Higher Peak Signal To Noise Ratio Value Research Articles

Enhancing Black-and-White Image Colorization Using Cycle GAN: A Study on Unpaired Image Translation

Abstract. This paper explores the application of Cycle-Consistent Generative Adversarial Network (Cycle GAN) for the colorization of black-and-white images, addressing the challenges in image to the image translation and it was not requiring paired datasets. Cycle GAN, a generative adversarial network, uses cycle consistency loss to map grayscale images to color, effectively preserving structural integrity. The model is trained on unpaired datasets containing black-and-white and color images, enabling it to generate colorized versions from grayscale inputs. Performance evaluation is conducted using Two significant evaluation metrics: Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index (SSIM). Results demonstrate that Cycle GAN effectively preserves image structure and detail, achieving high PSNR and SSIM values, particularly in scenes with distinct color boundaries. However, challenges arise in complex and low-resolution scenes where color accuracy and detail reconstruction may degrade. Additionally, this paper assesses the impact of different loss functions, learning rate schedules, and training strategies on the models output quality. Future work will focus on addressing these limitations by incorporating attention mechanisms and other advanced techniques to improve Cycle GAN's ability to handle intricate image features and complex scenes.

Multi-Image Steganography

Steganography is the practice of concealing information within various types of data, encompassing the embedding of confidential content like messages, images, audio, or video within a cover image. The primary objective involves hiding the secret message or image within the selected image through the utilization of the Least Significant Bit (LSB) technique. To ensure the safeguarding and security of the concealed content, the Advanced Encryption Standard (AES) Algorithm is implemented. The comparison of different image formats, each varying in text length or image size, is conducted. The algorithm's efficacy is evaluated through metrics such as Peak Signal to Noise Ratio (PSNR) and Mean Square Error (MSE), with a higher PSNR value indicating a superior image quality. Steganography assumes a vital role in numerous applications, including but not limited to medical, military, One Time Password (OTP), and copyright protection. Key Words: Image steganography, LSB, Advanced Encryption Standard, PSNR Ratio, MSE

Compression Run Length Encoding On Watermarking Using a Combination of DCT, DWT and SVD

This study focus on identifying medical images by proposing the Discrete Wavelet Transform (DWT), Discrete Cosine Transform (DCT) and Singular Value Decomposition (SVD) transformation watermarking technique and prove an increase the quality of watermarked images is good in terms of imperceptibility. Due to reduce the need for data memory compression is applied to the host image, where the compression technique chosen is lossless so that the compressed host image experiences a decrease in file size while maintaining data integrity, to maintain image degradation perceptions and diagnostic quality standards during the watermarking process. Here, we use DWT-DCT-SVD and Run Length Encoding (RLE). A good Peak Signal to Noise Ratio (PSNR) more than 30 dB using over than 200 compression size. The extracted watermark image is quite good with a fairly high PSNR value. The highest compression result size is in 32.2511.

Secure Medical Image Communication Using Fragile Data Hiding Based on Discrete Wavelet Transform and A₅ Lattice Vector Quantization

Secure communication of medical images is essential to telemedicine. Message Authentication Codes (MAC) can be embedded inside medical images to protect their integrity. Fragile watermarking algorithms are suitable options since they can be used to detect any tampering attempt. In this paper, a novel fragile data-hiding algorithm based on Integer-to-Integer Discrete Wavelet Transforms (IIDWT) and <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$A_{5}$ </tex-math></inline-formula> Lattice Vector Quantization (LVQ) is proposed. In the proposed data-hiding algorithm, a combination of the medical image Metadata and a MAC is embedded into the medical image. The Metadata includes information about the patient such as name, family, birthday, the place where it is created such as the name of the hospital, and the physician’s name. To preserve the privacy of the patients and the physician/hospital, the Metadata is then replaced with fake information. The receiver can extract the Metadata and the MAC. If the extracted MAC is the same as the expected MAC, the integrity of the medical image is guaranteed. Otherwise, a tampering attempt is detected. The proposed algorithm can embed 50% more data than similar algorithms in medical images while keeping the Peak Signal to Noise Ratio (PSNR) in acceptable ranges. Furthermore, the proposed algorithm is applied to a dataset of medical images and high PSNR values above 53.88 dB are experienced.

New Real-Time Impulse Noise Removal Method Applied to Chest X-ray Images.

In this paper, we propose a new Modified Laplacian Vector Median Filter (MLVMF) for real-time denoising complex images corrupted by "salt and pepper" impulsive noise. The method consists of two rounds with three steps each: the first round starts with the identification of pixels that may be contaminated by noise using a Modified Laplacian Filter. Then, corrupted pixels pass a neighborhood-based validation test. Finally, the Vector Median Filter is used to replace noisy pixels. The MLVMF uses a 5 × 5 window to observe the intensity variations around each pixel of the image with a rotation step of π/8 while the classic Laplacian filters often use rotation steps of π/2 or π/4. We see better identification of noise-corrupted pixels thanks to this rotation step refinement. Despite this advantage, a high percentage of the impulsive noise may cause two or more corrupted pixels (with the same intensity) to collide, preventing the identification of noise-corrupted pixels. A second round is then necessary using a second set of filters, still based on the Laplacian operator, but allowing focusing only on the collision phenomenon. To validate our method, MLVMF is firstly tested on standard images, with a noise percentage varying from 3% to 30%. Obtained performances in terms of processing time, as well as image restoration quality through the PSNR (Peak Signal to Noise Ratio) and the NCD (Normalized Color Difference) metrics, are compared to the performances of VMF (Vector Median Filter), VMRHF (Vector Median-Rational Hybrid Filter), and MSMF (Modified Switching Median Filter). A second test is performed on several noisy chest x-ray images used in cardiovascular disease diagnosis as well as COVID-19 diagnosis. The proposed method shows a very good quality of restoration on this type of image, particularly when the percentage of noise is high. The MLVMF provides a high PSNR value of 5.5% and a low NCD value of 18.2%. Finally, an optimized Field-Programmable Gate Array (FPGA) design is proposed to implement the proposed method for real-time processing. The proposed hardware implementation allows an execution time equal to 9 ms per 256 × 256 color image.

High capacity video hiding based on multi-resolution stationary wavelet transform and hybrid-matrix decomposition techniqueset Transform and hybrid-matrix decomposition techniques

Internet simplified digital data transferring. This data needs to be secured; so securing digital data becomes an important concern. Steganography provides security for data by inserting it into a cover and concealing it. In this paper, a steganography algorithm was introduced. This algorithm used the stationary wavelet transform (SWT) and اhybrid-matrix decomposition techniques, singular value decomposition (SVD) and QR factorization to conceal a video in another video. The algorithm performance was measured with reference to the peak signal to noise ratio (PSNR) and structural similarity index measure (SSIM) for the cover and the secret videos. The algorithm successfully hid a video in another cover video and both are of the same size; the hiding capacity was 100%. The algorithm achieved a SSIM that reached 0.97 and a high PSNR value that reached 68.8 proving that the imperceptibility of the proposed algorithm is very high. The comparative analysis shows that the suggested algorithm achieved higher imperceptibility than the other state-of-the-art algorithms regarding the average PSNR. The enhanced version of the proposed method was more robust against different types of attacks.

Imperceptible Image Steganography Using Symmetry-Adapted Deep Learning Techniques

Digital image steganography is the process of embedding information within a cover image in a secure, imperceptible, and recoverable way. This research extends a symmetry-adapted deep-learning approach to identify hidden patterns of images using two-dimensional convolutional neural networks (CNN). The proposed method (SteGuz) uses three CNNs to implement the different phases of the steganography process on digital image covers. SteGuz introduced a gain function, based on several image similarity metrics, to maximize the imperceptibility of the hiding process. Using 10 different pairs of cover-secret images, the performance of the proposed method was measured in terms of standard metrics such as peak signal to noise ratio (PSNR) and structured similarity index measurement (SSIM). The results showed that the proposed methodology outperformed the original method in terms of both imperceptibility and recoverability. In addition, when compared with some existing methods, SteGuz proved the outstanding performance of achieving a very high PSNR value while maintaining high accuracy of the extracted image.

Design and Analysis of Reversible Data Hiding Using Hybrid Cryptographic and Steganographic approaches for Multiple Images

Data concealing is the process of including some helpful information on images. The majority of sensitive applications, such sending authentication data, benefit from data hiding. Reversible data hiding (RDH), also known as invertible or lossless data hiding in the field of signal processing, has been the subject of a lot of study. A piece of data that may be recovered from an image to disclose the original image is inserted into the image during the RDH process to generate a watermarked image. Lossless data hiding is being investigated as a strong and popular way to protect copyright in many sensitive applications, such as law enforcement, medical diagnostics, and remote sensing. Visible and invisible watermarking are the two types of watermarking algorithms. The watermark must be bold and clearly apparent in order to be visible. To be utilized for invisible watermarking, the watermark must be robust and visibly transparent. Reversible data hiding (RDH) creates a marked signal by encoding a piece of data into the host signal. Once the embedded data has been recovered, the original signal may be accurately retrieved. For photos shot in poor illumination, visual quality is more important than a high PSNR number. The DH method increases the contrast of the host picture while maintaining a high PSNR value. Histogram equalization may also be done concurrently by repeating the embedding process in order to relocate the top two bins in the input image's histogram for data embedding. It's critical to assess the images after data concealment to see how much the contrast has increased. Common picture quality assessments include peak signal to noise ratio (PSNR), relative structural similarity (RSS), relative mean brightness error (RMBE), relative entropy error (REE), relative contrast error (RCE), and global contrast factor (GCF). The main objective of this paper is to investigate the various quantitative metrics for evaluating contrast enhancement. The results show that the visual quality may be preserved by including a sufficient number of message bits in the input photographs.

Secured Medical Data Transfer Using Reverse Data Hiding System Through Steganography

Reversible Data Hiding (RDH) is the process of transferring secret data hidden inside cover media to the recipient so the recipient can securely retrieve both the secret data and cover media. The RDH approach is applied in this study in the field of telemedicine, and medical-secret data is conveyed privately via medical cover video. Morse code-based data encryption technique tends to encrypt the medical-secret data by compression using the Arithmetic coding technique. Discrete Shearlet transform (DST) compresses the selected frame from the medical cover video and the compressed secret data is embedded into the compressed frame using logical operations. On a receiver side, the reversal process is carried over and the original cover frame will be retrieved from the stego frame after secret medical data is retrieved. Password is included on the receiver side for authentication purposes. Parameters such as encryption time, compression ratio, Mean Square Error (MSE) and Peak Signal to Noise Ratio (PSNR) are calculated and at the maximum iteration of the proposed algorithm, the highest PSNR value is achieved. In terms of Structural Similarity Index Measure (SSIM), a linear increase from 0.91 to 0.99 is evident for iterations. In comparison with other techniques, the proposed algorithm reaches a higher SSIM of 0.999 after the maximum number of iterations. Thus, the proposed method provides more security and authentication to the recipient.

Reversible Watermarking Method with Low Distortion for the Secure Transmission of Medical Images

In telemedicine, the realization of reversible watermarking through information security is an emerging research field. However, adding watermarks hinders the distribution of pixels in the cover image because it creates distortions (which lead to an increase in the detection probability). In this article, we introduce a reversible watermarking method that can transmit medical images with minimal distortion and high security. The proposed method selects two adjacent gray pixels whose least significant bit (LSB) is different from the relevant message bit and then calculates the distortion degree. We use the LSB pairing method to embed the secret matrix of patient record into the cover image and exchange pixel values. Experimental results show that the designed method is robust to different attacks and has a high PSNR (peak signal-to-noise ratio) value. The MRI image quality and imperceptibility are verified by embedding a secret matrix of up to 262,688 bits to achieve an average PSNR of 51.657 dB. In addition, the proposed algorithm is tested against the latest technology on standard images, and it is found that the average PSNR of our proposed reversible watermarking technology is higher (i.e., 51.71 dB). Numerical results show that the algorithm can be extended to normal images and medical images.

A Rician Noise Prediction and Removal Model for MRI Head Scans using wavelet based Non-Local Median Filter

In the medical imaging field, anatomical structure preservation is a difficult task during the denoising process. Magnetic resonance imaging (MRI) scanner corrupts the images by the Rician noise during the acquisition process. Rician noise affects the diagnosis and treatment planning for the subjects. Regenerating noise-free images is a time-consuming process with limited MR scanner resources available in developing countries. Therefore, the medical industry utilizes the advancement of computer-aided automatic denoising methods. This article presents a novel denoising method for Rician noise using a wavelet-based non-local median filtering (WNLMed) technique. The work contains three phases: noise estimation, wavelet thresholding using a lifting scheme, and non-local median filter (NLMed). Materials used for this experiment are collected from the Brainweb repositories and tested with validation metrics such as normalized absolute error (NAE), peak signal to noise ratio (PSNR), structure similarity index measure (SSIM), the figure of merit (FOM), and compared with the state-of-the-art methods. The method yields high PSNR value than other methods.

Morphological Based Medical Image Processing on Cervical Cytology Cancer Images Using Connected Component Techniques.

Cervical cancer is the fourth most common cancer in women. In 2018, it was estimated 570000 women were diagnosed with cervical cancer worldwide and about 311000 women died from the disease. An efficient technique is essential for solving the complication in the diagnosis of cervical cancer images. In this research, a new method is developed for cervical cancer image segmentation. First, the RGB image is converted into an HSI color model. The thresholding is applied to the saturation and intensity components to get binary images. These binary images are combined to get a new mask. Using the connected component concept nucleus and cytoplasm are segmented accurately. For the performance evaluation, peak signal-to-noise ratio (PSNR), mean square error (MSE), structural similarity index (SSIM), image quality index (IQI), structural content (SC), normalized cross-correlation (NK), precision (PR), recall (RC), the Average Difference (AD) and image fidelity (IF) are taken. The proposed techniques' highest PSNR values are 44.2341, 46.7953, 60.5925, and 61.4862, respectively. The proposed segmentation technique can attain a high PSNR (>40db) value at a threshold value equal to 0.1. Also proposed approach attains good precision, recall, and SSIM values. The lowest MSE values using proposed segmentation techniques are 0.0454, 0.0351, 0.0924, and 0.0271 individually. The AD, NK, SC, NAE, and LMSE values for the implemented approach are low, showing the segmented image's quality is very good. Thus, the proposed model performed better compared to other methods.

DE-NOISING OF TOMATO FRUIT IMAGE USING SPIRAL SEED FILTER

Fruit disease causes more economic losses in agricultural industry. In prediction of disease image pre-processing plays an important role. Fruits may appear healthy and fresh to human eye but its quality is known by customer after eating the fruits. Images are used to forecast quality of the fruits and vegetables, but accuracy of grading will be affected by distortion. Various noise affect the quality of the image and it can be denoised by various filters. The preservative edges, background information and contrast of images are the challenging issues in exiting filtering methods. This research proposed Spiral Seed Filter (SSF) to increase the quality of the tomato fruit image by extracting the luma variance and by applying the row wise and column wise 3x3 cross correlation. The result shows that the proposed filter increases the PSNR (Peak Signal to Noise ratio) and reduces MSE (Mean Square Error) metric values and yield good results. It gives highest PSNR value such as 94.68. It gives 0.0001 as MSE value for proposed method.

Retinal Digital Image Quality Improvement as A Diabetes Retinopatic Disease Detection Effort

Image processing is a technical term useful for modifying images in various ways. In medicine, image processing has a vital role. One example of images in the medical world, namely retinal images, can be obtained from a fundus camera. The retina image is useful in the detection of diabetic retinopathy. In general, direct observation of diabetic retinopathy is conducted by a doctor on the retinal image. The weakness of this method is the slow handling of the disease. For this reason, a computer system is required to help doctors detect diabetes retinopathy quickly and accurately. This system involves a series of digital image processing techniques that can process retinal images into good quality images. In this research, a method to improve the quality of retinal images was designed by comparing the methods for adjusting histogram equalization, contrast stretching, and increasing brightness. The performance of the three methods was evaluated using Mean Square Error (MSE), Peak Signal to Noise Ratio (PSNR), and Signal to Noise Ratio (SNR). Low MSE values and high PSNR and SNR values indicated that the image had good quality. The results of the study revealed that the image was the best to use, as evidenced by the lowest MSE values and the highest SNR and PSNR values compared to other techniques. It indicated that adaptive histogram equalization techniques could improve image quality while maintaining its information.

Low-dose CT reconstruction method based on prior information of normal-dose image.

Radiation risk from computed tomography (CT) is always an issue for patients, especially those in clinical conditions in which repeated CT scanning is required. For patients undergoing repeated CT scanning, a low-dose protocol, such as sparse scanning, is often used, and consequently, an advanced reconstruction algorithm is also needed. To develop a novel algorithm used for sparse-view CT reconstruction associated with the prior image. A low-dose CT reconstruction method based on prior information of normal-dose image (PI-NDI) involving a transformed model for attenuation coefficients of the object to be reconstructed and prior information application in the forward-projection process was used to reconstruct CT images from sparse-view projection data. A digital extended cardiac-torso (XCAT) ventral phantom and a diagnostic head phantom were employed to evaluate the performance of the proposed PI-NDI method. The root-mean-square error (RMSE), peak signal-to-noise ratio (PSNR) and mean percent absolute error (MPAE) of the reconstructed images were measured for quantitative evaluation of the proposed PI-NDI method. The reconstructed images with sparse-view projection data via the proposed PI-NDI method have higher quality by visual inspection than that via the compared methods. In terms of quantitative evaluations, the RMSE measured on the images reconstructed by the PI-NDI method with sparse projection data is comparable to that by MLEM-TV, PWLS-TV and PWLS-PICCS with fully sampled projection data. When the projection data are very sparse, images reconstructed by the PI-NDI method have higher PSNR values and lower MPAE values than those from the compared algorithms. This study presents a new low-dose CT reconstruction method based on prior information of normal-dose image (PI-NDI) for sparse-view CT image reconstruction. The experimental results validate that the new method has superior performance over other state-of-art methods.

Reversible data hiding with segmented secrets and smoothed samples in various audio genres

In this age, information technology has grown significantly. Computer networks, which connect a device to others, have made it easier for people to transfer data than before. Moreover, smart devices have the capability of supporting this data transmission, including those in the cloud that may contain massive data. However, the security factor can be a severe issue if sensitive big data, such as military and medical data, do not have enough protection. Furthermore, an attacker may be able to disclose such data. Some algorithms have been introduced to solve that problem, one of which is the data hiding method. Nevertheless, some factors are still challenging, concerning the capacity of the secret data and the quality of the generated data, which are represented by bit and Peak Signal-to-Noise Ratio (PSNR), respectively. Besides, some techniques are not reversible, which means that they cannot reconstruct the carrier (cover). In this research, we investigate those problems by taking audio as the carrier. It is done by sampling the audio file before being interpolated to present spaces for accommodating the secret. Meanwhile, the secret is segmented before the embedding. Later, the embedded audio is smoothed according to the required level. The experimental result is obtained by using a public data set containing various audio genres and instruments, and 11 secret sizes, from 1 to 100 kb. It shows that the proposed method outperforms the others. This higher PSNR value means that the proposed method can generate more similar stego data; it also implies that at a certain quality level, the number of bits that can be hidden in the audio cover is higher than that of others.

A Juxtaposition Between Integer Wavelet Transform and Discrete Wavelet Transform for Secure Image Steganography

Image steganography is a technique that is used to hide information. The information can be of various types like image, video, or audio. Steganography is done so that no one apart from the correct receiver can retrieve the information. This paper consists of all advantages and highlights of the wavelet transform but with the additional features like randomness and some default values that are already built-in it. Various algorithms can be used in steganography and they provide good hiding capacity and low detectability. Here we have hidden the image into the cover image using Integer Wavelet Transform (IWT) and also using Discrete Wavelet Transform (DWT) and compared which technique gives better results. It is very difficult to predict the presence of a hidden image inside the stego image since it looks exactly like the cover image. There is no loss in quality from the secret image to the extracted image since the PSNR (Peak Signal to noise ratio) is high for both of them. This process was done using both DWT and IWT and the results prove that that the IWT technique is not only simpler but also more efficient than the DWT technique since it gives higher PSNR values. Through the proposed algorithm, an increase in the strength and imperceptibility is noticed and it can also maintain various transformations such as scaling, translation, and rotation with algorithms that already exist. The final results, after comparing both the transforms prove that the algorithm which is being proposed in IWT is indeed effective

A Combination of Hill Cipher and LSB for Image Security

The maximum value obtained to test the encrypt hill cipher uses the avalanche effect with modification of one, two, three, and four key matrices 35.71%, therefore an additional security technique is needed. The Least Significant Bit (LSB) method is used to insert the ciphertext that has been generated from the hill cipher algorithm, has been testing using RGB, CMY, CMYK and YUV shapes with 6142 characters in 128 x 128 character images producing the highest PSNR value of 51.2826 dB in CMYK images. Steganography technique is applied because it has advantages in terms of imperceptibility, for example the results of a stego image are so similar to the original image that it is difficult to be distinguished by the human senses. Tests were carried out with 10 images, five images measuring 512 x 512 and five images measuring 16 x 16. While the messages to be inserted were 240, 480, and 960 characters for images measuring 512 x 512 and 24, 48 and 88 characters for images measuring 16 x16. Test results that I have done are calculated using Mean Square Error (MSE) and Peak Signal to Noise Ratio (PSNR) with a minimum PSNR of 51.2907 dB which means the resulting image is quite good. Computation time is calculated using tic toc on Matlab by encrypting 2000 and 6000 characters, and also computation time.

Video Super-Resolution using Multi-Frames Fusion and Perceptual Loss

Video super-resolution (VSR) has become more and more important in vision perception. Currently, most of video super-resolution methods used optical flow estimation by explicit motion compensation. We proposed a new network using multi-frames as input without motion compensation. In order to improve the performance of the reconstructed high-resolution (HR) frame, perceptual loss function is used to evaluate the deviation between the prediction and ground truth. Perceptual loss characteristic is able to improve the quality of image reconstruction on the vision, but with a low Peak Signal to Noise Ratio (PSNR). Experimental results show that compared with other methods, our model can recover more details in high-resolution image, although it does not get higher PSNR value.

Image steganography based on LSB substitution and encryption method: adaptive LSB+3

The goals of image steganography are to simultaneously reach maximum embedding capacity, enhanced embedding efficiency, better image quality, and more security. We present a two-step data hiding method that improves image quality, capacity, and embedding efficiency, and also provides stego security. In the first step of the proposed method, the hidden data are encrypted with the key words and shifting method to provide security. In the second stage, we propose adaptive least-significant-bit (LSB)+3 type I and adaptive LSB+3 type II methods to hide encrypted data in the cover image. The image quality of the stego image obtained from the proposed adaptive LSB+3 method is better than the traditional three-bit LSB methods. When maximum data are embedded in the cover image, a peak signal-to-noise ratio (PSNR) greater than 41 dB is reached. Experimental studies show that adaptive LSB+3 type I and adaptive LSB+3 type II methods are higher PSNR values (3.48% and 5.73%) than the standard three-bit LSB substitution methods.