A new two-step variational model for multiplicative noise removal with applications to texture images

Multiplicative noise removal problems have attracted much attention in recent years.Unlike additive noise,multiplicative noise destroys almost all information of the original image,especially for texture images.Motivated by the TV-Stokes model,we propose a new two-step variational model to denoise the texture images corrupted by multiplicative noise with a good geometry explanation in this paper.In the first step,we convert the multiplicative denoising problem into an additive one by the logarithm transform and propagate the isophote directions in the tangential field smoothing.Once the isophote directions are constructed,an image is restored to fit the constructed directions in the second step.The existence and uniqueness of the solution to the variational problems are proved.In these two steps,we use the gradient descent method and construct finite difference schemes to solve the problems.Especially,the augmented Lagrangian method and the fast Fourier transform are adopted to accelerate the calculation.Experimental results show that the proposed model can remove the multiplicative noise efficiently and protect the texture well.

Research on weak signal extraction and noise removal for GPR data based on principal component analysis

The ground penetrating radar （GPR） detection data is a wide band signal, always disturbed by some noise, such as ambient random noise and muhiple refleetion waves. The noise affects the target identification of underground medium seriously. A method based on principal component analysis （PCA） was proposed to ex- tract the target signal and remove the uncorrelated noise. According to the correlation of signal, the authors get the eigenvalues and corresponding eigenvectors by decomposing the covariance matrix of GPR data and make linear transformation for the GPR data to get the principal components （PCs）. The lower-order PCs stand h^r the strong correlated target signals of the raw data, and the higher-order ones present the uneorrelated noise. Thus the authors can extract the target signal and filter uncorrelated noise effectively by the PCA. This method was demonstrated on real ultra-wideband through-wall radar data and simulated GPR data. Both of the results show that the PCA method can effectively extract the GPR target signal and remove the uncorrelated noise.

Efficient Global Threshold Vector Outlyingness Ratio Filter for the Removal of Random Valued Impulse Noise

This research paper proposes a filter to remove Random Valued Impulse Noise (RVIN) based on Global Threshold Vector Outlyingness Ratio (GTVOR) that is applicable for real time image processing. This filter works with the algorithm that breaks the images into various decomposition levels using Discrete Wavelet Transform (DWT) and searches for the noisy pixels using the outlyingness of the pixel. This algorithm has the capability of differentiating high frequency pixels and the “noisy pixel” using the threshold as well as window adjustments. The damage and the loss of information are prevented by means of interior mining. This global threshold based algorithm uses different thresholds for different quadrants of DWT and thus helps in recovery of noisy image even if it is 90% affected. Experimental results exhibit that this method outperforms other existing methods for accurate noise detection and removal, at the same time chain of connectivity is not lost.

Scale Invariant Feature Transform with Crow Optimization for Breast Cancer Detection

Mammography is considered a significant image for accurate breast cancer detection.Content-based image retrieval(CBIR)contributes to classifying the query mammography image and retrieves similar mammographic images from the database.This CBIR system helps a physician to give better treatment.Local features must be described with the input images to retrieve similar images.Exist-ing methods are inefficient and inaccurate by failing in local features analysis.Hence,efficient digital mammography image retrieval needs to be implemented.This paper proposed reliable recovery of the mammographic image from the data-base,which requires the removal of noise using Kalman filter and scale-invariant feature transform(SIFT)for feature extraction with Crow Search Optimization-based the deep belief network(CSO-DBN).This proposed technique decreases the complexity,cost,energy,and time consumption.Training the proposed model using a deep belief network and validation is performed.Finally,the testing pro-cess gives better performance compared to existing techniques.The accuracy rate of the proposed work CSO-DBN is 0.9344,whereas the support vector machine(SVM)(0.5434),naïve Bayes(NB)(0.7014),Butterfly Optimization Algorithm(BOA)(0.8156),and Cat Swarm Optimization(CSO)(0.8852).

Salp Swarm Algorithm with Multilevel Thresholding Based Brain Tumor Segmentation Model

Biomedical image processing acts as an essential part of severalmedical applications in supporting computer aided disease diagnosis. MagneticResonance Image (MRI) is a commonly utilized imaging tool used tosave glioma for clinical examination. Biomedical image segmentation plays avital role in healthcare decision making process which also helps to identifythe affected regions in the MRI. Though numerous segmentation models areavailable in the literature, it is still needed to develop effective segmentationmodels for BT. This study develops a salp swarm algorithm with multi-levelthresholding based brain tumor segmentation (SSAMLT-BTS) model. Thepresented SSAMLT-BTS model initially employs bilateral filtering based onnoise removal and skull stripping as a pre-processing phase. In addition,Otsu thresholding approach is applied to segment the biomedical imagesand the optimum threshold values are chosen by the use of SSA. Finally,active contour (AC) technique is used to identify the suspicious regions in themedical image. A comprehensive experimental analysis of the SSAMLT-BTSmodel is performed using benchmark dataset and the outcomes are inspectedin many aspects. The simulation outcomes reported the improved outcomesof the SSAMLT-BTS model over recent approaches with maximum accuracyof 95.95%.

Scale Invariant Feature Transform with Crow Optimization for Breast Cancer Detection

Mammography is considered a significant image for accurate breast cancer detection.Content-based image retrieval(CBIR)contributes to classifying the query mammography image and retrieves similar mammographic images from the database.This CBIR system helps a physician to give better treatment.Local features must be described with the input images to retrieve similar images.Exist-ing methods are inefficient and inaccurate by failing in local features analysis.Hence,efficient digital mammography image retrieval needs to be implemented.This paper proposed reliable recovery of the mammographic image from the data-base,which requires the removal of noise using Kalmanfilter and scale-invariant feature transform(SIFT)for feature extraction with Crow Search Optimization-based the deep belief network(CSO-DBN).This proposed technique decreases the complexity,cost,energy,and time consumption.Training the proposed model using a deep belief network and validation is performed.Finally,the testing pro-cess gives better performance compared to existing techniques.The accuracy rate of the proposed work CSO-DBN is 0.9344,whereas the support vector machine(SVM)(0.5434),naïve Bayes(NB)(0.7014),Butterfly Optimization Algorithm(BOA)(0.8156),and Cat Swarm Optimization(CSO)(0.8852).

Automated Artificial Intelligence Empowered Colorectal Cancer Detection and Classification Model

Colorectal cancer is one of the most commonly diagnosed cancers and it develops in the colon region of large intestine.The histopathologist generally investigates the colon biopsy at the time of colonoscopy or surgery.Early detection of colorectal cancer is helpful to maintain the concept of accumulating cancer cells.In medical practices,histopathological investigation of tissue specimens generally takes place in a conventional way,whereas automated tools that use Artificial Intelligence(AI)techniques can produce effective results in disease detection performance.In this background,the current study presents an Automated AI-empowered Colorectal Cancer Detection and Classification(AAI-CCDC)technique.The proposed AAICCDC technique focuses on the examination of histopathological images to diagnose colorectal cancer.Initially,AAI-CCDC technique performs preprocessing in three levels such as gray scale transformation,Median Filtering(MF)-based noise removal,and contrast improvement.In addition,Nadam optimizer with EfficientNet model is also utilized to produce meaningful feature vectors.Furthermore,Glowworm Swarm Optimization(GSO)with Stacked Gated Recurrent Unit(SGRU)model is used for the detection and classification of colorectal cancer.The proposed AAI-CCDC technique was experimentally validated using benchmark dataset and the experimental results established the supremacy of the proposed AAI-CCDC technique over conventional approaches.

Automated quadrilateral mesh generation for digital image structures

With the development of advanced imaging technology, digital images are widely used. This paper proposes an automatic quadrilateral mesh generation algorithm for multi-colour imaged structures. It takes an original arbitrary digital image as an input for automatic quadrilateral mesh generation, this includes removing the noise, extracting and smoothing the boundary geometries between different colours, and automatic all-quad mesh generation with the above boundaries as constraints. An application example is provided to demonstrate the usefulness and effectiveness of the proposed approach.

Bangla Handwritten Character Recognition Using Extended Convolutional Neural Network

The necessity of recognizing handwritten characters is increasing day by day because of its various applications. The objective of this paper is to provide a sophisticated, effective and efficient way to recognize and classify Bangla handwritten characters. Here an extended convolutional neural network (CNN) model has been proposed to recognize Bangla handwritten characters. Our CNN model is tested on “BanglalLekha-Isolated” dataset where there are 10 classes for digits, 11 classes for vowels and 39 classes for consonants. Our model shows accuracy of recognition as: 99.50% for Bangla digits, 93.18% for vowels, 90.00% for consonants and 92.25% for combined classes.

Digital Filter for Electrocardiogram Preprocessing Based on Microprocessor

This paper proposes a different method to eliminate base wander and power line interference in electrocardiogram, which introduces the integer coefficient filter theory and gives the detail for designing digital filter to remove these two normal noise signals. Signal from the MIT-BIH electrocardiogram database was used to test the performance of the filter. From the test results, the performance of the digital filer is reDT good. The filter coefficient is an integer number, therefore, the filtering algorithm can be successfully implemented on the microprocessor.

Newly Constructed Real Time ECG Monitoring System Using LabView

This paper deals with the removal of noise and base wander in the transfer of ECG data from the patients to the doctor. The process of the project is receiving ECG signals from the patient and reading the data in PC using an Arduino (an open-source electronics prototyping platform based on flexible, easy-to-use hardware and software) board, and then the signal is subjected to the removal of noise and base wander by amplification circuits in LabView (a system design software) software. Thus obtained ECG signal is sent to the doctors using an Ethernet cable or LAN connection. This enables the doctors to monitor any number of patients more accurately by sitting in a single room.

Improved polyreference time domain method for modal identification using local or global noise removal techniques

Modal identification involves estimating the modal parameters, such as modal frequencies, damping ratios, and mode shapes, of a structural system from measured data. Under the condition that noisy impulse response signals associated with multiple input and output locations have been measured, the primary objective of this study is to apply the local or global noise removal technique for improving the modal identification based on the polyreference time domain (PTD) method. While the traditional PTD method improves modal parameter estimation by over-specifying the computational model order to absorb noise, this paper proposes an approach using the actual system order as the computational model order and rejecting much noise prior to performing modal parameter estimation algorithms. Two noise removal approaches are investigated: a "local" approach which removes noise from one signal at a time, and a "global" approach which removes the noise of multiple measured signals simultaneously. The numerical investigation in this article is based on experimental measurements from two test setups: a cantilever beam with 3 inputs and 10 outputs, and a hanged plate with 4 inputs and 32 outputs. This paper demonstrates that the proposed noise-rejection method outperforms the traditional noise-absorption PTD method in several crucial aspects.

Distribution-Transformed Network for Impulse Noise Removal

This work aims to explore the restoration of images corrupted by impulse noise via distribution-transformed network (DTN), which utilizes convolutional neural network to learn pixel-distribution features from noisy images. Compared with the traditional median-based algorithms, it avoids the complicated pre-processing procedure and directly tackles the original image. Additionally, different from the traditional methods utilizing the spatial neighbor information around the pixels or patches and optimizing in an iterative manner, this work turns to capture the pixel-level distribution information by means of wide and transformed network learning. DTN fits the distribution at pixel-level with larger receptions and more channels. Furthermore, DTN utilities a residual block without batch normalization layer to generate a good estimate. In terms of edge preservation and noise suppression, the proposed DTN consistently achieves significantly superior performance than current state-of-the-art methods, particularly at extreme noise densities.

An adaptive image sparse reconstruction method combined with nonlocal similarity and cosparsity for mixed Gaussian-Poisson noise removal

Compressed sensing(CS) has achieved great success in single noise removal. However, it cannot restore the images contaminated with mixed noise efficiently. This paper introduces nonlocal similarity and cosparsity inspired by compressed sensing to overcome the difficulties in mixed noise removal, in which nonlocal similarity explores the signal sparsity from similar patches, and cosparsity assumes that the signal is sparse after a possibly redundant transform. Meanwhile, an adaptive scheme is designed to keep the balance between mixed noise removal and detail preservation based on local variance. Finally, IRLSM and RACoSaMP are adopted to solve the objective function. Experimental results demonstrate that the proposed method is superior to conventional CS methods, like K-SVD and state-of-art method nonlocally centralized sparse representation(NCSR), in terms of both visual results and quantitative measures.

An Efficient Operator-Splitting Method for Noise Removal in Images

In this work,noise removal in digital images is investigated.The importance of this problem lies in the fact that removal of noise is a necessary pre-processing step for other image processing tasks such as edge detection,image segmentation,image compression,classification problems,image registration etc.A number of different approaches have been proposed in the literature.In this work,a non-linear PDE-based algorithm is developed based on the ideas proposed by Lysaker,Osher and Tai[IEEE Trans.Image Process.,13(2004),1345-1357].This algorithm consists of two steps:flow field smoothing of the normal vectors,followed by image reconstruction.We propose a finite-difference based additive operator-splitting method that allows for much larger time-steps.This results in an efficient method for noise-removal that is shown to have good visual results.The energy is studied as an objective measure of the algorithm performance.

Image restoration using total variation and anisotropic diffusion equation

This paper proposes a new model for the image restoration which combines the total variation minimization with the“pure”anisotropic diffusion equation of Alvarez and Morel.According to the introduction of new diffusion term,this model can not only remove noise but also enhance edges and keep their locality.And it can also keep textures and large-scale fine features that are not characterized by edges.Due to these favorable characteristics,the processed images turn much clearer and smoother,meanwhile,their significant details are kept,which results in appealing vision.