Edge Preservation Research Articles

A multi‐modality paradigm for CT and MRI fusion with applications of quantum image processing

AbstractAs pixel resolution continues to increase in images acquired from different sensors, the measurement of the correlation between pixels and their properties requires numerous processing steps over multiple iterations. Quantum image processing (QIP) is a technology capable of processing exponentially large volumes of data within polynomial time. One such application is image fusion. In the field of radiography, computerized tomography (CT) images provide the structural information of bone tissues, and magnetic resonance MR images can provide the visualization of gray‐scale anatomical structures of soft tissues. With the help of CT and MR fusion, a composite image can be obtained containing information on both hard and soft tissues. Clinicians often have to switch between these modalities to trace various patterns for effective staging and diagnosis of various oncological diseases. In this study, a multilevel filtering‐based image fusion algorithm that efficiently fuses information from CT and MR images into a single image has been proposed. First, source images are processed with a rolling guidance filter, and the detail layer is calculated. The base layer is then computed using guided filtering to ensure a high level of edge preservation. Furthermore, to minimize noise and artifacts, the detail layers are fused using the Karhunen–Loeve transform, and the base layers are combined using the weighted superimposition principle. Experimental results demonstrate that the proposed methodology is subjectively more efficient than the existing state‐of‐the‐art methods.

Region-Growing Algorithm on CT Angiography Images for Detection of Gynecological Malignant Tumor

This paper aimed to explore pelvic lymphadenectomy for gynecological malignant tumors guided by computed tomography angiography (CTA) images under region-growing algorithm (RGA). 100 cases of malignant tumor patients who received pelvic lymphadenectomy in hospital from January 2018 to January 2020 were analyzed. Patients were classified into control group (CTA image) and experimental group (RGA-based CTA image), each with 50 cases. The overall accuracy (OA) of the pelvic CT image segmentation parameters under RGA, the watershed segmentation algorithm (WA), and the swarm intelligence optimization algorithm (SIOA) was compared. Comparisons of segmentation parameters, denoising performance, and CT imaging of patients as well as diagnosis rate and total efficiency rate were carried out. The results showed that overall accuracy (OA) of RGA was considerably higher versus watershed segmentation algorithm (WA) and swarm intelligence optimization algorithm (SIOA). However, false positive rate (FPR) and false negative rate (FNR) of RGA were greatly lower than those of other algorithms. RGA greatly improved the accuracy of pelvic tumor detection. The peak signal-to-noise ratio (PSNR) of RGA was superior to that of WA and SIOA, but differences in edge preservation index (EPI) value were not significant. The diagnosis rate of the experimental group was 48/50 (96%), while the diagnosis rate by manual means was 38/50 (76%). For the diagnosis rate and total efficiency, results of the experimental group were evidently higher in contrast to the control group ( P < 0.05 ). In conclusion, under RGA, CTA image-guided pelvic lymphadenectomy had good segmentation accuracy and denoising performance, and it was superior in total efficiency and diagnosis rate, which was worthy of clinical promotion.

Non-Local Patch Regression Algorithm-Enhanced Differential Photoacoustic Methodology for Highly Sensitive Trace Gas Detection

A non-local patch regression (NLPR) denoising-enhanced differential broadband photoacoustic (PA) sensor was developed for the high-sensitive detection of multiple trace gases. Using the edge preservation index (EPI) and signal-to-noise ratio (SNR) as a dual-criterion, the fluctuation was dramatically suppressed while the spectral absorption peaks were maintained by the introduction of a NLPR algorithm. The feasibility of the broadband framework was verified by measuring the C2H2 in the background of ambient air. A normalized noise equivalent absorption (NNEA) coefficient of 6.13 × 10−11 cm−1·W·Hz−1/2 was obtained with a 30-mW globar source and a SNR improvement factor of 23. Furthermore, the simultaneous multiple-trace-gas detection capability was determined by measuring C2H2, H2O, and CO2. Following the guidance of single-component processing, the NLPR processed results showed higher EPI and SNR compared to the spectra denoised by the wavelet method and the non-local means algorithm. The experimentally determined SNRs of the C2H2, H2O, and CO2 spectra were improved by a factor of 20. The NNEA coefficient reached a value of 7.02 × 10−11 cm−1·W·Hz−1/2 for C2H2. The NLPR algorithm presented good performance in noise suppression and absorption peak fidelity, which offered a higher dynamic range and was demonstrated to be an effective approach for trace gas analysis.

Denoising, Edge Aware Restoration and Enhancement of Single Shallow Coastal Water Image

The dissolved particles and their resultant scattering are the underlying cause of low contrast and blur thereby producing poor quality underwater images. Single-shot shallow coastal underwater images are much in need of the preprocessing steps viz. image enhancement and restoration. The underwater image processing operations like classification, object detection and computer vision require an enhancement/restoration preprocessing. The paper aims to restore the visibility of objects in turbid water images with its effective edge aware restoration cum enhancement model. The restricted rolling guidance filter on the DCP-based restoration method produces better edge aware restoration and denoised output image. The model-based (MB) dark channel prior (DCP) along with an edge emphasis and contrast enhancement achieves the essential dehazing and improvement in contrast for the heavily blurred underwater images. The subjective and objective projections are an evidence for the same. This edge preserving and denoising nature of the model is also exhibited with comparisons made with promising algorithms over the decade.

Multilayer residual sparsifying transform (MARS) model for low-dose CT image reconstruction.

Signal models based on sparse representations have received considerable attention in recent years. On the other hand, deep models consisting of a cascade of functional layers, commonly known as deep neural networks, have been highly successful for the task of object classification and have been recently introduced to image reconstruction. In this work, we develop a new image reconstruction approach based on a novel multilayer model learned in an unsupervised manner by combining both sparse representations and deep models. The proposed framework extends the classical sparsifying transform model for images to a Multilayer residual sparsifying transform (MARS) model, wherein the transform domain data are jointly sparsified over layers. We investigate the application of MARS models learned from limited regular-dose images for low-dose CT reconstruction using penalized weighted least squares (PWLS) optimization. We propose new formulations for multilayer transform learning and image reconstruction. We derive an efficient block coordinate descent algorithm to learn the transforms across layers, in an unsupervised manner from limited regular-dose images. The learned model is then incorporated into the low-dose image reconstruction phase. Low-dose CT experimental results with both the XCAT phantom and Mayo Clinic data show that the MARS model outperforms conventional methods such as filtered back-projection and PWLS methods based on the edge-preserving (EP) regularizer in terms of two numerical metrics (RMSE and SSIM) and noise suppression. Compared with the single-layer learned transform (ST) model, the MARS model performs better in maintaining some subtle details. This work presents a novel data-driven regularization framework for CT image reconstruction that exploits learned multilayer or cascaded residual sparsifying transforms. The image model is learned in an unsupervised manner from limited images. Our experimental results demonstrate the promising performance of the proposed multilayer scheme over single-layer learned sparsifying transforms. Learned MARS models also offer better image quality than typical nonadaptive PWLS methods.

CT Image Reconstruction Using NLMfuzzyCD Regularization Method.

To achieve this goal, one of the most commonly iterative reconstruction algorithm called Maximum Likelihood Expectation Maximization (MLEM) is used. The conventional Maximum Likelihood (ML) algorithm can achieve quality images in CT. However, it still suffers from optimal smoothing as the number of iterations increases. For solving this problem, this paper presents a novel statistical image reconstruction algorithm for CT, which utilizes a nonlocal means of fuzzy complex diffusion as a regularization term for noise reduction and edge preservation. The proposed model was evaluated on four test cases phantoms. Qualitative and quantitative analyses indicate that the proposed technique has higher efficiency for computed tomography. The proposed method yields significant improvements when compared with the state-of-the-art techniques.

Edge detection algorithm based on valley lines and watershed

The purpose of edge detection algorithm is to highlight the edge in the image, which is also the premise and key of image segmentation. However, the traditional edge detection algorithm will amplify the influence of noise in the process of derivative operation, and the noisy edges will often appear, which is not conducive to the accurate extraction of edge. To solve this problem, we propose an edge detection algorithm combining valley lines and watershed algorithm. In this algorithm, the bilateral filter is used to replace the Gaussian filter to achieve edge preserving and denoising. The rewritten Canny operator is used to calculate the low value points and get the valley lines of the image. This process can achieve the first denoising. Then, the valley lines are used to replace the discrete points of water injection and the watershed algorithm is used to calculate the segmentation results of the image. At this time, there are many pseudo edges around the main boundary, and the pseudo edges are deleted by setting the threshold, so as to achieve the effect of secondary denoising. The experimental results show that our method has good performance in noise resistance and edge continuity compared with other and traditional edge detection algorithms.

Adaptive Directional Cubic Convolution for Integrated Circuit Chip Defect Image Interpolation

An adaptive directional cubic convolution interpolation method for integrated circuit (IC) chip defect images is proposed in this paper, to meet the challenge of preserving edge and texture information. In the proposed method, Otsu thresholding technique is employed to distinguish strong edge pixels from weak ones and texture regions, and estimate the direction of strong edges, adaptively. Boundary pixels are pre-interpolated using the original bicubic interpolation method to help improve the interpolation accuracy of the interior pixels. The experimental results of both classic test images and IC chip defect images demonstrate that the proposed method outperforms the competing methods with better edge and texture preservation, interpolation quality, more natural visual effect of the interpolated images and reasonable computational time. The proposed method can provide high quality IC chip images for defect detection and has been successfully applied on practical vision inspection for IC chips

Restoration and enhancement of breast ultrasound images using extended complex diffusion based unsharp masking.

Ultrasound is a well-known imaging modality for the interpretation of breast cancer. It is playing very important role for breast cancer detection that are missed by mammograms. The image acquisition is usually affected by the presence of noise, artifacts, and distortion. To overcome such type of issues, there is a need of image restoration and enhancement to improve the quality of image. This paper proposes a single framework for denoising and enhancement of ultrasound images, where a smoothing filter is replaced with an extended complex diffusion-based filter in an unsharp masking technique. The performance evaluation of the proposed method is tested on real ultrasound breast cancer images database and synthetic ultrasound image. The performance evaluation comprises qualitative and quantitative evaluation along with comparative analysis of pre-existing and proposed method. The quantitative evaluation metrics are mean squared error, peak-signal-to-noise ratio, correlation parameter, normalized absolute error, universal quality index, similarity structure index, edge preservation index, a measure of enhancement, a measure of enhancement by entropy, and second derivative like measurement. The result specifies that the proposed method is better suited approach for the removal of speckle noise which follows Rayleigh distribution, restoration of information, enhancement of abnormalities, and proper edge preservation.

Speckle filtering of ultrasonic images using weighted nuclear norm minimization in wavelet domain

Medical images such as ultrasound images suffer from multiplicative speckle noise which reduces the contrast of ultrasound images and adversely affects the diagnosis process. Discrete Wavelet transform (DWT) is widely accepted in the area of image processing due to its time localization, multi-resolution and sparseness properties. DWT decomposes the noisy image into approximation coefficients and detail coefficients. The detail wavelet coefficients of clean image have sparsity property, whereas in the case of noisy image, sparsity of detail coefficients is reduced due to the presence of speckle noise. Thus, in the proposed method, low rank based Weighted Nuclear Norm Minimization (WNNM) is applied on detail coefficients to reveal the sparsity property of DWT. WNNM is applied on the group matrix of non-local similar patches of detail subbands of DWT to approximate the low-rank denoised version of the subbands. Moreover, less amount of edge and structure information is present in the approximation coefficients of DWT. Thus, in the proposed method, Non-local Means (NLM) filter with Square-Chord distance is also used to denoise speckle noise from approximation coefficients of DWT. Exhaustive experiments are conducted on various images such as real US images, simulated kidney image and synthetic image. It is observed that the mean improvement in terms of PSNR and CNR values of the proposed hybrid method are 1.50% and 3.81% respectively over WNNM based Despeckling using Low-Rank Approximation (DLRA) method. Qualitative and quantitative analyses show that the proposed hybrid method performed better than existing speckle reduction methods in terms of both speckle reduction and edge preservation.

Evaluation of the change in synthetic aperture radar imaging using transfer learning and residual network

Change detection from synthetic aperture radar images becomes a key technique to detect change area related to some phenomenon as flood and deformation of the earth surface. This paper proposes a transfer learning and Residual Network with 18 layers (ResNet-18) architecture-based method for change detection from two synthetic aperture radar images. Before the application of the proposed technique, batch denoising using convolutional neural network is applied to the two input synthetic aperture radar image for speckle noise reduction. To validate the performance of the proposed method, three known synthetic aperture radar datasets (Ottawa; Mexican and for Taiwan Shimen datasets) are exploited in this paper. The use of these datasets is important because the ground truth is known, and this can be considered as the use of numerical simulation. The detected change image obtained by the proposed method is compared using two image metrics. The first metric is image quality index that measures the similarity ratio between the obtained image and the image of the ground truth, the second metrics is edge preservation index, it measures the performance of the method to preserve edges. Finally, the method is applied to determine the changed area using two Sentinel 1 B synthetic aperture radar images of Eddahbi dam situated in Morocco.

Point cloud modeling and slicing algorithm for trajectory planning of spray painting robot

AbstractTo improve the uniformity of coating thickness and spraying efficiency, new point cloud modeling and slicing algorithm are proposed to deal with free-form surfaces for the spray painting robot in this paper. In the process of point cloud modeling, the edge preservation algorithm is firstly presented to avoid damaging the edge characteristic of the point cloud model. For the spraying gun, the coating deposition model on the free-form surface is determined on the basis of the elliptic double β distribution model. Then, the grid projection algorithm is proposed to obtain grid points between adjacent slices on the free-form surface. Based on this, the analytical solution for calculating the coating thickness at each grid point is obtained. The cross-section contour points are obtained by intercepting the point cloud model with several parallel slices, which is important for the trajectory planning of the spray painting robot. Finally, the uniformity of coating thickness is optimized in terms of the moving speed of the spraying gun and the slice thickness. The simulation and numerical experiment results show that the uniformity of coating thickness and spraying efficiency are improved using the proposed point cloud modeling and slicing algorithm.

Multi-modal medical image fusion framework using co-occurrence filter and local extrema in NSST domain

The fusion of vital imaging information has turned into a primary issue for biomedical applications. In this paper, a new multi-modality medical image fusion method is proposed in the shearlet domain. In the proposed algorithm, input images are decomposed using Non-subsampled shearlet transform (NSST) to get low and high frequencies components. A novel procedure to decompose and combine the base layers and detail layers using the local extrema (LE) approach is used and fused using a Co-occurrence filter (CoF) in low-frequency components. In high-frequency components, an edge-preserving image fusion strategy is performed using sum modified Laplacian (SML) to combine the high-frequency coefficients. The experimental outcomes and comparative analysis are performed over the Multi-modal medical image dataset using proposed and existing methods. It is exhibited through test outcomes and assessments that the proposed technique beats the cutting-edge fusion strategies concerning edge preservation in subjective and objective assessment criteria.

Binocular stereo vision calibration based on accurate ellipse detection algorithm of direct calculation and grating conversion check

With the rapid development of science and technology, binocular vision detection technology has become one of the most important technologies because of its high precision and stability. In order to achieve high-precision three-dimensional measurement of high-speed rail train, a binocular stereo vision system is built in this paper. The visual image is gray-scale processed, and then the integral image is used to realize the edge preservation processing of local mean square deviation, and then the denoised image is enhanced. At the same time, FAST algorithm based on accelerated segmentation detection is proposed to extract feature points. In order to solve the problem of camera calibration, this paper proposes a high-precision binocular stereo vision calibration algorithm based on direct calculation and grating conversion calibration. Firstly, the reliable information points are determined from the two-dimensional image, and then the edge image is obtained by effectively detecting the ellipse contour according to the set of information points. Finally, the ellipse parameters are extracted by using the ellipse contour information, and finally the camera parameters are solved by using the ring point. Compared with the traditional calibration method, the experimental results show that the average reprojection error of the two cameras is about 0.1 pixel, and the data accuracy is high, which proves the feasibility and theoretical correctness of the experimental method.

SAR Image Despeckling Algorithm Using Non-Local Means with Adaptive Filtering Strength

A new Non-Local Means (NLM) despeckling algorithm (AFS-NLM) with Adaptive Filtering Strength (AFS) is proposed to improve the performance of reducing multiplicative speckle and preserving the edges in SAR images. A modified Kuan filtering coefficient which can better characterize the homogeneous and edge regions of SAR image is formed by using the local mean and variance calculated in the Frost filtered image to improve the estimation of SAR image scene parameters. An improved NLM which adapts to the multiplicative noise characteristics is constructed by the new similarity measurement parameter estimated by the local mean ratio and the new adaptive decay factor estimated by the improved Kuan filtering coefficient. A new weighted filtering model which can automatically adjust the filtering strength is formed. In the new model, the improved NLM filters controlled by the skew smoothing parameters and the skew edge protection parameters are used to replace the local average value of pixels and the gray value of pixels in the classic Kuan filter model as weighting items, and the adaptive adjustment factor constructed by the improved Kuan filter coefficient is used to weight the two items. Experimental results and comparisons with several advanced despeckling algorithms in recent years show that the proposed algorithm has better speckle suppression and edge preservation performance.

Common Best Proximity Point Theorems in JS-Metric Spaces Endowed with Graphs

In this paper, we introduce a notion of G -proximal edge preserving and dominating G -proximal Geraghty for a pair of mappings, which will be used to present some existence and uniqueness results for common best proximity points. Here, the mappings are defined on subsets of a JS-metric space endowed with a directed graph. An example is also provided to support the results. Moreover, we apply our result to a similar setting, where the JS-metric space is endowed with a binary relation.

A Decision Based Neighbourhood Referred Asymmetrically Trimmed Modified Trimean for the Removal of High Density Salt and Pepper Noise in Images and Videos

A Decision Based Neighbourhood Referred Asymmetrically Trimmed Modified Trimean for the Removal of High Density salt and pepper noise in Images and videos is proposed. The proposed algorithm initially checks for the outliers in a 3 × 3 neighbourhood. If the processed pixel is noisy then check for the presence of noisy pixels with the 4 neighbours; If the 4 neighbours are found to hold outliers then mean of the 4 neighbours will replace the output. If the 4 neighbours are not noisy then the output is replaced by asymmetrically trimmed Modified Trimean. If all the pixels of the current processing window are noisy then the mean of all elements will replace the processed pixel. If the processed pixel does not hold the outlier then the pixel is termed as not noisy and left unaltered. The proposed algorithm exhibit excellent noise elimination capability with enhanced edge preservation capability. The algorithm was tested on a standard database and the results of the proposed algorithm were compared to 16standard and existing algorithms. The proposed algorithm exhibit excellent results in terms of both Quantitative and qualitative measures.

DRONE: Dual-Domain Residual-based Optimization NEtwork for Sparse-View CT Reconstruction.

Deep learning has attracted rapidly increasing attention in the field of tomographic image reconstruction, especially for CT, MRI, PET/SPECT, ultrasound and optical imaging. Among various topics, sparse-view CT remains a challenge which targets a decent image reconstruction from very few projections. To address this challenge, in this article we propose a Dual-domain Residual-based Optimization NEtwork (DRONE). DRONE consists of three modules respectively for embedding, refinement, and awareness. In the embedding module, a sparse sinogram is first extended. Then, sparse-view artifacts are effectively suppressed in the image domain. After that, the refinement module recovers image details in the residual data and image domains synergistically. Finally, the results from the embedding and refinement modules in the data and image domains are regularized for optimized image quality in the awareness module, which ensures the consistency between measurements and images with the kernel awareness of compressed sensing. The DRONE network is trained, validated, and tested on preclinical and clinical datasets, demonstrating its merits in edge preservation, feature recovery, and reconstruction accuracy.

A Multi-Objective Enhanced Fruit Fly Optimization (MO-EFOA) Framework for Despeckling SAR Images using DTCWT based Local Adaptive Thresholding

ABSTRACT The importance of Satellite Aperture Radar (SAR) imagery systems is increasing day-by-day in various field such as earth observation, hi-technology war mechanisms, etc. The images captured by SAR imagery systems are mainly used to detect and classify objects captured in the images. Due to the complexity of the image capturing process, SAR images can be highly noisy – often consisting of multiplicative noise, also known as speckle. To detect or classify objects in SAR images, speckle noise must be removed from images. During despeckling process, the preservation of important information in the SAR images while removing noise such as edge or patterns is a crucial task. Despeckling methods are liable to compromise on edge preservation ability while aspiring for good quality denoised images. Many researchers have proposed wavelet transform based despeckling approaches such as Discrete Wavelet Transform (DWT), Undecimated Wavelet Transform (UDWT), Dual Tree Complex Wavelet Transform (DTCWT). In these approaches, finding the best values of the coefficients plays an important role in yielding excellent denoised images with preserved edges. In this paper, we have proposed a novel optimization framework that optimizes thresholding coefficients of DTCWT despeckling method for SAR images. The proposed optimization framework is based on Fruit Fly Optimization (FOA) algorithm. The approach is a multi-objective optimization algorithm that is used to find maximum values for Peak Signal-to-Noise Ratio (PSNR), Mean Structural Similarity Index (MSSIM) and Equivalent number of look (ENL). The maximum value of MSSIM indicates high edge preservation capacity, whereas maximum PSNR value indicates good quality denoising of images. The maximum ENL value represents a good speckle-noise smoothing capability. We have applied our framework over some classical images as well as over SAR images of MSTAR dataset. In our experiments, we found that our proposed framework results in the excellent PSNR 36.87 dB, 35.4 dB and 37.8 dB, MSSIM values 0.92, 0.93 and 0.92, respectively, in the case of lena image, MSTAR dataset image and TerraSAR-X dataset image.

Topological Data Analysis For Evaluating PDE-based Denoising Models

Image denoising is process of removing the noise (i.e. artifacts) in digital image. Noise reduction is an essential process of image processing in order to improve, analyze and interpret important information in an image. Edges are important to the visual appearance of images, to preserve important features such as edges and corners during the noise reduction process. A class of fourth- and second-order partial differential equations (PDEs) are used to optimize the trade-off between noise removal and edge preservation. Image quality assessment plays an important role in various image processing applications. It is still an active field of research. Several techniques have been suggested for measuring image quality but none of them are ideal for measuring the quality. This paper presents a new assessment of image quality based on topological data analysis (TDA) which is used for evaluating noise removal from colour images and also for assessing the performance of PDE-based denoising models. The experimental results show that the proposed assessment model gives high correlation. Furthermore, the proposed method provides very low computational load and similar extraction of characteristics to human perceptional assessment.