PSNR Research Articles

Detection of individual brain tau deposition in Alzheimer's disease based on latent feature-enhanced generative adversarial network

The conventional methods for interpreting tau PET imaging in Alzheimer's disease (AD), including visual assessment and semi-quantitative analysis of fixed hallmark regions, are insensitive to detect individual small lesions because of the spatiotemporal neuropathology's heterogeneity. In this study, we proposed a latent feature-enhanced generative adversarial network model for the automatic extraction of individual brain tau deposition regions. The latent feature-enhanced generative adversarial network we propose can learn the distribution characteristics of tau PET images of cognitively normal individuals and output the abnormal distribution regions of patients. This model was trained and validated using 1131 tau PET images from multiple centres (with distinct races, i.e., Caucasian and Mongoloid) with different tau PET ligands. The overall quality of synthetic imaging was evaluated using structural similarity (SSIM), peak signal to noise ratio (PSNR), and mean square error (MSE). The model was compared to the fixed templates method for diagnosing and predicting AD. The reconstructed images archived good quality, with SSIM = 0.967 ± 0.008, PSNR = 31.377 ± 3.633, and MSE = 0.0011 ± 0.0007 in the independent test set. The model showed higher classification accuracy (AUC = 0.843, 95 % CI = 0.796-0.890) and stronger correlation with clinical scales (r = 0.508, P < 0.0001). The model also achieved superior predictive performance in the survival analysis of cognitive decline, with a higher hazard ratio: 3.662, P < 0.001. The LFGAN4Tau model presents a promising new approach for more accurate detection of individualized tau deposition. Its robustness across tracers and races makes it a potentially reliable diagnostic tool for AD in practice.

Generative adversarial network-based synthesis of contrast-enhanced MR images from precontrast images for predicting histological characteristics in breast cancer

Objective. Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) is a sensitive tool for assessing breast cancer by analyzing tumor blood flow, but it requires gadolinium-based contrast agents, which carry risks such as brain retention and astrocyte migration. Contrast-free MRI is thus preferable for patients with renal impairment or who are pregnant. This study aimed to investigate the feasibility of generating contrast-enhanced MR images from precontrast images and to evaluate the potential use of synthetic images in diagnosing breast cancer. Approach. This retrospective study included 322 women with invasive breast cancer who underwent preoperative DCE-MRI. A generative adversarial network (GAN) based postcontrast image synthesis (GANPIS) model with perceptual loss was proposed to generate contrast-enhanced MR images from precontrast images. The quality of the synthesized images was evaluated using the peak signal-to-noise ratio (PSNR) and structural similarity (SSIM). The diagnostic performance of the generated images was assessed using a convolutional neural network to predict Ki-67, luminal A and histological grade with the area under the receiver operating characteristic curve (AUC). The patients were divided into training (n = 200), validation (n = 60), and testing sets (n = 62). Main results. Quantitative analysis revealed strong agreement between the generated and real postcontrast images in the test set, with PSNR and SSIM values of 36.210 ± 2.670 and 0.988 ± 0.006, respectively. The generated postcontrast images achieved AUCs of 0.918 ± 0.018, 0.842 ± 0.028 and 0.815 ± 0.019 for predicting the Ki-67 expression level, histological grade, and luminal A subtype, respectively. These results showed a significant improvement compared to the use of precontrast images alone, which achieved AUCs of 0.764 ± 0.031, 0.741 ± 0.035, and 0.797 ± 0.021, respectively. Significance. This study proposed a GAN-based MR image synthesis method for breast cancer that aims to generate postcontrast images from precontrast images, allowing the use of contrast-free images to simulate kinetic features for improved diagnosis.

Metal Artifact Correction in Industrial CT Images Based on a Dual-Domain Joint Deep Learning Framework

Industrial computed tomography (CT) images reconstructed directly from projection data using the filtered back projection (FBP) method exhibit strong metal artifacts due to factors such as beam hardening, scatter, statistical noise, and deficiencies in the reconstruction algorithms. Traditional correction approaches, confined to either the projection domain or the image domain, fail to fully utilize the rich information embedded in the data. To leverage information from both domains, we propose a joint deep learning framework that integrates UNet and ResNet architectures for the correction of metal artifacts in CT images. Initially, the UNet network is employed to correct the imperfect projection data (sinograms), the output of which serves as the input for the CT image reconstruction unit. Subsequently, the reconstructed CT images are fed into the ResNet, with both networks undergoing a joint training process to optimize image quality. We take the projection data obtained by analytical simulation as the data set. The resulting optimized industrial CT images show a significant reduction in metal artifacts, with the average Peak Signal-to-Noise Ratio (PSNR) reaching 36.13 and the average Structural Similarity Index (SSIM) achieving 0.953. By conducting simultaneous correction in both the projection and image domains, our method effectively harnesses the complementary information from both, exhibiting a marked improvement in correction results over the deep learning-based single-domain corrections. The generalization capability of our proposed method is further verified in ablation experiments and multi-material phantom CT artifact correction.

Chromatic Aberration Correction in Harmonic Diffractive Lenses Based on Compressed Sensing Encoding Imaging

Large-aperture, lightweight, and high-resolution imaging are hallmarks of major optical systems. To eliminate aberrations, traditional systems are often bulky and complex, whereas the small volume and light weight of diffractive lenses position them as potential substitutes. However, their inherent diffraction mechanism leads to severe dispersion, which limits their application in wide spectral bands. Addressing the dispersion issue in diffractive lenses, we propose a chromatic aberration correction algorithm based on compressed sensing. Utilizing the diffractive lens’s focusing ability at the reference wavelength and its degradation performance at other wavelengths, we employ compressed sensing to reconstruct images from incomplete image information. In this work, we design a harmonic diffractive lens with a diffractive order of M=150, an aperture of 40 mm, a focal length f0=320 mm, a reference wavelength λ0=550 nm, a wavelength range of 500–800 nm, and 7 annular zones. Through algorithmic recovery, we achieve clear imaging in the visible spectrum, with a peak signal-to-noise ratio (PSNR) of 22.85 dB, a correlation coefficient of 0.9596, and a root mean square error (RMSE) of 0.02, verifying the algorithm’s effectiveness.

A cycle generative adversarial network for generating synthetic contrast-enhanced computed tomographic images from non-contrast images in the internal jugular lymph node-bearing area.

The objectives of this study were to create a mutual conversion system between contrast-enhanced computed tomography (CECT) and non-CECT images using a cycle generative adversarial network (cycleGAN) for the internal jugular region. Image patches were cropped from CT images in 25 patients who underwent both CECT and non-CECT imaging. Using a cycleGAN, synthetic CECT and non-CECT images were generated from original non-CECT and CECT images, respectively. The peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM) were calculated. Visual Turing tests were used to determine whether oral and maxillofacial radiologists could tell the difference between synthetic versus original images, and receiver operating characteristic (ROC) analyses were used to assess the radiologists' performances in discriminating lymph nodes from blood vessels. The PSNR of non-CECT images was higher than that of CECT images, while the SSIM was higher in CECT images. The Visual Turing test showed a higher perceptual quality in CECT images. The area under the ROC curve showed almost perfect performances in synthetic as well as original CECT images. In conclusion, synthetic CECT images created by cycleGAN appeared to have the potential to provide effective information in patients who could not receive contrast enhancement.

Discerning Reality through Haze: An Image Dehazing Network Based on Multi-Feature Fusion

Numerous single-image dehazing algorithms have been developed, employing a spectrum of techniques ranging from intricate physical computations to state-of-the-art deep-learning methodologies. However, conventional deep-learning approaches, particularly those based on standard convolutional neural networks (CNNs), often result in the persistence of residual fog patches when applied to images featuring high fog concentration or heterogeneous fog distribution. In response to this challenge, we propose an innovative solution known as the multi-feature fusion image dehazing network (MFID-Net). This approach employs an end-to-end methodology to directly capture the mapping relationship between hazy and fog-free images. Central to our approach is the introduction of a novel multi-feature fusion (MF) module, strategically designed to address channel and pixel characteristics in regions with uneven or high fog concentrations. Notably, this module achieves effective haze reduction while minimizing computational resources, thereby mitigating the issue of residual fog patches. Experimental results underscore the superior performance of our algorithm compared to similar dehazing methods, as evidenced by higher scores in structural similarity (SSIM), peak signal-to-noise ratio (PSNR), and computational velocity. Moreover, MFID-Net exhibits significant advancements in restoring details within expansive monochromatic areas, such as skies and white walls.

Scalable Video Fidelity Enhancement: Leveraging the state-of-the-art AI Models

Improving visual quality is crucial as we navigate through the vast world of data. State-of-the-art (SOTA) artificial intelligence (AI) models provide highly effective solutions. Driven by the ever-growing demand for high-fidelity multimedia content, this research explores the groundbreaking capabilities of SOTA AI models to revolutionize video quality enhancement. Existing video capture methods often struggle with limitations in hardware, bandwidth, and compression, leading to subpar visual experiences. To address this challenge, we propose a novel Video Quality Enhancement Solution (VQES) that synergistically combines Google FILM for frame interpolation and Real-ESRGAN for image super-resolution. By applying these models to each video frame and integrating scalable post-processing techniques, a comprehensive VQES has been devised. Extensive experiments demonstrate that our VQES outperforms existing methods in terms of peak signal-to-noise ratio (PSNR) improvement and user-perceived visual quality. By advancing video fidelity, this research paves the way for consistently immersive, informative, and enjoyable visual experiences.

Super-Resolution for Land Surface Temperature Retrieval Images via Cross-Scale Diffusion Model Using Reference Images

Geothermal resources are efficient, clean, and renewable energy sources. Using high-resolution images captured by remote sensing satellites for temperature retrieval and searching for geothermal anomaly areas is an efficient method. However, obtaining land surface temperature retrieval images requires multiple steps of calculation, which can result in a great loss of image information and resolution. Therefore, the super-resolution reconstruction of LST retrieval images is currently a challenge in geothermal resource exploration. Although the current super-resolution methods for LST retrieval images can appropriately restore image quality, the overall restoration of the surface temperature information in the region is still not ideal. We propose a cross-scale reference image super-resolution model based on a diffusion model using deep learning technology. First, we propose the Pre-Super-Resolution Network (PreNet), which can improve both indices and the visual effect of images. Second, to reduce the white noise in the super-resolution images, we propose the Cross-Scale Reference Image Attention Mechanism (CSRIAM). The introduction of this mechanism greatly reduces noise in the images and improves the overall image quality. Compared to previous methods, we improved both experimental indices such as Peak Signal-to-Noise Ratio (PSNR), Structural Similarity (SSIM), etc., and vision quality, and optimized the recovery of geothermal anomalies. Through our experimental results, we found that the CS-Diffusion model has a very strong ability to restore the image quality of the LST retrieval. After restoring its image quality, we can make a positive contribution to subsequent geothermal resource exploration.

Image de-photobombing benchmark

AbstractRemoving photobombing elements from images is a challenging task that requires sophisticated image inpainting techniques. Despite the availability of various methods, their effectiveness depends on the complexity of the image and the nature of the distracting element. To address this issue, we conducted a benchmark study to evaluate 10 state-of-the-art photobombing removal methods on a dataset of over 300 images. Our study focused on identifying the most effective image inpainting techniques for removing unwanted regions from images. We annotated the photobombed regions that require removal and evaluated the performance of each method using peak signal-to-noise ratio (PSNR), structural similarity index (SSIM), and Fréchet inception distance (FID). The results show that image inpainting techniques can effectively remove photobombing elements, but more robust and accurate methods are needed to handle various image complexities. Our benchmarking study provides a valuable resource for researchers and practitioners to select the most suitable method for their specific photobombing removal task.

Rotational Convolution Design in Convolutional Neural Networks for Direct 3D Electromagnetic Tomography

The three-dimensional (3D) reconstruction of Electromagnetic Tomography (EMT) is an important task for many applications, such as the non-destructive testing of inner defects in rail systems. Additionally, image reconstruction algorithms utilizing deep learning methods have been verified to be useful in recent years. Therefore, the interpretability of deep learning is a question that is relevant to its application in other areas. This paper proposes an innovative rotational convolution pattern, Conv-P, for convolutional neural network (CNN) image reconstruction in a 3D EMT system. This pattern is based on the projection relationships inherent in tomographic imaging, where each convolution is performed on adjacent projections along the excitation rotation direction. The advantage of this pattern is that it can generate the convolution process by utilizing the 3D structural information from real sensors. To verify the effectiveness of this convolution pattern, we constructed a 3D dual-layer 16-coil EMT model and tested its image reconstruction performance. The results demonstrate that, compared with two common convolution patterns, Conv-P achieves a 4.7% and 4.1% increase in the Image Correlation Coefficient (CC), a 19.8% and 13.1% reduction in the Relative Image Error (IE), a 0.67% and 1.59% increase in the Peak Signal-to-Noise Ratio (PSNR), and a 3.24% and 0.74% increase in the Structural Similarity Index Measure (SSIM).

Full-dose whole-body PET synthesis from low-dose PET using high-efficiency denoising diffusion probabilistic model: PET consistency model.

Positron Emission Tomography (PET) has been a commonly used imaging modality in broad clinical applications. One of the most important tradeoffs in PET imaging is between image quality and radiation dose: high image quality comes with high radiation exposure. Improving image quality is desirable for all clinical applications while minimizing radiation exposure is needed to reduce risk to patients. We introduce PET Consistency Model (PET-CM), an efficient diffusion-based method for generating high-quality full-dose PET images from low-dose PET images. It employs a two-step process, adding Gaussian noise to full-dose PET images in the forward diffusion, and then denoising them using a PET Shifted-window Vision Transformer (PET-VIT) network in the reverse diffusion. The PET-VIT network learns a consistency function that enables direct denoising of Gaussian noise into clean full-dose PET images. PET-CM achieves state-of-the-art image quality while requiring significantly less computation time than other methods. Evaluation with normalized mean absolute error (NMAE), peak signal-to-noise ratio (PSNR), multi-scale structure similarity index (SSIM), normalized cross-correlation (NCC), and clinical evaluation including Human Ranking Score (HRS) and Standardized Uptake Value (SUV) Error analysis shows its superiority in synthesizing full-dose PET images from low-dose inputs. In experiments comparing eighth-dose to full-dose images, PET-CM demonstrated impressive performance with NMAE of 1.278±0.122%, PSNR of 33.783±0.824dB, SSIM of 0.964±0.009, NCC of 0.968±0.011, HRS of 4.543, and SUV Error of 0.255±0.318%, with an average generation time of 62 s per patient. This is a significant improvement compared to the state-of-the-art diffusion-based model with PET-CM reaching this result 12× faster. Similarly, in the quarter-dose to full-dose image experiments, PET-CM delivered competitive outcomes, achieving an NMAE of 0.973±0.066%, PSNR of 36.172±0.801dB, SSIM of 0.984±0.004, NCC of 0.990±0.005, HRS of 4.428, and SUV Error of 0.151±0.192% using the same generation process, which underlining its high quantitative and clinical precision in both denoising scenario. We propose PET-CM, the first efficient diffusion-model-based method, for estimating full-dose PET images from low-dose images. PET-CM provides comparable quality to the state-of-the-art diffusion model with higher efficiency. By utilizing this approach, it becomes possible to maintain high-quality PET images suitable for clinical use while mitigating the risks associated with radiation. The code is availble at https://github.com/shaoyanpan/Full-dose-Whole-body-PET-Synthesis-from-Low-dose-PET-Using-Consistency-Model.

A novel approach toward optimized image processing using sigma delta modulation

Image processing has widespread uses practically in every branch of science and arts. Processing images is more difficult than processing sound or data as there are more bits in the high pixel quality image. It requires more space to store the image, more bandwidth to transmit it, and more time and resources to process. An image's complexity may decrease if its bit size is decreased. Sigma-delta modulation, or SDM for short, is an alternative method of minimizing data-word length to compression. Digital signal processing (DSP) systems can be made simpler by using the SDM approach, which was first created for analog to digital conversion (ADC). This paper suggests a novel way to use SDM in MATLAB for improved image processing. Consequently, the suggested single-bit SDM-based image arithmetic architecture is tested and compared with the traditional image arithmetic techniques. Additionally, to see the noisy channel influence on the traditional and proposed systems, some statistical metrics are also studied at different noise variance values, such as signal to noise ratio (SNR), mean square error (MSE), and Peak SNR value. The suggested architecture for the SDM-based image arithmetic precisely matches the addition and subtraction results of the conventional design, even yielding a higher SNR and the same Peak SNR as the traditional methods. In contrast, the outcomes of division and multiplication fall within an acceptable range. For better results the over-sampling ratio (OSR), an inherent characteristic of SDM must be increased at the cost of more processing cycles. Therefore, the trade-off between fewer resources, limited transmission bandwidth, and comparatively more cycles is provided by the SDM-based technique.

Recognition of 3D Images by Fusing Fractional-Order Chebyshev Moments and Deep Neural Networks.

In order to achieve efficient recognition of 3D images and reduce the complexity of network parameters, we proposed a novel 3D image recognition method combining deep neural networks with fractional-order Chebyshev moments. Firstly, the fractional-order Chebyshev moment (FrCM) unit, consisting of Chebyshev moments and the three-term recurrence relation method, is calculated separately using successive integrals. Next, moment invariants based on fractional order and Chebyshev moments are utilized to achieve invariants for image scaling, rotation, and translation. This design aims to enhance computational efficiency. Finally, the fused network embedding the FrCM unit (FrCMs-DNNs) extracts depth features to analyze the effectiveness from the aspects of parameter quantity, computing resources, and identification capability. Meanwhile, the Princeton Shape Benchmark dataset and medical images dataset are used for experimental validation. Compared with other deep neural networks, FrCMs-DNNs has the highest accuracy in image recognition and classification. We used two evaluation indices, mean square error (MSE) and peak signal-to-noise ratio (PSNR), to measure the reconstruction quality of FrCMs after 3D image reconstruction. The accuracy of the FrCMs-DNNs model in 3D object recognition was assessed through an ablation experiment, considering the four evaluation indices of accuracy, precision, recall rate, and F1-score.

Dynamic iterative correction algorithm for designing diffractive optical elements

When utilizing the Gerchberg–Saxton (GS) algorithm to design diffractive optical elements, correction coefficients are introduced to improve the quality of the design results. The main design idea is to correct the target information dynamically during the iterative calculation process. The effectiveness of the proposed method is demonstrated through the verification of beam shaping and phase-type hologram designs. Compared to the traditional GS algorithm, the results of beam shaping show that the light intensity nonuniformity and the root-mean-square error (RMSE) of the shaped spot are reduced by an order of magnitude. The results of phase-type holograms show that the reconstructed image’s peak signal-to-noise ratio (PSNR) is improved by about 12 dB. Finally, the paper also discusses the selection of correction coefficients, providing insights into the selection of optimal design correction coefficients. The simulation and experimental results show that the improved algorithm proposed in this paper is not only simple in design but also highly efficient in obtaining a high-quality phase structure, which is of great help in designing high-quality diffractive optical elements.

Super-resolution reconstruction method of the optical synthetic aperture image using generative adversarial network

Abstract In order to solve the contradiction between large aperture elements and high-resolution images, in this study, we propose an improved image-resolution method based on generative adversarial network (GAN). First, we analyze the imaging principle of the optical synthetic aperture. Further, we improve a super-resolution GAN; especially, this network uses a multi-scale convolutional cascade to obtain global features of the image, and a multi-scale receptive field block and residual in residual dense block are built to obtain image details. In addition, this study uses the Mish function as the activation function of the discriminator to solve the problems of neuron extreme, gradient explosion, and poor generalization ability of the model. Through simulation, the results show that the proposed method can achieve a peak signal-to-noise ratio (PSNR) of 30 dB compared with traditional image super-resolution reconstruction methods for synthetic aperture image. The method proposed has an improvement of 2 dB in the PSNR and 0.016 in structure similarity index measure compared with the original super-resolution GAN. Therefore, this method can effectively reduce the image distortion and improve the quality of image reconstruction.

Hide Digital Images in Encrypted Image Files After Two Stages

This paper introduces a novel encryption technique for concealing digital images within encrypted files through a two-stage process. The methodology incorporates sparse coding and compressive sensing, leveraging a learned dictionary to recover the sparse coding of plain images. Comprising compressive sampling and random projection with a Gaussian measurement matrix, the approach achieves joint compression and encryption. Pseudorandom encryption and chaos-based block scrambling are subsequently applied to produce the final encrypted image. Experimental results using 256 × 256 test photographs from the USC-SIPI dataset demonstrate the superiority of the proposed method in terms of both Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index (SSIM). The study also conducts key sensitivity analysis, revealing the method's susceptibility to changes in the secret key, and statistical attack analysis, demonstrating its robustness against attacks exploiting statistical information. In conclusion, the proposed encryption technique not only ensures cryptographic strength but also excels in image reconstruction quality, making it a promising solution for secure image transmission and storage

Secure Pixel-Level Data Concealment: A Novel Approach for Securing Black and White Images within Color Images

In the era of rampant digital data transfer, concerns regarding the secure and reliable transmission of information persist, with numerous attempts at concealing and transporting data globally. Despite the plethora of existing techniques, issues persist, ranging from misinterpretation to malicious misuse of data during the transfer process. To address some of these challenges, this research introduces an innovative method centered on the modification of pixel data to embed concealed information. The primary objective is to alter pixel values in a manner that accommodates the storage of data pertaining specifically to black and white image pixel data. The proposed technique is designed to exclusively encode information related to two-pixel values, with careful adjustments made to ensure the masked image remains non-deceptive. Pixel values undergo subtle alterations to mitigate susceptibility issues associated with corner values, particularly at the border values of 254 and 255 for RGB values. The developed method presents a simplified yet robust data hiding technique, allowing the storage of black and white images within color images while achieving a high Peak Signal-to-Noise Ratio (PSNR) compared to standard ".png" images. Crucially, the developed approach addresses the challenge of minimizing drastic changes in pixel color, enhancing the overall fidelity of the stego image. Furthermore, the versatility of the proposed method is showcased by its potential to accommodate more than three images when the stego image size is appropriately large and segmented. A practical and efficient solution has been contributed to the persistent issues associated with secure data transfer, presenting a novel methodology for concealing black and white images within color images.

Development of Multi Modal Image Fusion Techniques in Night Vision Technology Using Deep Learning

This study is aimed at exploring new development in nighttime image processing based on nighttime photography/night vision. We use various learning methodologies based on neural networks to develop multisensor data processing techniques. The ability of Convolutional Neural Networks (CNN) to enhance image quality and clarity under conditions of low light or at night is the focus of our research. To do this A large database has been created, containing 3200 images both taken from the internet as well as our own. This data is preprocessed, normalized and features expanded using some common methods of data augmentation in order to optimize model performance. We compared our proposed CNN model with existing literature through a series of experiments. Performance was measured using Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index (SSIM), and Feature Similarity Index (FSIM). The Results are now in. They showed that our model can improve various metrics with higher scores. And they show the real-time monitoring capabilities in urban streets for our model. This research brings multisensor image fusion based on night-adjacent techniques forward from night vision technology and provides insight into practical and potential future directions for using deep learning techniques to improve safety and security in many different environments.

Enhancing Diagnostic Accuracy: A Hybrid Approach to Mitigate Speckle and Rician Noise in Medical Images

This research explores the detrimental effects of Rician and speckle noise in medical imaging, particularly within MRI and radiographic modalities. Such noise can significantly obscure critical details, potentially leading to misdiagnoses and inaccurate measurements. Rician noise candidly dangles on the signal strength. Removing this noise affects the origial information in image that makes this noise removal perplexing. On other hand speckle noise is visualised like granular clog in ultrasound imageries. It creates ambiguous details and edges in the images.   To address this challenge, the study introduces a novel hybrid method implemented in Java. The method employs a frequency-based decomposition approach for speckle noise and separates images into magnitude and phase components for Rician noise. This allows for targeted filtering, utilizing customized versions of median and Gaussian filters, to effectively remove noise while preserving crucial image features. The proposed method was rigorously assessed using 200 contaminated brain and lung MRIs and radiographs, demonstrating superior performance compared to traditional filters based on crucial system of measurement like Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index (SSIM), and Mean Squared Error (MSE). This research presents a promising solution for enhancing the quality and reliability of medical images, potentially leading to improved diagnostic accuracy and patient outcomes.

Framework for Image Denoising Employing Different Thresholding Techniques

Abstract:: Noise represents a lack of data in the image, which can be removed using image denoising. Image denoising can be achieved by Gaussian filtering, anisotropic filtering, wavelet thresholding, etc. In this work, wavelet-based denoising has been used because it can effectively remove both additive and multiplicative noise from images, and preserve fine details and edges in the image. In this work, different thresholding techniques, like Visu shrink and Bayes shrink for Hard Thresholding (HT) and Soft Thresholding (ST), employing different standard deviations ranging from 0.05-0.3 with a difference of 0.05, have been used. The Peak Signal-to-Noise Ratio (PSNR) has been evaluated as a performance parameter. For grayscale images, the maximum value of PSNR has been obtained as 29.483 dB, while for RGB images, a value of 34.324dB using Bayes shrink considering ST at 0.05 variance has been achieved. 2.2% improvement has been observed in grayscale images, while an 8.6% improvement has been observed in RGB images with Bayes shrink ST compared to Bayes shrink HT. Also, while comparing PSNR values of other thresholding techniques, ST has been found to provide better results than HT. The PSNR values for images produced by Bayes shrink have been found to be high, which implies the quality of reconstructed images to be better with Bayes shrink than with Visu shrink.