Edge Enhancement Research Articles

Combination of edge enhancement and cold diffusion model for low dose CT image denoising.

Since the quality of low dose CT (LDCT) images is often severely affected by noise and artifacts, it is very important to maintain high quality CT images while effectively reducing the radiation dose. In recent years, the representation of diffusion models to produce high quality images and stable trainability has attracted wide attention. With the extension of the cold diffusion model to the classical diffusion model, its application has greater flexibility. Inspired by the cold diffusion model, we proposes a low dose CT image denoising method, called CECDM, based on the combination of edge enhancement and cold diffusion model. The LDCT image is taken as the end point (forward) of the diffusion process and the starting point (reverse) of the sampling process. Improved sobel operator and Convolution Block Attention Module are added to the network, and compound loss function is adopted. The experimental results show that CECDM can effectively remove noise and artifacts from LDCT images while the inference time of a single image is reduced to 0.41 s. Compared with the existing LDCT image post-processing methods, CECDM has a significant improvement in all indexes.

Blind image quality assessment using Beltrami filter-based contrast features (BF-bCF) & LSTM network

ABSTRACT Advanced networks excel in Blind Image Quality Assessment (BIQA), however accurate estimation of quality scores remains challenging due to unrevealed features extricated under various distortions. This article presents a Beltrami filter-based Contrast feature and long short-term memory (BF-bCF & LSTM) framework for feature extraction, suitable for both authentic and synthetic image distortions. The framework comprises four modules: an edge preservation and enhancement module, a distortion-conscious module, a weight module, and a quality-predicting network. The edge enhancement module assists the distortion-conscious module by enhancing the overall quality of the input grayscale image. The distortion-conscious module uses a modified Difference of Gaussian (DoG) measure to mitigate the distortion and assign patch weights in the filtered image. The proposed BIQA framework assimilating LSTM effectively extricates significant components using principal component analysis (PCA) and predicts nearer scores. Experiments on synthetic and authentic datasets showed superior performance relating to SROCC and PLCC above 0.9.

Edge enhancement and feature modulation based network for light field depth estimation

Estimating depth from light field images is a critical issue in light field applications. While learning-based methods have made significant strides in light field depth estimation, achieving high accuracy and speed simultaneously remains a major challenge. This paper proposes a light field depth estimation network based on edge enhancement and feature modulation, which significantly improves depth estimation results by emphasizing inter-view correlations while preserving image edge features. Specifically, to prioritize edge details, we introduce an Edge-Enhanced Cost Constructor (EECC) that integrates edge information with existing cost constructors to improve depth estimation performance in complex areas. Furthermore, most light field depth estimation networks utilize only sub-aperture images (SAIs) without considering the inherent angular information in macro-pixel image (MacPI). To address this limitation, we propose the MacPI-Guided Feature Modulation (MGFM) module, which leverages angular information between different views in MacPI to modulate features at each view. Experimental results show that our method not only performs excellently on synthetic datasets but also demonstrates outstanding generalization on real-world datasets, achieving a better balance between accuracy and computation speed.

Reconfigurable Homojunction Phototransistor for Near-Zero Power Consumption Artificial Biomimetic Retina Function.

Semiconductor photodetectors integrating preliminary signal-processing functions play a vital role in artificial biomimetic retina systems. Herein, we propose a tungsten diselenide (WSe2) phototransistor with a dual-layer gate dielectric and an asymmetric graphene insert structure. This phototransistor exhibits a bidirectional self-powered photocurrent by controlling the gate voltage via the formation of reconfigurable p+-p and n-p homojunctions in the channel from the asymmetric graphene insert. At the same time, the nonvolatile electron and hole stored in the dual-layer gate dielectric are generated using a temporary gate voltage, which can replace the gate voltage to regulate the channel charge. Moreover, the photocurrent shows a linear relation with the temporary programming gate voltage. The phototransistor exhibits a rectification ratio of >4 orders of magnitude without the gate voltage, indicating its significant capability to operate in a fully self-powered mode with near-zero power consumption. Based on the device characteristics, we successfully simulate the biological functions of the photoreceptor layer and bipolar cell layer in the retinal receptive field. The identification of the object motion direction in the receptive field can be realized by integrating three programmable devices on the chip. Furthermore, edge enhancement of the image is achieved by independently modulating the light response of each pixel in the sensor by varying the programming gate voltage. This study will promote the developing progress of future artificial biomimetic retina systems.

Concurrent Image Differentiation and Integration Processings Enabled By Polarization‐Multiplexed Metasurface

AbstractOptical computing and image processing performed by sensor front‐end metasurfaces is receiving increasing interest because of advantages such as significant reduction of latency time, energy consumption, and system complexity. Despite the rapid progress, concurrent processing, the most important feature of electronic computing, has not yet been well implemented in optical computing. Here, a metasurface‐based optical image processor that can perform optical differentiation and integration tasks simultaneously is proposed. This optical front‐end processor integrates two coherent transfer functions corresponding to differential and integral convolution kernels into a built‐in metasurface by polarization encoding, allowing concurrent processing of multiple all‐optical computational tasks. The simultaneous differentiation and integration operations on images for edge enhancement and denoising are demonstrated at multiple visible wavelengths. This concurrent processing architecture paves a promising pathway toward multifunctional and higher‐speed image processing for machine vision and biomedical imaging and shows the potential to expedite and potentially supplant certain digital neural network algorithms.

A Method for Fingerprint Edge Enhancement Based on Radial Hilbert Transform

Fingerprints play a significant role in various fields due to their uniqueness. In order to effectively utilize fingerprint information, it is necessary to enhance image quality. This paper introduces a method based on Radial Hilbert transform (RHLT), which simulates the vortex filter using the point spread function (PSF) of spiral phase plate (SPP) with a topological charge l=1, for fingerprint edge enhancement. The experimental results show that the processed fingerprint image has more distinct edges, with an increase in information entropy and average gradient. Unlike classical edge detection operators, the fingerprint edge image obtained by the RHLT method exhibits a lower mean square error (MSE) and a higher peak signal-to-noise ratio (PSNR). This indicates that the RHLT method provides more accurate edge detection and demonstrates higher noise-resistance capabilities. Due to its ability to highlight edge information while preserving more original features, this method has great application potential in fingerprint image processing.

An Edge-Enhanced Network for Polyp Segmentation.

Colorectal cancer remains a leading cause of cancer-related deaths worldwide, with early detection and removal of polyps being critical in preventing disease progression. Automated polyp segmentation, particularly in colonoscopy images, is a challenging task due to the variability in polyp appearance and the low contrast between polyps and surrounding tissues. In this work, we propose an edge-enhanced network (EENet) designed to address these challenges by integrating two novel modules: the covariance edge-enhanced attention (CEEA) and cross-scale edge enhancement (CSEE) modules. The CEEA module leverages covariance-based attention to enhance boundary detection, while the CSEE module bridges multi-scale features to preserve fine-grained edge details. To further improve the accuracy of polyp segmentation, we introduce a hybrid loss function that combines cross-entropy loss with edge-aware loss. Extensive experiments show that the EENet achieves a Dice score of 0.9208 and an IoU of 0.8664 on the Kvasir-SEG dataset, surpassing state-of-the-art models such as Polyp-PVT and PraNet. Furthermore, it records a Dice score of 0.9316 and an IoU of 0.8817 on the CVC-ClinicDB dataset, demonstrating its strong potential for clinical application in polyp segmentation. Ablation studies further validate the contribution of the CEEA and CSEE modules.

Improved Building Extraction from Remotely Sensed Images by Integration of Encode–Decoder and Edge Enhancement Models

Improved Building Extraction from Remotely Sensed Images by Integration of Encode–Decoder and Edge Enhancement Models

A Novel Network for Low-Dose CT Denoising Based on Dual-Branch Structure and Multi-Scale Residual Attention.

Deep learning-based denoising of low-dose medical CT images has received great attention both from academic researchers and physicians in recent years, and has shown important application value in clinical practice. In this work, a novel two-branch and multi-scale residual attention-based network for low-dose CT image denoising is proposed. It adopts a two-branch framework structure, to extract and fuse image features at shallow and deep levels respectively, to recover image texture and structure information as much as possible. We propose the adaptive dynamic convolution block (ADCB) in the local information extraction layer. It can effectively extract the detailed information of low-dose CT denoising and enables the network to better capture the local details and texture features of the image, thereby improving the denoising effect and image quality. Multi-scale edge enhancement attention block (MEAB) is proposed in the global information extraction layer, to perform feature fusion through dilated convolution and a multi-dimensional attention mechanism. A multi-scale residual convolution block (MRCB) is proposed to integrate feature information and improve the robustness and generalization of the network. To demonstrate the effectiveness of our method, extensive comparison experiments are conducted and the performances evaluated on two publicly available datasets. Our model achieves 29.3004 PSNR, 0.8659 SSIM, and 14.0284 RMSE on the AAPM-Mayo dataset. It is evaluated by adding four different noise levels σ = 15, 30, 45, and 60 on the Qin_LUNG_CT dataset and achieves the best results. Ablation studies show that the proposed ADCB, MEAB, and MRCB modules improve the denoising performances significantly. The source code is available at https://github.com/Ye111-cmd/LDMANet .

MEEAFusion: Multi-Scale Edge Enhancement and Joint Attention Mechanism Based Infrared and Visible Image Fusion.

Infrared and visible image fusion can integrate rich edge details and salient infrared targets, resulting in high-quality images suitable for advanced tasks. However, most available algorithms struggle to fully extract detailed features and overlook the interaction of complementary features across different modal images during the feature fusion process. To address this gap, this study presents a novel fusion method based on multi-scale edge enhancement and a joint attention mechanism (MEEAFusion). Initially, convolution kernels of varying scales were utilized to obtain shallow features with multiple receptive fields unique to the source image. Subsequently, a multi-scale gradient residual block (MGRB) was developed to capture the high-level semantic information and low-level edge texture information of the image, enhancing the representation of fine-grained features. Then, the complementary feature between infrared and visible images was defined, and a cross-transfer attention fusion block (CAFB) was devised with joint spatial attention and channel attention to refine the critical supplemental information. This allowed the network to obtain fused features that were rich in both common and complementary information, thus realizing feature interaction and pre-fusion. Lastly, the features were reconstructed to obtain the fused image. Extensive experiments on three benchmark datasets demonstrated that the MEEAFusion proposed in this research has considerable strengths in terms of rich texture details, significant infrared targets, and distinct edge contours, and it achieves superior fusion performance.

Restriction-induced time-dependent transcytolemmal water exchange: Revisiting the Kӓrger exchange model

The Kӓrger model and its derivatives have been widely used to incorporate transcytolemmal water exchange rate, an essential characteristic of living cells, into analyses of diffusion MRI (dMRI) signals from tissues. The Kӓrger model consists of two homogeneous exchanging components coupled by an exchange rate constant and assumes measurements are made with sufficiently long diffusion time and slow water exchange. Despite successful applications, it remains unclear whether these assumptions are generally valid for practical dMRI sequences and biological tissues. In particular, barrier-induced restrictions to diffusion produce inhomogeneous magnetization distributions in relatively large-sized compartments such as cancer cells, violating the above assumptions. The effects of this inhomogeneity are usually overlooked. We performed computer simulations to quantify how restriction effects, which in images produce edge enhancements at compartment boundaries, influence different variants of the Kӓrger-model. The results show that the edge enhancement effect will produce larger, time-dependent estimates of exchange rates in e.g., tumors with relatively large cell sizes (>10 μm), resulting in overestimations of water exchange as previously reported. Moreover, stronger diffusion gradients, longer diffusion gradient durations, and larger cell sizes, all cause more pronounced edge enhancement effects. This helps us to better understand the feasibility of the Kärger model in estimating water exchange in different tissue types and provides useful guidance on signal acquisition methods that may mitigate the edge enhancement effect. This work also indicates the need to correct the overestimated transcytolemmal water exchange rates obtained assuming the Kärger-model.

Study on the impact of camera ISP algorithms on stripe structured light 3D reconstruction and the improvement of 3D reconstruction accuracy by photon input

This paper investigates the impact of camera image signal processing (ISP) algorithms on stripe structured light 3D reconstruction and explores the improvement of 3D reconstruction accuracy by photon input. Existing 3D reconstruction technologies have broad applications in fields such as intelligent manufacturing, healthcare, and consumer electronics, but their high precision requirements often cannot be met by current ISP algorithms. By using handheld devices to capture images and combining key techniques such as the multi-step phase shifting method, multi-frequency phase unwrapping method, and triangulation method, this paper conducts an in-depth study on the application of photon input in 3D reconstruction. The study demonstrates that using non-visual information (RAW images) as input can significantly improve reconstruction accuracy, producing more accurate results compared to images processed by ISP. The paper also quantifies the impact of ISP processing on 3D reconstruction results by comparing the depth information and point cloud data of two sets of images. Experimental results show that disabling certain ISP algorithms, such as bilateral noise filtering (BNF), edge enhancement (EEH), and non-local means denoising (NLM), can further improve reconstruction accuracy and reduce errors. In conclusion, this paper proposes a photon image-based 3D reconstruction method that, combined with artificial intelligence technology and differentiable point cloud rendering techniques, holds promise for achieving higher precision and faster 3D reconstruction. This technology is of great significance in practical applications, particularly in the field of industrial close-range 3D reconstruction.

Quantitative determination of fractional topological charge based on the rotational Doppler effect

The utilization of fractional-order vortex beams extends the diversity of optical field manipulation, permits for more flexible control over beam propagation, and provides novel applications in optical communications, edge enhancement imaging, and particle manipulation. However, compared with the integer-order vortex beams, the topological charge measurement techniques for fractional-order vortex beams are not well developed, impeding the further exploration of its applications. In this paper, the frequency signal of rotational Doppler effect and corresponding broadening behavior under the fractional-order vortex beam illumination were analyzed. When the fractional topological charge approaches a half integer, the broadening is minimized. Leveraging this relationship, we designed a phase-compensated scheme coupled with signal-to-noise ratio detection to realize the real-time fractional topological charge measurement. The single pixel photodetector was used and eliminated the need for two-dimensional image acquisition and analysis, ensuring efficient acquisition and quantitative analysis. Both theoretical and experimental results confirm the feasibility of this method, thereby advancing the comprehension of the optical Doppler effect and potentially paving the way for future investigations into fractional vortex beams.

Enhancing magnetic source edges using the tilt angle of the analytic‐signal amplitudes of the horizontal gradient

AbstractEnhancing magnetic data is often complicated due to the non‐vertical orientation of the geomagnetic field and the orientation of remanent source magnetization. The complication can be reduced by reducing the data to the pole (mathematically making the geomagnetic field vertical), but this reduction process is problematic. The analytic‐signal amplitude can be used to enhance the edges of two‐dimensional sources without a reduction to the pole. However, the shape of the analytic‐signal amplitude is weakly dependent on the magnetization direction for grid data. This study presents an improved technique, namely the tilt angle of the analytic‐signal amplitudes of the horizontal gradient of the vertical integral. This quantity is also only weakly dependent on the magnetization direction and outlines the edges as well or somewhat better than other methods. It also implicitly involves second derivatives of the magnetic field, and we use synthetic data to demonstrate that noise is not amplified as much as it is when using other edge enhancement techniques that implicitly use second derivatives. A dataset of the Apiaí Terrane, Brazil, shows good lateral continuity of features compared with other edge‐enhancement methods, and subtle features like faults are easier to identify in the images generated by our new method. Upward continuation of the field, which is normally required, was not necessary to reduce the impact of noise on this field example.

Spin–orbit optical broadband achromatic spatial differentiation imaging

Spatial optical analog differentiation allows ultrahigh-speed and low-power-consumption of image processing, as well as label-free imaging of transparent biological objects. Optical analog differentiation with broadband and incoherent sources is appealing for its multi-channels and multi-task information processing, as well as the high-quality differentiation imaging. Currently, broadband and incoherent optical differentiation is still challenging. Here, a compact and broadband achromatic optical spatial differentiator is demonstrated based on the intrinsic spin–orbit coupling in a natural thin crystal. By inserting a uniaxial crystal just before the camera of a conventional microscope, the spin to orbit conversion will embed an optical vortex to the image field and make a second-order topological spatial differentiation to the field, thus an isotropic differential image will be captured by the camera. The wavelength-independent property of the intrinsic spin–orbit coupling effect allows us to achieve broadband analog computing and achromatic spatial differentiation imaging. With this differentiation imaging method, both amplitude and pure phase objects are detected with high contrast. Transparent living cells and biological tissues are imaged with their edge contours and intracellular details protruded in the edge detection mode and edge enhancement mode, respectively. These findings pave the way for optical analog computing with broadband incoherent light sources and concurrently drive the advancement of high-performance and cost-effective phase contrast imaging.

High-speed wafer surface defect detection with edge enhancement via optical spatial filtering in serial time-encoded imaging

With the rapid development of the chip and metasurface industries, high-speed defect detection of wafer during semiconductor batch manufacturing has become increasingly important for yield control. Here, we propose a high-speed, macro-scale wafer surface defect detection method with enhanced image edges, via optical spatial filtering in serial time-encoded imaging. By using blazed gratings to spatially project different wavelength components of pulsed light into a one-dimensional line, together with dispersive Fourier time stretching technology, a high-speed serial time-encoded imaging system based on a single pixel detector is constructed for testing the wafer surface defects, and optical spatial filtering is introduced to improve the imaging quality. Experiments show high-pass spatial filtering effectively restrains environmental interference and enhances image edge detection. Small target detection is achieved without a complex image algorithm. Our solution extends optical spatial filtering to serial time-encoded imaging, not only permitting wafer macro scale defect detection with edge enhancement, but also having potential significance for imaging lidar, imaging spectrometers, ghost imaging technology, and more.

Fuzzy C-Means clustering based selective edge enhancement scheme for improved road crack detection

One of the most serious problems currently in the world is road cracking, which could lower traffic safety and raise the risk of road accidents. A substantial sum of money is spent annually on maintaining and fixing the roads. However, manual crack detection is less accurate and takes longer. The focus of this study is on how artificial intelligence can be applied to image processing to improve crack detection. This study introduces the pixel classification enhancement fuzzy C-Means clustering, a new fuzzy C-Means clustering algorithm. The road crack detection from image is achieved automatically by utilizing second order pixel differences, an exponentially varying intensity dependent edge pixel enhancement scaling factor and intensity-based edge & non-edge fuzzy factors that helps to detect the cracks even in low contrast photos. This method doesn't necessitate training with image datasets. In addition, it can recognize edges or fractures in a range of unseen images. According to standard performance parameters, the experimental results demonstrate that the novel fuzzy C-Means segmentation-based approach performs better than many of the existing methods for contaminated or non-contaminated images in identifying patholes, transverse, and longitudinal cracks from road photos, as well as alligator cracks. The proposed method can assist managers or maintenance engineers in preventing further damage and quickly identifying different types of cracks with less manual labor and expense.

Multi-Resolution Learning and Semantic Edge Enhancement for Super-Resolution Semantic Segmentation of Urban Scene Images.

Super-resolution semantic segmentation (SRSS) is a technique that aims to obtain high-resolution semantic segmentation results based on resolution-reduced input images. SRSS can significantly reduce computational cost and enable efficient, high-resolution semantic segmentation on mobile devices with limited resources. Some of the existing methods require modifications of the original semantic segmentation network structure or add additional and complicated processing modules, which limits the flexibility of actual deployment. Furthermore, the lack of detailed information in the low-resolution input image renders existing methods susceptible to misdetection at the semantic edges. To address the above problems, we propose a simple but effective framework called multi-resolution learning and semantic edge enhancement-based super-resolution semantic segmentation (MS-SRSS) which can be applied to any existing encoder-decoder based semantic segmentation network. Specifically, a multi-resolution learning mechanism (MRL) is proposed that enables the feature encoder of the semantic segmentation network to improve its feature extraction ability. Furthermore, we introduce a semantic edge enhancement loss (SEE) to alleviate the false detection at the semantic edges. We conduct extensive experiments on the three challenging benchmarks, Cityscapes, Pascal Context, and Pascal VOC 2012, to verify the effectiveness of our proposed MS-SRSS method. The experimental results show that, compared with the existing methods, our method can obtain the new state-of-the-art semantic segmentation performance.

Mineralogy and rare earth elements spatial distribution in the carboniferous rocks of the eastern El Galala El Bahariya, Egypt

The Carboniferous rocks in the eastern part of El Galala El Bahariya were investigated using integrated field and laboratory techniques to determine their mineralogy, rare earth elements (REEs) distribution, and structural lineament density. The succession is mainly composed of argillaceous and minor arenaceous rocks, exhibiting variations in lithology across the study area. The essential minerals of these rocks are quartz, kaolinite, and illite. The accessory minerals include microcline, gypsum, anhydrite, halite, barite, hematite, pyrite, anatase and gibbsite, in addition to, the radioactive and REEs-bearing minerals such as uranophane, xenotime, monazite, and zircon. These minerals are reported in the rocks of the study area for the first time. The types, forms, habits, and modes of occurrence of the recorded minerals indicate multiple origins: allogenic–authigenic, and primary-secondary. REEs in the rocks exhibit enriched patterns with a negative Eu anomaly, likely due to low plagioclase content or and/or Eu removal by alteration processes. The distribution of REEs is influenced by textural attributes, with finer sediments in the southern part showing higher REEs content, ascribed to the high clay content and presence of gibbsite. The preferential mobility of LREEs is evident, explaining elevated LREEs/HREEs ratios in the rocks. Utilizing remote sensing techniques, lithological units and alteration zones were determined using decorrelation stretch and band ratio methods. The structural features, identified by Laplacian filter and edge enhancement, revealed the presence of NW–SE, N–S, and NE–SW faults that structurally regulate alteration zones and REEs distribution. These alteration zones are associated with clay minerals, REEs concentrations, and high lineament structure density. Spatial distribution maps highlight higher REEs concentrations in the southern part of the study area. These findings were validated using various analytical methods, including mineralogical and geochemical investigations, main component analysis, minimum noise fraction, decorrelation stretch, and spectral reflectance studies. They provide new insights into the REEs potential of the Carboniferous rocks and heighten our understanding of REEs genesis and distribution in the region.

DdeNet: A dual-domain end-to-end network combining Pale-Transformer and Laplacian convolution for sparse view CT reconstruction

Sparse view (SV) computed tomography (CT) is a clinical diagnostic technique aimed at reducing radiation dose to the human body from X-rays. However, SVCT reconstructed using conventional filtered back-projection (FBP) algorithms will produce severe streak artifacts. In recent years, convolutional neural networks (CNNs) have demonstrated considerable success in addressing the inverse problem of SVCT reconstruction. However, the local convolutional operations of CNNs ignores long-range dependencies of contextual feature information, thereby limiting their capability in feature extraction. To address this limitation, we propose a dual-domain end-to-end network (DdeNet) combining Pale-Transformer and Laplacian convolution for SVCT reconstruction. Initially, in the projection domain, a UNet is employed to restore the interpolated sinogram. Subsequently, in the image domain, we introduce Pale-Transformer and Laplacian convolution to design a dual-stream feature fusion network for finely restoring the CT images reconstructed by FBP. The dual-stream feature fusion network comprises an image restoration network (IRN) module and an edge enhancement network (EEN) module. The depthwise separable convolution based modified pale-shaped self-attention mechanism in Pale-Transformer captures global feature information of the CT image in the IRN, while the Laplacian convolution and multi-scale convolution block with a squeeze and excitation mechanism in the EEN further extract and restore edge feature information of the CT image. Finally, the feature information output from IRN and EEN is fused along the channel dimension and then convolved to obtain the final reconstructed CT image. Experimental results demonstrate that DdeNet exhibits superior generalization and reconstruction performance compared to the previous CNN or Transformer-based reconstruction methods.