Showing papers on "Median filter published in 2020"

Computer-aided diagnosis of skin cancer based on soft computing techniques

Abstract: Skin cancer is a type of disease in which malignant cells are formed in skin tissues. However, skin cancer is a dangerous disease, and an early detection of this disease helps the therapists to cure this disease. In the present research, an automatic computer-aided method is presented for the early diagnosis of skin cancer. After image noise reduction based on median filter in the first stage, a new image segmentation based on the convolutional neural network optimized by satin bowerbird optimization (SBO) has been adopted and its efficiency has been indicated by the confusion matrix. Then, feature extraction is performed to extract the useful information from the segmented image. An optimized feature selection based on the SBO algorithm is also applied to prune excessive information. Finally, a support vector machine classifier is used to categorize the processed image into the following two groups: cancerous and healthy cases. Simulations have been performed of the American Cancer Society database, and the results have been compared with ten different methods from the literature to investigate the performance of the system in terms of accuracy, sensitivity, negative predictive value, specificity, and positive predictive value.

A decision based asymmetrically trimmed modified winsorized median filter for the removal of salt and pepper noise in images and videos

Abstract: A decision based asymmetrically trimmed Winsorized median for the removal of salt and pepper noise in images and videos is proposed. The proposed filter initially classifies the pixels as noisy and non noisy and later replaces the noisy pixels with asymmetrically trimmed modified winsorized median leaving the non noisy pixels unaltered. Exhaustive experiments were conducted on standard image database and the performance of the proposed filter was evaluated in terms of both quantitative and qualitatively with existing algorithm. It was found that the proposed algorithm was found to exhibit excellent noise suppression capabilities by preserving the fine information of the image even at higher noise densities. The performance of the proposed filter was found good even for videos.

Adaptive frequency median filter for the salt and pepper denoising problem

Abstract: In this article, the authors propose an adaptive frequency median filter (AFMF) to remove the salt and pepper noise. AFMF uses the same adaptive condition of adaptive median filter (AMF). However, AFMF employs frequency median to restore grey values of the corrupted pixels instead of the median of AMF. The frequency median can exclude noisy pixels from evaluating a grey value of the centre pixel of the considered window, and it focuses on the uniqueness of grey values. Hence, the frequency median produces a grey value closer to the original grey value than the one by the median of AMF. Therefore, AFMF outperforms AMF. In experiments, the authors tested the proposed method on a variety of natural images of the MATLAB library, as well as the TESTIMAGES data set. Additionally, they also compared the denoising results of AFMF to the ones of other state-of-the-art denoising methods. The results showed that AFMF denoises more effectively than other methods.

Comparison of Smoothing Filters in Analysis of EEG Data for the Medical Diagnostics Purposes.

Abstract: This paper covers a brief review of both the advantages and disadvantages of the implementation of various smoothing filters in the analysis of electroencephalography (EEG) data for the purpose of potential medical diagnostics. The EEG data are very prone to the occurrence of various internal and external artifacts and signal distortions. In this paper, three types of smoothing filters were compared: smooth filter, median filter and Savitzky–Golay filter. The authors of this paper compared those filters and proved their usefulness, as they made the analyzed data more legible for diagnostic purposes. The obtained results were promising, however, the studies on finding perfect filtering methods are still in progress.

Ore image segmentation method using U-Net and Res_Unet convolutional networks

Abstract: Image segmentation has been increasingly used to identify the particle size distribution of crushed ore; however, the adhesion of ore particles and dark areas in the images of blast heaps and conveyor belts usually results in lower segmentation accuracy. To overcome this issue, an image segmentation method UR based on deep learning U-Net and Res_Unet networks is proposed in this study. Gray-scale, median filter and adaptive histogram equalization techniques are used to preprocess the original ore images captured from an open pit mine to reduce noise and extract the target region. U-Net and Res_Unet are utilized to generate ore contour detection and optimization models, and the ore image segmentation result is illustrated by OpenCV. The efficiency and accuracy of the newly proposed UR method is demonstrated and validated by comparing with the existing image segmentation methods.

Fast Depth Estimation for Light Field Cameras

Abstract: Fast depth estimation for light field images is an important task for multiple applications such as image-based rendering and refocusing. Most previous approaches to light field depth estimation involve high computational costs. Therefore, in this study, we propose a fast depth estimation method based on multi-view stereo matching for light field images. Similar to other conventional methods, our method consists of initial depth estimation and refinement. For the initial estimation, we use a one-bit feature for each pixel and calculate matching costs by summing all combinations of viewpoints with a fast algorithm. To reduce computational time, we introduce an offline viewpoint selection strategy and cost volume interpolation. Our refinement process solves the minimization problem in which the objective function consists of $\ell _{1}$ data and smoothness terms. Although this problem can be solved via a graph cuts algorithm, it is computationally expensive; therefore, we propose an approximate solver based on a fast-weighted median filter. Experiments on synthetic and real-world data show that our method achieves competitive accuracy with the shortest computational time of all methods.

Implementing canny edge detection algorithm for noisy image

Abstract: Edge detection is a significant stage in different image processing operations like pattern recognition, feature extraction, and computer vision. Although the Canny edge detection algorithm exhibits high precision is computationally more complex contrasted to other edge detection methods. Due to the traditional Canny algorithm uses the Gaussian filter, which gives the edge detail represents blurry also its effect in filtering salt-and-pepper noise is not good. In order to resolve this problem, we utilized the median filter to maintain the details of the image and eliminate the noise. This paper presents implementing and enhance the accuracy of Canny edge detection for noisy images. Results present that this proposed method can definitely overcome noise disorders, preserve the edge useful data, and likewise enhance the edge detection precision.

AMST: Alignment to Median Smoothed Template for Focused Ion Beam Scanning Electron Microscopy Image Stacks.

Abstract: Alignment of stacks of serial images generated by Focused Ion Beam Scanning Electron Microscopy (FIB-SEM) is generally performed using translations only, either through slice-by-slice alignments with SIFT or alignment by template matching. However, limitations of these methods are two-fold: the introduction of a bias along the dataset in the z-direction which seriously alters the morphology of observed organelles and a missing compensation for pixel size variations inherent to the image acquisition itself. These pixel size variations result in local misalignments and jumps of a few nanometers in the image data that can compromise downstream image analysis. We introduce a novel approach which enables affine transformations to overcome local misalignments while avoiding the danger of introducing a scaling, rotation or shearing trend along the dataset. Our method first computes a template dataset with an alignment method restricted to translations only. This pre-aligned dataset is then smoothed selectively along the z-axis with a median filter, creating a template to which the raw data is aligned using affine transformations. Our method was applied to FIB-SEM datasets and showed clear improvement of the alignment along the z-axis resulting in a significantly more accurate automatic boundary segmentation using a convolutional neural network.

Multi-modality medical image fusion using hybridization of binary crow search optimization.

Abstract: In clinical applications, single modality images do not provide sufficient diagnostic information. Therefore, it is necessary to combine the advantages or complementarities of different modalities of images. In this paper, we propose an efficient medical image fusion system based on discrete wavelet transform and binary crow search optimization (BCSO) algorithm. Here, we consider two different patterns of images as the input of the system and the output is the fused image. In this approach, at first, to enhance the image, we apply a median filter which is used to remove the noise present in the input image. Then, we apply a discrete wavelet transform on both the input modalities. Then, the approximation coefficients of modality 1 and detailed coefficients of modality 2 are combined. Similarly, approximation coefficients of modality 2 and detailed coefficients of modality 1 are combined. Finally, we fuse the two modality information using novel fusion rule. The fusion rule parameters are optimally selected using binary crow search optimization (BCSO) algorithm. To evaluate the performance of the proposed method, we used different quality metrics such as structural similarity index measure (SSIM), Fusion Factor (FF), and entropy. The presented model shows superior results with 6.63 of entropy, 0.849 of SSIM and 5.9 of FF.

A Deep Learning Approach in the Discrete Cosine Transform Domain to Median Filtering Forensics

Abstract: This letter presents a novel median filtering forensics approach, based on a convolutional neural network (CNN) with an adaptive filtering layer (AFL), which is built in the discrete cosine transform (DCT) domain. Using the proposed AFL, the CNN can determine the main frequency range closely related with the operational traces. Then, to automatically learn the multi-scale manipulation features, a multi-scale convolutional block is developed, exploring a new multi-scale feature fusion strategy based on the maxout function. The resultant features are further processed by a convolutional stream with pooling and batch normalization operations, and finally fed into the classification layer with the Softmax function. Experimental results show that our proposed approach is able to accurately detect the median filtering manipulation and outperforms the state-of-the-art schemes, especially in the scenarios of low image resolution and serious compression loss.

Adaptive Cuckoo Search based optimal bilateral filtering for denoising of satellite images.

Abstract: A satellite image transmitted from satellite to the ground station is corrupted by different kinds of noises such as impulse noise, speckle noise and Gaussian noise. The traditional methods of denoising can remove the noise components but cannot preserve the quality of the image and lead to over-blurring of the edges in the image. To overcome these drawbacks, this paper develops an optimized bilateral filter for image denoising and preserving the edges using different nature inspired optimization algorithms which can effectively denoise the image without blurring the edges in the image. Denoising the image using a bilateral filter requires the decision of the control parameters so that the noise is removed and the edge details are preserved. With the help of optimization algorithms such as Particle Swarm Optimization (PSO), Cuckoo Search (CS) and Adaptive Cuckoo Search (ACS), the control parameters in the bilateral filter are decided for optimal performance. It is observed that the proposed Adaptive Cuckoo Search based bilateral filter denoising gives better results in terms of Peak Signal to Noise Ratio (PSNR), Mean Square Error (MSE), Feature Similarity Index (FSIM), Entropy and CPU time in comparison to traditional methods such as Median filter and RGB spatial filter.

Comparative Analysis of Gaussian Filter, Median Filter and Denoise Autoenocoder

Abstract: Images can be enhanced and denoised with the help of filters. In this paper, we use a Gaussian filter, a Median Filter and a Denoising Auto encoder for noise removal. Gaussian filter is a linear type of filter which is based on Gaussian function. But the median filter is a non-linear type of filter. It preserves edge while removing noise. Deep Convolutional neural network (CNN) is able to handle Gaussian denoising at a certain noise level. We compare these three types of noise removers with the help of four types of evaluation techniques. We use time performance, Peak signal-to-noise ratio (PSNR), Structure Similarity (SSIM) and Normalization mean square error (NMSE) evaluation techniques for finding the best filter for removing noise from the image on different situations. We found that sometimes a Gaussian filter is better and sometimes the median filter is better depending on the iteration of the filter. Sometimes a denoise autoencoder is also better but it takes more time with respect to a Gaussian filter and a median filter. When we consider only the time parameter, then the Median filter gives better results in less time in comparison to a Gaussian filter and a denoise autoencoder filter.

Restoration of highly salt-and-pepper-noise-corrupted images using novel adaptive trimmed median filter

Abstract: The paper presents a novel adaptive trimmed median (ATM) filter to remove salt-and-pepper (SAP) noise of high noise density (ND). The proposed filter computes median of trimmed window of adaptive size containing noise-free pixels (NFP) for ND up medium range while performs new interpolation-based procedure at high ND. Further, for the rare scenarios especially at the boundary where denoising using interpolation is not good enough, the proposed filter denoises the candidate pixel with the help of nearest processed pixels. The proposed ATM filter effectively suppresses SAP noise because denoising mostly utilizes original non-noisy pixels. The proposed algorithm is evaluated for varying ND (10–90%) with different benchmark images (greyscale and coloured) over the existing approaches. The proposed ATM filter on an average provides 1.59 dB and 0.37 dB higher PSNR values on the greyscale and color images, respectively.

Comparison of Motion Artefact Reduction Methods and the Implementation of Adaptive Motion Artefact Reduction in Wearable Electrocardiogram Monitoring.

Abstract: A motion artefact is a kind of noise that exists widely in wearable electrocardiogram (ECG) monitoring. Reducing motion artefact is challenging in ECG signal preprocessing because the spectrum of motion artefact usually overlaps with the very important spectral components of the ECG signal. In this paper, the performance of the finite impulse response (FIR) filter, infinite impulse response (IIR) filter, moving average filter, moving median filter, wavelet transform, empirical mode decomposition, and adaptive filter in motion artefact reduction is studied and compared. The results of this study demonstrate that the adaptive filter performs better than other denoising methods, especially in dealing with the abnormal ECG signal which is measured from a patient with heart disease. In the implementation of adaptive motion artefact reduction, the results show that the use of the impedance pneumography signal as the reference input signal for the adaptive filter can effectively reduce the motion artefact in the ECG signal.

Heart Rate Estimation of PPG Signals With Simultaneous Accelerometry Using Adaptive Neural Network Filtering

Abstract: Motion artifacts (MA) are potent sources of noise in wearable photoplethysmography (PPG) signals and can impact the estimation of heart rate (HR) of an individual. In this paper, a method using adaptive neural network filters (ANNF) is proposed for accurate estimation of HR using dual channel PPG signals and simultaneous, three - dimensional acceleration signals. The MA cancellation method using ANNF, utilizes acceleration data as input signal. The PPG signals serve as a target, while the error is the clean PPG signal. The proposed method also includes a post-processing smoothing and median filter which improves the HR estimation. The reason for this approach is that the acceleration signal in wearables are only within 3% of the ground truth value. Experimental results on datasets recorded from 12 subjects, publicly available, showed that the proposed algorithm achieves an absolute error of 1.15 beats per minute (BPM). The results also confirm that the proposed method is highly resilient to motion artifacts and maintains high accuracy for PPG estimation and compares favorably against other methods.

A novel watermarking method based on differential evolutionary algorithm and wavelet transform

Abstract: In this paper, a new Watermarking method based on the optimization framework and discrete wavelet transform (DWT) is presented. In this method, first, the watermark image is divided into several blocks. Then, using differential evolution (DE) algorithm, an appropriate location for each of these blocks is found in the cover image. In the proposed method, the results of the DE algorithm, which is needed for the reconstruction phase are also embedded as a vector in the cover image under the wavelet domain. Also, to achieve the highest PSNR in the reconstruction phase, the optimal values for Alpha-blending coefficients (used in the embedding and extraction process) are determined with the multi-objective DE-based optimization algorithm. Several experiments are presented to illustrate the imperceptibility and robustness of the proposed algorithm against different types of attacks, including salt and pepper, Gaussian, median filtering, rescaling, compression, and rotation. The obtained results are also compared with state-of-the-art methods and show the superiority of the proposed method in most cases.

Effectiveness of Random Deep Feature Selection for Securing Image Manipulation Detectors Against Adversarial Examples

Abstract: We investigate if the random feature selection approach proposed in [1] to improve the robustness of forensic detectors to targeted attacks, can be extended to detectors based on deep learning features. In particular, we study the transferability of adversarial examples targeting an original CNN image manipulation detector to other detectors (a fully connected neural network and a linear SVM) that rely on a random subset of the features extracted from the flatten layer of the original network. The results we got by considering three image manipulation detection tasks (resizing, median filtering and adaptive histogram equalization), two original network architectures and three classes of attacks, show that feature randomization helps to hinder attack transferability, even if, in some cases, simply changing the architecture of the detector, or even retraining the detector is enough to prevent the transferability of the attacks.

Deep Learning Based Switching Filter for Impulsive Noise Removal in Color Images.

Abstract: Noise reduction is one of the most important and still active research topics in low-level image processing due to its high impact on object detection and scene understanding for computer vision systems. Recently, we observed a substantially increased interest in the application of deep learning algorithms. Many computer vision systems use them, due to their impressive capability of feature extraction and classification. While these methods have also been successfully applied in image denoising, significantly improving its performance, most of the proposed approaches were designed for Gaussian noise suppression. In this paper, we present a switching filtering technique intended for impulsive noise removal using deep learning. In the proposed method, the distorted pixels are detected using a deep neural network architecture and restored with the fast adaptive mean filter. The performed experiments show that the proposed approach is superior to the state-of-the-art filters designed for impulsive noise removal in color digital images.