Structural Similarity Image Research Articles

Image semantic segmentation based on improved DeepLabv3+ network and superpixel edge optimization

Image semantic segmentation is a fundamental problem in the field of computer vision. Although the existing semantic segmentation model based on fully convolutional neural network continuously optimizes the segmentation effect, the inherent spatial invariance of the network still leads to cause the loss of object edge details. Moreover, most models use the pixel-by-pixel loss to optimize the target, and the dependencies between pixels are ignored. When facing objects with smaller spatial structures in the image, the segmentation result is not satisfactory. Based on the theory of relative entropy and mutual information, we propose an overall objective loss function that integrates pixel similarity and image structure similarity. It can better pay attention to the structure and detail information of small objects in space by modeling the dependency relationship between pixels. We use the DeepLabv3+ network based on group normalization, with the improved ResNet50 as the backbone. After that, considering the particular advantages of superpixel segmentation for object edges, we propose a superpixel edge optimization algorithm, which combines pixel-level semantic features and superpixel-level regional information to obtain the semantic segmentation results after edge optimization. Experiments on PASCAL VOC 2012 and cityscapes datasets show that the proposed method improves the performance of semantic segmentation and shows better results in small target structures and object edge details.

Fusion of Infrared and Visible Images Using Fuzzy Based Siamese Convolutional Network

Traditional techniques based on image fusion are arduous in integrating complementary or heterogeneous infrared (IR)/visible (VS) images. Dissimilarities in various kind of features in these images are vital to preserve in the single fused image. Hence, simultaneous preservation of both the aspects at the same time is a challenging task. However, most of the existing methods utilize the manual extraction of features; and manual complicated designing of fusion rules resulted in a blurry artifact in the fused image. Therefore, this study has proposed a hybrid algorithm for the integration of multi-features among two heterogeneous images. Firstly, fuzzification of two IR/VS images has been done by feeding it to the fuzzy sets to remove the uncertainty present in the background and object of interest of the image. Secondly, images have been learned by two parallel branches of the siamese convolutional neural network (CNN) to extract prominent features from the images as well as high-frequency information to produce focus maps containing source image information. Finally, the obtained focused maps which contained the detailed integrated information are directly mapped with the source image via pixel-wise strategy to result in fused image. Different parameters have been used to evaluate the performance of the proposed image fusion by achieving 1.008 for mutual information (MI), 0.841 for entropy , 0.655 for edge information (EI), 0.652 for human perception (HP), and 0.980 for image structural similarity (ISS). Experimental results have shown that the proposed technique has attained the best qualitative and quantitative results using 78 publically available images in comparison to the existing discrete cosine transform (DCT), anisotropic diffusion & karhunen-loeve (ADKL), guided filter (GF), random walk (RW), principal component analysis (PCA), and convolutional neural network (CNN) methods.

Novel Optimized Framework for Video Processing in IoRT Driven Hospitals

Internet of Remote things (IoRT) has gained recent attention and is considered as one most prominent research topics being carried out by numerous researchers worldwide. IoRT is being used in various applications and this paper mainly concentrates on the healthcare industry wherein it could be used effectively for patient monitoring. IoRT plays a crucial role in monitoring the patients in any healthcare center remotely by allowing simultaneous video transmissions possible from the emergency areas like Intensive Care Unit (ICU). Considering general scenarios, the video transmissions are done by the main use of Gaussian distribution. With the help of the proposed IoRT based system, the video transmission could be effectively done by making use of short-term snapshots. This system enables a wide range of intermittent distributions. As the system basically works on multiple videos, denoising these videos is the primary challenge. Image-denoising is one of the important pre-processing stages, used to improve the overall quality of the images used in video transmission. The use of a Median Filter is done to minimize the overall Signal-to-Noise Ratio (SNR). Even though numerous types of Median filters are available, in this work we have made use of a 3D (Dimension) filter to get more effective results as the edges of the video frames are preserved. The paper has made use of a Hybrid algorithm combining the Cuckoo Search Optimization technique along with a Genetic Algorithm (GA) to optimize the frames in the video. The use of this hybrid algorithm paves a way to obtain equal intensity-based frames. For analyzing collective performance Peak Signal Noise Ratio (PSNR), Universal Image Quality Index (UIQI) and Structural Similarity Index (SSI) are used as quality assessment metrics to deliver a high-performance noise-free optimized video. The simulation results show better performance when compared with other image Noise Filtering Methods and other optimization algorithms when used in IoRT driven hospitals.

Diagnosis of Early Cervical Cancer with a Multimodal Magnetic Resonance Image under the Artificial Intelligence Algorithm.

This research was conducted to explore the value of multimodal magnetic resonance imaging (MRI) based on the alternating direction algorithm in the diagnosis of early cervical cancer. 64 patients diagnosed with early cervical cancer clinicopathologically were included, and according to the examination methods, they were divided into A group with conventional multimodal MRI examination and B group with the multimodal MRI examination under the alternating direction algorithm. The diagnostic results of two types of multimodal MRI for early cervical cancer staging were compared with the results of clinicopathological examination to judge the application value in the early diagnosis of cervical cancer. The results showed that in the 6 randomly selected samples of early cervical cancer patients, the peak signal-to-noise ratio (PSNR) and structural similarity image measurement (SSIM) of multimodal MRI images under the alternating direction algorithm were significantly higher than those of conventional multimodal MRI images and the image reconstruction was clearer under this algorithm. By comparing MRI multimodal staging, statistical analysis showed that the staging accuracy of B group was 75%, while that of A group was only 59.38%. For the results of postoperative medical examinations, the examination consistency of B group was better than that of A group, with a statistically significant difference (P < 0.05). The area under the receiver operating characteristic (ROC) curve (AUC) of B group was larger than that of A group; thus, sensitivity was improved and misdiagnosis was reduced significantly. Multimodal MRI under the alternating direction algorithm was superior to conventional multimodal MRI examination in the diagnosis of early cervical cancer, as the lesions were displayed more clearly, which was conducive to the detection rate of small lesions and the staging accuracy. Therefore, it could be used as an ideal MRI method for the assistant diagnosis of cervical cancer staging.

Spatiotemporal Flexible Sparse Reconstruction for Rapid Dynamic Contrast-Enhanced MRI.

Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) is a tissue perfusion imaging technique. Some versatile free-breathing DCE-MRI techniques combining compressed sensing (CS) and parallel imaging with golden-angle radial sampling have been developed to improve motion robustness with high spatial and temporal resolution. These methods have demonstrated good diagnostic performance in clinical setting, but the reconstruction quality will degrade at high acceleration rates and overall reconstruction time remains long. In this paper, we proposed a new parallel CS reconstruction model for DCE-MRI that enforces flexible weighted sparse constraint along both spatial and temporal dimensions. Weights were introduced to flexibly adjust the importance of time and space sparsity, and we derived a fast-thresholding algorithm which was proven to be simple and efficient for solving the proposed reconstruction model. Results on both the brain tumor DCE and liver DCE show that, at relatively high acceleration factor of fast sampling, lowest reconstruction error and highest image structural similarity are obtained by the proposed method. Besides, the proposed method achieves faster reconstruction for liver datasets and better physiological measures are also obtained on tumor images.

Rail surface defect inspection via a self-reference template and similarity evaluation

Although railway transportation has rapidly evolved in recent times, the existing manual maintenance of rail infrastructure presents several challenges, such as labor intensity and tediousness. Computer vision, as one of the automatic inspection methods, shows promising prospects for railway detection tasks. In this study, we proposed a novel rail surface defect detection method based on a self-reference template and similarity evaluation. Firstly, a self-reference template was generated by extracting the domain information together with the longitudinal direction of the rail image. We further defined an image structural similarity index, and subsequently compared all the transversal rows with the background template. A coarse-to-fine segmentation method was further proposed to locate the defect. In the first step of the segmentation procedure, rows with large differences were selected using the Otsu algorithm adaptively. The exact position of the defect was then determined by utilizing both gradient magnitude and grayscale information. Our method was evaluated on a public rail surface defects dataset, which included two types of data. The experiment results showed that our method detected type-I and type-II defects with 89.04% and 89.61% recall, and 98.46% and 97.87% precision, respectively. This shows that our method achieved higher accuracy than the established detection algorithms.

DESN: An unsupervised MR image denoising network with deep image prior

Magnetic Resonance Imaging (MRI) is a widely used medical diagnosis technique. However, the quality of MR image is affected by the noise which is caused by mechanical and environmental reasons during the MR image acquisition process. For decades, various kinds of methods including filtering approaches, transform domain approaches and statistical approaches have been applied to the MR image denoising problem, while there are also some drawbacks exiting in these methods such as arising undesirable change of texture and long computation time needed. In this paper, we proposed a novel MR image denoising method called DESN which is a neural network method and has a novel network architecture with well-designed loss function. In DESN, the convolutional neural networks itself is considered as a regularizer or image prior information for the inverse problems such as denoising. The network architecture of DESN is designed from the auto-encoder architecture, it has three main parts: encoder network for extracting low-resolution image features, decoder network for restoring high-resolution features and skip connections for transmitting abstract information from encoder network to decoder network. Besides, we also design a novel loss function which contains two main parts: data fidelity loss (Lfidelity), image quality penalty (Lq) and three loss terms: mean squared error term (LMSE), image structure similarity term (LS), image information entropy term (LIE). We compare the performance of DESN with DIP and some state of the art denoising methods, and the performance of our network with different loss terms are also compared in three MR modalities. The comparative results show that DESN have the superior performance in generating high-quality MR image with enough edge and texture information.

An Information Retention and Feature Transmission Network for Infrared and Visible Image Fusion

The aim of infrared and visible image fusion is to generate a composite image that contains the thermal radiation information in the infrared image and optical spectral information in visible image. In this paper, we proposed an end-to-end deep infrared and visible image fusion network which has the capability of information retention and feature transmission. In our proposed network, residual dense blocks (RDB) are introduced to ensure complete deep features extraction of source images. We also design intermediate feature transmission blocks to avoid information loss caused by convolution. In addition, we constrain the network by a comprehensive loss function based on image intensity, gradients, and structure similarity. The loss function ensures that the fused images retain rich details. We introduce weight blocks to produce adaptive weights to control the retention of similar information in two source images, which can reduce the intermediate information loss and play the role of information retention. Extensive experiments on both public <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">TNO</i> and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">RoadScene</i> datasets are conduced to test the performances of the proposed method. Related ablation experiments are conducted to investigate the validation of the weight blocks and the feature transmission blocks. The experimental results demonstrate that the fusion results of the proposed network show more texture information and better visual quality than other state-of-the-art fusion methods. From both subjective and objective points, our method is competitive with or even outperform most of advanced fusion methods.

Image Compression Using Permanent Neural Networks for Predicting Compact Discrete Cosine Transform Coefficients

This study proposes a new image compression technique that produces a high compression ratio yet consumes low execution times. Since many of the current image compression algorithms consume high execution times, this technique speeds up the execution time of image compression. The technique is based on permanent neural networks to predict the discrete cosine transform partial coefficients. This can eliminate the need to generate the discrete cosine transformation every time an image is compressed. A compression ratio of 94% is achieved while the average decompressed image peak signal to noise ratio and structure similarity image measure are 22.25 and 0.65 respectively. The compression time can be neglected when compared to other reported techniques because the only needed process in the compression stage is to use the generated neural network model to predict the few discrete cosine transform coefficients.

An infrared and visible image fusion method based on multi-scale transformation and norm optimization

In this paper, we propose a new infrared and visible image fusion method based on multi-scale transformation and norm optimization. In this method, a new loss function is designed with contrast fidelity (L2 norm) and sparse constraint (L1 norm), and the split Bregman method is used to optimize the loss function to obtain pre-fusion images. The final fused base layer is obtained by using a multi-level decomposition latent low-rank representation (MDLatLRR) method to decompose the pre-fusion images. Then, using the pre-fusion image as the reference, image structure similarity (SSIM) is introduced to evaluate the validity of detail information from the visible image, and the SSIM is then transformed into a weight map which is applied to the optimization method based on L2 norm to generate the final detail fusion layer. Our proposed method is evaluated and compared with 18 state-of-the-art image fusion methods, both qualitatively and quantitatively on four public datasets (i.e., CVC14 driving dataset, TNO dataset with natural scenarios, RoadScene dataset, and whole brain atlas dataset). The results show that our proposed method is generally better than the compared methods in terms of highlighting targets and retaining effective detail information.

Dynamic Disturbance Analysis of Whiskbroom Area Array Imaging of Aerospace Optical Camera

The whiskbroom scanning imaging mode effectively expands the imaging field of the space optical camera, and realizes high-resolution and wide-width spatial imaging. However, the dynamic disturbance in the short-term and large-scale imaging process will cause uneven degradation of the image. Therefore, a geometric model of the camera instantaneous imaging at a moment is constructed. Then, the movement trend of the camera and the deflection of the light are deduced separately for establishing the analysis model of the kinematic disturbance and the morphological disturbance. Finally, the dynamic disturbance result of the imaging process is obtained by fusing both kinematic disturbance and morphological disturbance, and the simulated image of the dynamic disturbance is evaluated by combining the geometric parameters and the image quality evaluation index. The results show that the dynamic disturbance of the imaging will be enhanced with the increase of the whiskbroom angle and angular velocity, resulting in the decrease of the peak signal-to-noise ratio and the structural similarity of the image. When the angular velocity on the 500km orbit increases from 1°/ $s$ to 10°/ $s$ , the peak signal-to-noise ratio and structural similarity of the simulated image, affected by the combining influence of kinematic disturbance and morphological disturbance, decrease by 2.1454 dB and 0.1131 respectively at 0°, but decrease by 1.5680 dB and 0.0405 at 45°. The analysis results of this paper can provide an effective reference for further research on the degradation process of whiskbroom ultra-wide image and improve the quality of the image.

A Novel AlphaSRGAN for Underwater Image Super Resolution

Obtaining clear images of underwater scenes with descriptive details is an arduous task. Conventional imaging techniques fail to provide clear cut features and attributes that ultimately result in object recognition errors. Consequently, a need for a system that produces clear images for underwater image study has been necessitated. To overcome problems in resolution and to make better use of the Super-Resolution (SR) method, this paper introduces a novel method that has been derived from the Alpha Generative Adversarial Network (AlphaGAN) model, named Alpha Super Resolution Generative Adversarial Network (AlphaSRGAN). The model put forth in this paper helps in enhancing the quality of underwater imagery and yields images with greater resolution and more concise details. Images undergo pre-processing before they are fed into a generator network that optimizes and reforms the structure of the network while enhancing the stability of the network that acts as the generator. After the images are processed by the generator network, they are passed through an adversarial method for training models. The dataset used in this paper to learn Single Image Super Resolution (SISR) is the USR 248 dataset. Training supervision is performed by an unprejudiced function that simultaneously scrutinizes and improves the image quality. Appraisal of images is done with reference to factors like local style information, global content and color. The dataset USR 248 which has a huge collection of images has been used for the study is composed of three collections of images—high (640 480) and low (80 60, 160 120, and 320 240). Paired instances of different sizes—2, 4 and 8—are also present in the dataset. Parameters like Mean Opinion Score (MOS), Peak Signal-to-Noise Ratio (PSNR), Structural Similarity (SSIM) and Underwater Image Quality Measure (UIQM) scores have been compared to validate the improved efficiency of our model when compared to existing works.

Adversarial Attack Based on Perturbation of Contour Region to Evade Steganalysis-Based Detection

Deep neural networks (DNN) are applied in various fields because they afford good performance. However, they seem vulnerable to adversarial examples. Therefore, studies are actively investigating adversarial defenses to improve the robustness of DNNs as well as adversarial attacks to generate more intensive adversarial perturbations. Most existing attack methods excessively modify images by generating overly large distortions or adding perturbations to regions with little impact on the DNN. As a result, the local smoothness of images is not maintained, and changes can be easily detected using a steganalysis-based detector. In this study, we propose a contour attack method to evade steganalysis-based detection. This method extracts the contour region from an image and adds perturbations only to applicable regions, thus maintaining the local smoothness. It can solve the problems mentioned above and effectively evade steganalysis-based detectors. Our experimental results demonstrate that the local smoothness is better than that in the case of original attack methods and that the detection evasion rate for a steganalysis detector is up to 19.9% higher. Further, structural similarity (SSIM) measurements and image comparisons demonstrate the improved imperceptibility of perturbations. In particular, the SSIM values for images subjected to the contour attack are close to 1.0.

SAR Image Formation Method with Azimuth Periodically Missing Data Based on RELAX Algorithm

Synthetic aperture radar (SAR) is a widely used remote sensing observation technique. However, SAR raw echo data may be lost during the process of data acquisition by radar platform. In this paper, the imaging problem of SAR echo signal with periodically missing data along the azimuth is analyzed and a novel imaging method is proposed. Firstly, the problem of artificial artifact targets caused by periodically missing data is explained in detail, and the corresponding mathematical model is established. Then, the recovery method based on the RELAX algorithm with periodic notches data is proposed. In addition, when the size of two-dimensional (2D) echo data are large, block restoration along the azimuth is proposed to reduce the amount of calculation. Finally, the advantages of the algorithm proposed in this paper is demonstrated by the points target simulated SAR echo data processing and the real raw SAR echo data processing. When the azimuth periodically missing data rate is 50%, the SAR echo data can be recovered and the well-focused image can be obtained. Comparing the image entropy value and structural similarity index (SSIM) of the focused image, it proves the superiority of the proposed algorithm in solving the imaging problem of SAR azimuth periodically missing data.

Efficient image structural similarity quality assessment method using image regularised feature

Image regularised features play a critical role in image processing domain, by integrating regularised feature and structural similarity, a new full-reference image assessment method (IRF_SSIM) is proposed in this study. As well known, the gradient operator always be used to capture the edge information of the image, while the total variational regularised features can be adopted to calculate the detailed change information of image contrast and texture, as well as noise removal and edge retention. Therefore, the IRF_SSIM method extends the gradient features into the image regularised features to measure the structural changes in the image. In addition, image quality is also affected by variations of luminance and contrast. For a more comprehensive image quality assessment, the IRF_SSIM method considers the changes in structure, luminance and contrast simultaneously. In other words, the total image quality is estimated by structural similarity calculated by integrating the effects of image structure, luminance and contrast changes. Comparing with the representative methods, the experimental results illustrate that the IRF_SSIM method is highly consistent with the subjective assessment results.

Structural Similarity Loss for Learning to Fuse Multi-Focus Images.

Convolutional neural networks have recently been used for multi-focus image fusion. However, some existing methods have resorted to adding Gaussian blur to focused images, to simulate defocus, thereby generating data (with ground-truth) for supervised learning. Moreover, they classify pixels as ‘focused’ or ‘defocused’, and use the classified results to construct the fusion weight maps. This then necessitates a series of post-processing steps. In this paper, we present an end-to-end learning approach for directly predicting the fully focused output image from multi-focus input image pairs. The suggested approach uses a CNN architecture trained to perform fusion, without the need for ground truth fused images. The CNN exploits the image structural similarity (SSIM) to calculate the loss, a metric that is widely accepted for fused image quality evaluation. What is more, we also use the standard deviation of a local window of the image to automatically estimate the importance of the source images in the final fused image when designing the loss function. Our network can accept images of variable sizes and hence, we are able to utilize real benchmark datasets, instead of simulated ones, to train our network. The model is a feed-forward, fully convolutional neural network that can process images of variable sizes during test time. Extensive evaluation on benchmark datasets show that our method outperforms, or is comparable with, existing state-of-the-art techniques on both objective and subjective benchmarks.

Predicting the Perceptual Quality of Point Cloud: A 3D-to-2D Projection-Based Exploration

Point cloud is emerged as a promising media format to represent realistic 3D objects or scenes in applications, such as virtual reality, teleportation, etc. How to accurately quantify the subjective point cloud quality for application-driven optimization, however, is still a challenging and open problem. In this paper, we attempt to tackle this problem in a systematic means. First, we produce a fairly large point cloud dataset where ten popular point clouds are augmented with seven types of impairments (e.g., compression, photometry/color noise, geometry noise, scaling) at six different distortion levels, and organize a formal subjective assessment with tens of subjects to collect mean opinion scores (MOS) for all 420 processed point cloud samples (PPCS). We then try to develop an objective metric that can accurately estimate the subjective quality. Towards this goal, we choose to project the 3D point cloud onto six perpendicular image planes of a cube for the color texture image and corresponding depth image, and aggregate image-based global (e.g., Jensen-Shannon (JS) divergence) and local features (e.g., edge, depth, pixel-wise similarity, complexity) among all projected planes for a final objective index. Model parameters are fixed constants after performing the regression using a small and independent dataset previously published. The proposed metric has demonstrated the state-of-the-art performance for predicting the subjective point cloud quality compared with multiple full-reference and no-reference models, e.g., the weighted peak signal-to-noise ratio (PSNR), structural similarity (SSIM), feature similarity (FSIM) and natural image quality evaluator (NIQE). The dataset is made publicly accessible at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">http://smt.sjtu.edu.cn</uri> or <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">http://vision.nju.edu.cn</uri> for all interested audiences.

Learning an adaptive model for extreme low‐light raw image processing

Low-light images suffer from severe noise and low illumination. In this work, the authors propose an adaptive low-light raw image enhancement network to avoid parameter-handcrafting in current deep learning models and to improve image quality. The proposed method can be divided into two sub-models: brightness prediction and exposure shifting (ES). The former is designed to control the brightness of the resulting image by estimating a guideline exposure time . The latter learns to approximate an exposure-shifting operator ES, converting a low-light image with real exposure time to a noise-free image with guideline exposure time . Additionally, structural similarity loss and image enhancement vector are introduced to promote image quality, and a new campus image data set (CID) for training the proposed model is proposed to overcome the limitations of the existing data sets. In quantitative tests, it is shown that the proposed method has the lowest noise level estimation score compared with the state-of-the-art low-light algorithms, suggesting a superior denoising performance. Furthermore, those tests illustrate that the proposed method is able to adaptively control the global image brightness according to the content of the image scene. Lastly, the potential application in video processing is briefly discussed.

An Ultrasound Image Enhancement Method Using Neutrosophic Similarity Score.

Ultrasound images, having low contrast and noise, adversely impact in the detection of abnormalities. In view of this, an enhancement method is proposed in this work to reduce noise and improve contrast of ultrasound images. The proposed method is based on scaling with neutrosophic similarity score (NSS), where an image is represented in the neutrosophic domain through three membership subsets T, I, and F denoting the degree of truth, indeterminacy, and falseness, respectively. The NSS measures the belonging degree of pixel to the texture using multi-criteria that is based on intensity, local mean intensity and edge detection. Then, NSS is utilized to extract the enhanced coefficient and this enhanced coefficient is applied to scale the input image. This scaling reflects contrast improvement and denoising effect on ultrasound images. The performance of proposed enhancement method is evaluated on clinical ultrasound images, using both subjective and objective image quality measures. In subjective evaluation, with proposed method, overall best score of 4.3 was obtained and that was 44% higher than the score of original images. These results were also supported by objective measures. The results demonstrated that the proposed method outperformed the other methods in terms of mean brightness preservation, edge preservation, structural similarity, and human perception-based image quality assessment. Thus, the proposed method can be used in computer-aided diagnosis systems and to visually assist radiologists in their interactive-decision-making task.

Adaptive Trimmed Median Filter for Impulse Noise Detection and Removal with an Application to Mammogram Images

Mammography imaging is one of the most widely used techniques for breast cancer screening and analysis of abnormalities. However, due to some technical difficulties during the time of acquisition and digital storage of mammogram images, impulse noise may be present. Therefore, detection and removals of impulse noise from the mammogram images are very essential for early detection and further diagnosis of breast cancer. In this paper, a novel adaptive trimmed median filter (ATMF) is proposed for impulse noise (salt &amp; pepper (SNP)) detection and removal with an application to mammogram image denoising. Automatic switching mechanism for updating the Window of Interest (WoI) size from ([Formula: see text]) to ([Formula: see text]) or ([Formula: see text]) is performed. The proposed method is applied on publicly available mammogram images corrupted with varying SNP noise densities in the range 5%–90%. The performance of the proposed method is measured by various quantitative indices like peak signal to noise ratio (PSNR), mean square error (MSE), image enhancement factor (IEF) and structural similarity index measure (SSIM). The comparative analysis of the proposed method is done with respect to other state-of-the-art noise removal methods viz., standard median filter (SMF), decision based median filter (DMF), decision based unsymmetric trimmed median filter (DUTMF), modified decision based unsymmetric trimmed median filter (MDUTMF) and decision based unsymmetric trimmed winsorized mean filter (DUTWMF). The superiority of the proposed method over other compared methods is well evident from the experimental results in terms of the quantitative indices (viz., PSNR, IEF and SSIM) and also from the visual quality of the denoised images. Paired t-test confirms the statistical significance of the higher PSNR values achieved by the proposed method as compared to the other counterpart techniques. The proposed method turned out to be very effective in denoising both high and low density noises present in (mammogram) images.