the enhancement factor better than the conventional techniques like the Wiener- and wavelet-based procedures. Conclusions The proposed method can readily enhance the image fusing a unique constructive interaction of noise and signal, and enables improved diagnosis over conventional methods. The approach well illustrates the novel potential of using a small amount of Gaussian noise to improve the image quality.

108 citations

"Wavelet-based contrast enhancement ..." refers background or methods in this paper

  • ...Earlier application of stochastic resonance in contrast enhancement [13], [14] tested its applicability using externally added noise and selected parameters experimentally....

    [...]

  • ...Metric of contrast enhancement (F ) is based on global variance and mean of original and enhanced images [14]....

    [...]

  • ...Recently, other stochastic resonance-based techniques in wavelet and fourier domains for the enhancement of unclear diagnostic ultrasound and MRI images respectively have been reported [13], [14]....

    [...]

  • ...Recently some of the works on application of stochastic resonance for grayscale image or edge enhancement that have been reported in literature are [22, 4, 23, 12, 13, 14, 15, 6]....

    [...]

Journal Article•DOI•
Color equalization method and its application to color image processing

[...]

Ilia M. Bockstein1•
Russian Academy of Sciences1
01 May 1986-Journal of The Optical Society of America A-optics Image Science and Vision
TL;DR: In this article, a method of digital color image processing is described that leads to the equalization of the brightness histogram and of conditional saturation histogram for each hue area, which can be directly used for preparation of color images for interpretation and for the enhancement of color pictures for visual quality.
Abstract: A method of digital color-image processing is described that leads to the equalization of the brightness histogram and of conditional saturation histograms for each hue area. Means for solving problems that arise in the practical realization of the method are considered. Color equalization can be directly used for preparation of color images for interpretation and for the enhancement of color pictures for visual quality. In the first case, application of the method can result in an increase of the visibility of objects that are initially almost indistinguishable. In the second case it leads to multicolored pictures with unchanged color features.

73 citations

Journal Article•DOI•
Enhancement of feature extraction for low-quality fingerprint images using stochastic resonance

[...]

Choonwoo Ryu1, Seong G. Kong1, Hakil Kim2•
Temple University1, Inha University2
01 Jan 2011-Pattern Recognition Letters
TL;DR: Experimental results show that Gaussian noise added to low-quality fingerprint images enables the extraction of useful features for biometric identification by adding noise to the original signal.
Abstract: This paper presents a new approach to enhancing feature extraction for low-quality fingerprint images by adding noise to the original signal. Feature extraction often fails for low-quality fingerprint images obtained from excessively dry or wet fingers. In nonlinear signal processing systems, a moderate amount of noise can help amplify a faint signal while excessive amounts of noise can degrade the signal. Stochastic resonance (SR) refers to a phenomenon where an appropriate amount of noise added to the original signal can increase the signal-to-noise ratio. Experimental results show that Gaussian noise added to low-quality fingerprint images enables the extraction of useful features for biometric identification. SR was applied to 20 fingerprint images in the FVC2004 DB2 database that were rejected by a state-of-the-art fingerprint verification algorithm due to failures in feature extraction. SR enabled feature extraction from 10 out of 11 low-quality images with poor contrast. The remaining nine images were damaged fingerprints from which no meaningful features can be obtained. Improved feature extraction using SR decreases an equal error rate of fingerprint verification from 6.55% to 5.03%. The receiver operating characteristic curve shows that the genuine acceptance rates are improved for all false acceptance rates.

69 citations

"Wavelet-based contrast enhancement ..." refers background in this paper

  • ...[15] have developed a new approach for enhancing feature extraction from low quality fingerprint images using stochastic resonance....

    [...]

  • ...Both [12] and [15] use the concept of non-dynamic SR that adds N parallel frames of independent and identically distributed (i....

    [...]

  • ...Recently some of the works on application of stochastic resonance for grayscale image or edge enhancement that have been reported in literature are [22, 4, 23, 12, 13, 14, 15, 6]....

    [...]

Journal Article•DOI•
Noise-induced contrast enhancement using stochastic resonance on singular values

[...]

Rajib Kumar Jha1, Rajlaxmi Chouhan2•
Indian Institutes of Information Technology1, Indian Institutes of Technology2
01 Feb 2014-Signal, Image and Video Processing
TL;DR: The proposed DSR-SVD technique is found to give noteworthy better performance in terms of contrast enhancement factor, color enhancement factor and perceptual quality measure.
Abstract: In this paper, a dynamic stochastic resonance (DSR)-based technique in singular value domain for contrast enhancement of dark images has been presented. The internal noise due to the lack of illumination is utilized using a DSR iterative process to obtain enhancement in contrast, colorfulness as well as perceptual quality. DSR is a phenomenon that has been strategically induced and exploited and has been found to give remarkable response when applied on the singular values of a dark low-contrast image. When an image is represented as a summation of image layers comprising of eigen vectors and values, the singular values denote luminance information of each such image layer. By application of DSR on the singular values using the analogy of a bistable double-well potential model, each of the singular values is scaled to produce an image with enhanced contrast as well as visual quality. When compared with performance of some existing spatial domain enhancement techniques, the proposed DSR-SVD technique is found to give noteworthy better performance in terms of contrast enhancement factor, color enhancement factor and perceptual quality measure.

59 citations

"Wavelet-based contrast enhancement ..." refers background or methods in this paper

  • ...As described in [6], this denotation can be done with the view that a low contrast image is a noisy image containing internal noise due to lack of illumination....

    [...]

  • ...t a, optimum value of a for maximum SNR is found to be a=2σ0(2) (as derived in [6])....

    [...]

  • ...Among SR-based techniques, a comparison with singular-value-based DSR (SVD-DSR) [6] and suprathresh­old SR-based technique (SSR) [7] has been made....

    [...]

  • ...For mathematical formulation of theory of dynamic stochastic resonance, readers are advised to refer to [6] where an analogy to Benzi et al....

    [...]

  • ...4(a) Method F PQM CEF F PQM CEF F PQM CEF DWT-DSR 3.0 10.0 3.1 2.5 10.0 2.7 5.3 8.95 5.75 SVD-DSR 5.8 9.4 1.3 3.1 9.7 3.1 5.23 8.40 4.62 SSR 2.2 9.5 6.5 6.1 8.9 5.1 2.51 7.95 6.00 CLAHE 1.9 10.8 0.5 2.2 10.5 1.3 1.98 7.85 2.73 Photoshop 5.4 8.5 1.3 2.1 11.0 1.3 4.69 8.69 4.75 Gamma 9.5 8.5 11.5 1.2 10.9 1.5 5.92 6.92 5.01 Retinex 7.8 8.2 7.1 0.1 12.4 0.2 4.78 6.96 8.37 MSR 1.8 9.5 7.1 0.4 11.7 0.7 1.68 7.18 2.77 MHPF 8.4 8.2 16.8 0.6 11.7 0.8 5.02 9.01 7.21 MCE 1.0 12.2 0.2 1.1 8.8 1.0 1.18 8.77 0.96 MCE-DRC 0.7 11.9 0.2 0.9 11.1 1.0 0.97 9.01 7.21 CES 1.2 11.3 0.3 0.9 10.3 1.5 1.13 8.32 1.58 contrast enhancement of dark images using non-dynamic stochastic resonance....

    [...]

Related Papers (5)
No-reference perceptual quality assessment of JPEG compressed images

[...]

10 Dec 2002
Zhou Wang, Hamid R. Sheikh, Alan C. Bovik
Enhancement of Color Images by Scaling the DCT Coefficients

[...]

01 Oct 2008-IEEE Transactions on Image Processing
Jayanta Mukherjee, Sanjit K. Mitra
Magnetic resonance image enhancement using stochastic resonance in Fourier domain

[...]

01 Nov 2010-Magnetic Resonance Imaging
V. P. Subramanyam Rallabandi, Prasun Kumar Roy
A multiscale retinex for bridging the gap between color images and the human observation of scenes

[...]

01 Jul 1997-IEEE Transactions on Image Processing
D.J. Jobson, Zia-ur Rahman, G.A. Woodell
Enhancement of dark and low-contrast images using dynamic stochastic resonance

[...]

06 Jun 2013-Iet Image Processing
Rajlaxmi Chouhan, Rajib Kumar Jha, Prabir Kumar Biswas