Optimization of Stego Image Retaining Secret Information Using Genetic Algorithm with 8-connected PSNR

Roy, Rinita; Laha, Sumit

doi:10.1016/j.procs.2015.08.168

Cited by 27 publications

(22 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Full reference evaluation indexes include index MSE (Mean squared error), PSNR (peak signal to noise ratio) and SSIM (Structural similarity). The MSE index represents the mean difference between the dehazing image and the haze‐free image and can be given by

normalMSE (() H^{'}, F) = \frac{1}{3 italicXY} \sum_{x = 1}^{X} \sum_{y = 1}^{Y} \sum_{c = 1}^{3} {(H^{'} (x, y, c) - F (x, y, c))}^{2} .

In an image block, X × Y pixels are expressed as XY, the number of rgb color channels c , H ′( x , y , c ) the dehazing image of synthetic or realistic scene.…”

Section: Experiments and Comparisonmentioning

confidence: 99%

See 1 more Smart Citation

MFDC‐net: Multifeature‐based deep convolutional neural network for single image haze removal

Jing-juan

2019

Concurrency and Computation

View full text Add to dashboard Cite

Summary When it comes to the dehazing method based on the ambient light scattering model, there are ill‐conditioning problems of great concern. Therefore, the inaccurate estimation of the global atmospheric light and transmittance can bring about hue error phenomena, halo artifacts, and image noises. In this paper, we present an effective and efficient approach to solve above problems. Firstly, we adopt single‐threshold segmentation method and quad‐tree algorithms, which can break through the limitation that the dark channel prior theory (DCP) is not suitable for sky region, to quickly and accurately locate and estimate the global atmospheric light. Secondly, we design a new deep convolutional network architecture, which can effectively suppress the halo effect of image edges and restrain image noises, to optimize transmittance. Numerous of outdoor and synthesis haze image test results indicate that the optimized approach could shorten the processing time greatly. Besides, with more accurate global atmospheric light value and transmittance, the image noise and the halo artifact can be effectively suppressed and removed respectively, the hue error phenomenon improved, and the image contrast significantly enhanced in the dehazing results.

show abstract

normalMSE (() H^{'}, F) = \frac{1}{3 italicXY} \sum_{x = 1}^{X} \sum_{y = 1}^{Y} \sum_{c = 1}^{3} {(H^{'} (x, y, c) - F (x, y, c))}^{2} .

In an image block, X × Y pixels are expressed as XY, the number of rgb color channels c , H ′( x , y , c ) the dehazing image of synthetic or realistic scene.…”

Section: Experiments and Comparisonmentioning

confidence: 99%

“…Full reference evaluation indexes include index MSE 24 (Mean squared error), PSNR 25,26 (peak signal to noise ratio) and SSIM 26,27 (Structural similarity). The MSE index represents the mean difference between the dehazing image and the haze-free image and can be given by…”

Section: Objective Quantitative Evaluationmentioning

confidence: 99%

MFDC‐net: Multifeature‐based deep convolutional neural network for single image haze removal

Jing-juan

2019

Concurrency and Computation

View full text Add to dashboard Cite

show abstract

“…Furthermore, following an application of some attacks (image enhancement/processing operation), a normalised cross-correlation examination indicates no significant difference between the original image before embedding and after embedding. In contrast to this finding, it has been stated that the PSNR measurement is not valid or it does not truly indicate the signal to noise ratio accurately when the content of the original file changes after embedding (Lazzerini et al 2010; Roy and Laha 2015). Some studies have also shown that PSNR poorly correlates with the subjective quality (Huynh-Thu and Ghanbari 2012; Tanchenko 2014); however, PSNR is still extensively used in evaluating the noise/denoising performance (Ong et al 2006; Yoo and Ahn 2013), although PSNR as a quality metric that is constantly debated, in that it either is/is not relevant or is wrongly used as a quality metric.…”

Section: Introductionmentioning

confidence: 96%

An intermediate significant bit (ISB) watermarking technique using neural networks

2016

View full text Add to dashboard Cite

Prior research studies have shown that the peak signal to noise ratio (PSNR) is the most frequent watermarked image quality metric that is used for determining the levels of strength and weakness of watermarking algorithms. Conversely, normalised cross correlation (NCC) is the most common metric used after attacks were applied to a watermarked image to verify the strength of the algorithm used. Many researchers have used these approaches to evaluate their algorithms. These strategies have been used for a long time, however, which unfortunately limits the value of PSNR and NCC in reflecting the strength and weakness of the watermarking algorithms. This paper considers this issue to determine the threshold values of these two parameters in reflecting the amount of strength and weakness of the watermarking algorithms. We used our novel watermarking technique for embedding four watermarks in intermediate significant bits (ISB) of six image files one-by-one through replacing the image pixels with new pixels and, at the same time, keeping the new pixels very close to the original pixels. This approach gains an improved robustness based on the PSNR and NCC values that were gathered. A neural network model was built that uses the image quality metrics (PSNR and NCC) values obtained from the watermarking of six grey-scale images that use ISB as the desired output and that are trained for each watermarked image’s PSNR and NCC. The neural network predicts the watermarked image’s PSNR together with NCC after the attacks when a portion of the output of the same or different types of image quality metrics (PSNR and NCC) are obtained. The results indicate that the NCC metric fluctuates before the PSNR values deteriorate.

show abstract

“…The implicit errors are removed and the time complexity is decreased using genetic algorithm [4]. Rinita Roy et al (2015) proposed an optimization technique using genetic algorithm to optimize imperceptibility measure which results in high image quality watermarked image. A heuristic initialization technique to generate initial population and fitness function based on PSNR from 8-connected neighbours of each pixel is followed to optimize the quality of the stego image [5].…”

Section: Introductionmentioning

confidence: 99%

“…Rinita Roy et al (2015) proposed an optimization technique using genetic algorithm to optimize imperceptibility measure which results in high image quality watermarked image. A heuristic initialization technique to generate initial population and fitness function based on PSNR from 8-connected neighbours of each pixel is followed to optimize the quality of the stego image [5]. D. Venkatesan et al (2012) proposed optimization of fidelity in digital image watermarking using a new Genetic Algorithm based on Center of Mass Selection Operator (CMGA), to find the optimum locations for digital watermark insertion in a cover image with the focus to optimize fidelity [6].…”

Section: Introductionmentioning

confidence: 99%

Mean Square Error Optimization to Authenticate Multi-Modality Medical Images in Wavelet Domain

Jayanthi¹,

Sridevi²

2018

IJET

View full text Add to dashboard Cite

Medical image watermarking which hides patient's information in the medical image ensures its imperceptibility and at the same time provides robustness to the information that is embedded. Current research scenario embeds the authenticated message as watermark in the frequency domain to get watermarked image which has most of its values as real numbers. Since pixel intensity values must be represented as integers, the watermarked image is converted into spatial domain where the rounding error problem occurs and the embedded message cannot be extracted to prove its authenticity. In proposed work, a new watermarking scheme in Discrete Wavelet Transform (DWT) domain based on Genetic Algorithm (GA) is implemented to ensure correct retrieval of embedded watermark by optimizing Mean Square Error (MSE) measure.

show abstract

Optimization of Stego Image Retaining Secret Information Using Genetic Algorithm with 8-connected PSNR

Cited by 27 publications

References 12 publications

MFDC‐net: Multifeature‐based deep convolutional neural network for single image haze removal

MFDC‐net: Multifeature‐based deep convolutional neural network for single image haze removal

An intermediate significant bit (ISB) watermarking technique using neural networks

Mean Square Error Optimization to Authenticate Multi-Modality Medical Images in Wavelet Domain

Contact Info

Product

Resources

About