Edge Preservation Research Articles

A low-dose CT image denoising method based on state space model

Abstract Low-dose CT medical imaging techniques introduce noise while reducing radiation risks, necessitating denoising processing. However, existing mainstream denoising methods face a difficult trade-off between preserving image detail information and accurately removing noise. To address this issue, we propose a low-dose CT image denoising method based on a state space model. Firstly, a dynamic edge information enhancement module is introduced to automatically extract edge information from images using a learnable LoG operator and fuse it into feature layers at different scales to suppress edge information loss caused by denoising processes. Secondly, a U-net encoder based on state space estimation is designed to dynamically model spatial relationships between pixels through neighborhood filtering, enabling consideration of local differences in pixel values during denoising and better preservation of edges and textures. Compared to existing denoising methods, our approach achieves stable noise removal in low-dose CT images while preserving the original texture structure.

A wavelet CNN with appropriate feed-allocation and PSO optimized activations for diabetic retinopathy grading

This work modifies the architecture of conventional CNN with the integration of Multi-resolution Analysis (MRA) in a CNN framework for Diabetic Retinopathy (DR) diagnosis and grading. Here, the HF sub-bands are subjected to optimized activations and are directly fed to the fully connected layers, as it encompasses edge features. Unlike FD-Relu, the proposed function preserves significant negative coefficients, compared to the S-Relu, the proposed third-order S-Relu is optimized such that it sustains the activations in the range suitable for the wavelet coefficients. The coefficients of higher-order terms of the proposed 3rd-order S-Relu are optimized with PSO, fitting the maximum energy of the wavelet sub-bands to ensure High Frequency (HF) edge preservation. The authors re-architecture 3 different CNNs published in the Retinal Image analysis field, with spatial and wavelet inputs with optimized activations. The highest accuracy of 96% is attained with the AlexNet re-architecture, with 35,126 fundus images secured from the Kaggle dataset. As we can infer the proposed re-architecture wavelet CNN outperformed the multiscale shallow CNNs, multiscale attention net, and stacked CNNs with a 6.6, 0.3, 0.7 per cent increase in accuracy. The entire implementation of the wavelet CNN is made available under source code.

A Novel Fractional-Order Non-Convex TVα,p Model in Image Deblurring

In this paper, we propose a non-convex model with fractional-order applied to image deblurring problems. In the new model, fractional-order gradients have been introduced to preserve detailed features, and a source term with a blurry kernel is used for deblurring. This aspect of the model ensures that it can handle various blurring scenarios. Additionally, we devise an algorithm that maintains the non-expansiveness of the support set for image gradients, serving as a critical component in our approach to address image deblurring issues. After approximate linearization, the algorithm can be easily implemented. Some standard image processing techniques similar to fast Fourier transform can be utilized. Global convergence has likewise been confirmed and established. Moreover, we have also demonstrated that the proposed deblurring algorithm exhibits edge preservation properties. Compared with several existing classic models, the proposed method maintains a good balance between detail preservation, edge preservation, and deblurring. In addition, compared with several classic methods, the proposed method improved PSNR and SSIM by 0.9733 and 0.0111, respectively.

An adaptive low‐rank group sparse model based on edge‐preserving for eliminating mixed noise in SRTM

AbstractThe Shuttle Radar Topography Mission (SRTM) is a digital representation of the terrain surface morphology that contains rich terrain information and is widely used in environmental analyses. However, SRTM is adversely affected by mixed noise, which typically include random and stripe noise. Mixed noise results in the significant loss of topographic information, which reduce the validity of related research. To eliminate mixed noise in SRTM data, we propose an adaptive low‐rank group sparse model based on edge preservation (ALGS_EP) to remove mixed noise from datasets. The method relies on a low‐rank group sparse model that considers the gradient features of the terrain. It calculates a terrain factor to adapt the noise elimination model to terrain changes. Additionally, it integrates with the edge structure of elevation data and applies a double‐gradient constraint to preserve the structural details of the elevation data. The proposed model, built upon the alternating direction multiplier method framework, enhances the traditional weighted kernel paradigm minimization algorithm by introducing variable weights that adjust according to the gradient of elevation data during iterations. Additionally, it incorporates the correlation between strip noise and residual data blocks when computing the iteration count, ensuring an iterative solution approach that converges to the optimal solution. We used ALGS_EP to process global SRTM 1 data and published a higher‐quality and higher‐precision elevation dataset. The elevation data noise before and after noise elimination were statistically analyzed. Simulated and empirical results show that the model is highly robust and more effective than existing methods in both visual and quantitative evaluations. The noise elimination rate was 97.6%, compared to the original data. Therefore, this research was valuable for applications that use digital elevation model as an important data layer.

Improvement of horizontal streak on disparity map thru parameter optimization for stereo vision algorithm

In this paper, an improved local based stereo vision disparity map (SVDM) algorithm is proposed. The proposed local based SVDM algorithm include four stages and they are matching cost computation, cost aggregation disparity optimization and disparity refinement. The matching cost computation started by combining pixel to pixel matching techniques, which are absolute difference (AD) and gradient matching (GM) in producing the initial disparity map. Next, the cost aggregation uses minimum spanning tree (MST) segmentation, which equipped with edge preserving properties and noise filtering. Then, disparity optimization uses local approach with winner-take-all (WTA) technique. At the final stage, disparity refinement uses bilateral filter (BF) with weighted median (WM), which can improve the disparity map through noise removing and edges preserving. Then, the research continues to optimize the proposed local based SVDM algorithm through parameters optimization in obtaining the final disparity map. Here, multiple parameters from the proposed SVDM algorithm are manipulated and they are constant values for GM and several constant parameters in BF. By selecting the optimum parameter values, the performance of the proposed SVDM algorithm increased, especially robustness towards the horizontal streaks.

Adaptive decomposition with guided filtering and Laplacian pyramid-based image fusion method for medical applications

Medical image fusion enhances diagnostic precision and facilitates clinical decision-making by integrating information from multiple medical imaging modalities. However, this field is still challenging as the output integrated image, whether from spatial or transform domain algorithms, may suffer from drawbacks such as low contrast, blurring effect, noise, over smoothness, etc. Also, some existing novel works are restricted to specific image datasets. So, to address such issues, a new multi-modal medical image fusion approach based on the advantageous effects of multiple transforms has been introduced in the present work. For this, we use an adaptive image decomposition tool known as Hilbert vibration decomposition (HVD). HVD decomposes an image into different energy components, and after a proper decomposition of the source images, the desirable features of the decomposed components are then passed through a guided filter (GF) for edge preservation. Then, the Laplacian pyramid integrates these filtered parts using the choose max rule. Since HVD offers better spatial resolution and is independent of fixed cut-off frequencies like other transforms, the subjective outputs from this method for different publicly available medical image datasets are clear and better than the previously 20 state-of-the-art published results. Moreover, the obtained values of different objective evaluation metrics such as information entropy (IE): 7.6943, 5.9737, mean: 110.6453, 54.6346, standard deviation (SD): 85.5376, 61.8129, average gradient (AG): 109.2818, 64.6451, spatial frequency (SF): 0.1475, 0.1100, and edge metric (QHK/S): 0.5400, 0.6511 demonstrate its comparability to others. The algorithm's running period of just 0.161244 s also indicates high computational efficiency.

Enhanced low-light image fusion through multi-stage processing with Bayesian analysis and quadratic contrast function

This manuscript introduces an innovative multi-stage image fusion framework that adeptly integrates infrared (IR) and visible (VIS) spectrum images to surmount the difficulties posed by low-light settings. The approach commences with an initial preprocessing stage, utilizing an Efficient Guided Image Filter for the infrared (IR) images to amplify edge boundaries and a function for the visible (VIS) images to boost local contrast and brightness. Utilizing a two-scale decomposition technique that incorporates Lipschitz constraints-based smoothing, the images are effectively divided into distinct base and detail layers, thereby guaranteeing the preservation of essential structural information. The process of fusion is carried out in two distinct stages: firstly, a method grounded in Bayesian theory is employed to effectively combine the base layers, so effectively addressing any inherent uncertainty. Secondly, a Surface from Shade (SfS) method is utilized to ensure the preservation of the scene's geometry by enforcing integrability on the detail layers. Ultimately a Choose Max principle is employed to determine the most prominent textural characteristics, resulting in the amalgamation of the base and detail layers to generate an image that exhibits a substantial enhancement in both clarity and detail. The efficacy of our strategy is substantiated by rigorous testing, showcasing notable progressions in edge preservation, detail enhancement, and noise reduction. Consequently, our method presents significant advantages for real-world applications in image analysis.

Iterative Tomographic Image Reconstruction Algorithm Based on Extended Power Divergence by Dynamic Parameter Tuning.

Computed tomography (CT) imaging plays a crucial role in various medical applications, but noise in projection data can significantly degrade image quality and hinder diagnosis accuracy. Iterative algorithms for tomographic image reconstruction outperform transform methods, especially in scenarios with severe noise in projections. In this paper, we propose a method to dynamically adjust two parameters included in the iterative rules during the reconstruction process. The algorithm, named the parameter-extended expectation-maximization based on power divergence (PXEM), aims to minimize the weighted extended power divergence between the measured and forward projections at each iteration. Our numerical and physical experiments showed that PXEM surpassed conventional methods such as maximum-likelihood expectation-maximization (MLEM), particularly in noisy scenarios. PXEM combines the noise suppression capabilities of power divergence-based expectation-maximization with static parameters at every iteration and the edge preservation properties of MLEM. The experimental results demonstrated significant improvements in image quality in metrics such as the structural similarity index measure and peak signal-to-noise ratio. PXEM improves CT image reconstruction quality under high noise conditions through enhanced optimization techniques.

Deep learning based bilateral filtering for edge-preserving denoising of respiratory-gated PET

BackgroundResidual image noise is substantial in positron emission tomography (PET) and one of the factors limiting lesion detection, quantification, and overall image quality. Thus, improving noise reduction remains of considerable interest. This is especially true for respiratory-gated PET investigations. The only broadly used approach for noise reduction in PET imaging has been the application of low-pass filters, usually Gaussians, which however leads to loss of spatial resolution and increased partial volume effects affecting detectability of small lesions and quantitative data evaluation. The bilateral filter (BF) — a locally adaptive image filter — allows to reduce image noise while preserving well defined object edges but manual optimization of the filter parameters for a given PET scan can be tedious and time-consuming, hampering its clinical use. In this work we have investigated to what extent a suitable deep learning based approach can resolve this issue by training a suitable network with the target of reproducing the results of manually adjusted case-specific bilateral filtering.MethodsAltogether, 69 respiratory-gated clinical PET/CT scans with three different tracers ([18F]\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$[^{18}\ ext {F}]$$\\end{document}FDG, [18F]\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$[^{18}\ ext {F}]$$\\end{document}L-DOPA, [68Ga]\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$[^{68}\ ext {Ga}]$$\\end{document}DOTATATE) were used for the present investigation. Prior to data processing, the gated data sets were split, resulting in a total of 552 single-gate image volumes. For each of these image volumes, four 3D ROIs were delineated: one ROI for image noise assessment and three ROIs for focal uptake (e.g. tumor lesions) measurements at different target/background contrast levels. An automated procedure was used to perform a brute force search of the two-dimensional BF parameter space for each data set to identify the “optimal” filter parameters to generate user-approved ground truth input data consisting of pairs of original and optimally BF filtered images. For reproducing the optimal BF filtering, we employed a modified 3D U-Net CNN incorporating residual learning principle. The network training and evaluation was performed using a 5-fold cross-validation scheme. The influence of filtering on lesion SUV quantification and image noise level was assessed by calculating absolute and fractional differences between the CNN, manual BF, or original (STD) data sets in the previously defined ROIs.ResultsThe automated procedure used for filter parameter determination chose adequate filter parameters for the majority of the data sets with only 19 patient data sets requiring manual tuning. Evaluation of the focal uptake ROIs revealed that CNN as well as BF based filtering essentially maintain the focal SUVmax\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\ ext {SUV}_\ ext {max}$$\\end{document} values of the unfiltered images with a low mean ± SD difference of δSUVmaxCNN,STD\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\delta \ ext {SUV}_\ ext {max}^{\ ext {CNN},\ ext {STD}}$$\\end{document} = (−3.9 ± 5.2)% and δSUVmaxBF,STD\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\delta \ ext {SUV}_\ ext {max}^{\ ext {BF},\ ext {STD}}$$\\end{document} = (−4.4 ± 5.3)%. Regarding relative performance of CNN versus BF, both methods lead to very similar SUVmax\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\ ext {SUV}_\ ext {max}$$\\end{document} values in the vast majority of cases with an overall average difference of δSUVmaxCNN,BF\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\delta \ ext {SUV}_\ ext {max}^{\ ext {CNN},\ ext {BF}}$$\\end{document} = (0.5 ± 4.8)%. Evaluation of the noise properties showed that CNN filtering mostly satisfactorily reproduces the noise level and characteristics of BF with δNoiseCNN,BF\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\delta \ ext {Noise}^{\ ext {CNN},\ ext {BF}}$$\\end{document} = (5.6 ± 10.5)%. No significant tracer dependent differences between CNN and BF were observed.ConclusionsOur results show that a neural network based denoising can reproduce the results of a case by case optimized BF in a fully automated way. Apart from rare cases it led to images of practically identical quality regarding noise level, edge preservation, and signal recovery. We believe such a network might proof especially useful in the context of improved motion correction of respiratory-gated PET studies but could also help to establish BF-equivalent edge-preserving CNN filtering in clinical PET since it obviates time consuming manual BF parameter tuning.

Unsupervised speckle noise reduction technique for clinical ultrasound imaging.

Deep learning-based image enhancement has significant potential in the field of ultrasound image processing, as it can accurately model complicated nonlinear artifacts and noise, such as ultrasonic speckle patterns. However, training deep learning networks to acquire reference images that are clean and free of noise presents significant challenges. This study introduces an unsupervised deep learning framework, termed speckle-to-speckle (S2S), designed for speckle and noise suppression. This framework can complete its training without the need for clean (speckle-free) reference images. The proposed network leverages statistical reasoning for the mutual training of two in vivo images, each with distinct speckle patterns and noise. It then infers speckle- and noise-free images without needing clean reference images. This approach significantly reduces the time, cost, and effort experts need to invest in annotating reference images manually. The experimental results demonstrated that the proposed approach outperformed existing techniques in terms of the signal-to-noise ratio, contrast-to-noise ratio, structural similarity index, edge preservation index, and processing time (up to 86 times faster). It also performed excellently on images obtained from ultrasound scanners other than the ones used in this work. S2S demonstrates the potential of employing an unsupervised learning-based technique in medical imaging applications, where acquiring a ground truth reference is challenging.

Contextual based hybrid classification with FCM to handle mixed pixels and edge preservation

Contextual based hybrid classification with FCM to handle mixed pixels and edge preservation

Real-GDSR: Real-World Guided DSM Super-Resolution via Edge-Enhancing Residual Network

Abstract. A low-resolution digital surface model (DSM) features distinctive attributes impacted by noise, sensor limitations and data acquisition conditions, which failed to be replicated using simple interpolation methods like bicubic. This causes super-resolution models trained on synthetic data does not perform effectively on real ones. Training a model on real low and high resolution DSMs pairs is also a challenge because of the lack of information. On the other hand, the existence of other imaging modalities of the same scene can be used to enrich the information needed for large-scale super-resolution. In this work, we introduce a novel methodology to address the intricacies of real-world DSM super-resolution, named REAL-GDSR, breaking down this ill-posed problem into two steps. The first step involves the utilization of a residual local refinement network. This strategic approach departs from conventional methods that trained to directly predict height values instead of the differences (residuals) and utilize large receptive fields in their networks. The second step introduces a diffusion-based technique that enhances the results on a global scale, with a primary focus on smoothing and edge preservation. Our experiments underscore the effectiveness of the proposed method. We conduct a comprehensive evaluation, comparing it to recent state-of-the-art techniques in the domain of real-world DSM super-resolution (SR). Our approach consistently outperforms these existing methods, as evidenced through qualitative and quantitative assessments.

Enhancing clinical diagnostics: novel denoising methodology for brain MRI with adaptive masking and modified non-local block.

Medical image denoising has been a subject of extensive research, with various techniques employed to enhance image quality and facilitate more accurate diagnostics. The evolution of denoising methods has highlighted impressive results but struggled to strike equilibrium between noise reduction and edge preservation which limits its applicability in various domains. This paper manifests the novel methodology that integrates an adaptive masking strategy, transformer-based U-Net Prior generator, edge enhancement module, and modified non-local block (MNLB) for denoising brain MRI clinical images. The adaptive masking strategy maintains the vital information through dynamic mask generation while the prior generator by capturing hierarchical features regenerates the high-quality prior MRI images. Finally, these images are fed to the edge enhancement module to boost structural information by maintaining crucial edge details, and the MNLB produces the denoised output by deriving non-local contextual information. The comprehensive experimental assessment is performed by employing two datasets namely the brain tumor MRI dataset and Alzheimer's dataset for diverse metrics and compared with conventional denoising approaches. The proposed denoising methodology achieves a PSNR of 40.965 and SSIM of 0.938 on the Alzheimer's dataset and also achieves a PSNR of 40.002 and SSIM of 0.926 on the brain tumor MRI dataset at a noise level of 50% revealing its supremacy in noise minimization. Furthermore, the impact of different masking ratios on denoising performance is analyzed which reveals that the proposed method showed PSNR of 40.965, SSIM of 0.938, MAE of 5.847, and MSE of 3.672 at the masking ratio of 60%. Moreover, the findings pave the way for the advancement of clinical image processing, facilitating precise detection of tumors in clinical MRI images.

Best proximity points for generalized (F, R)-proximal contractions

We present the notion of generalized (F, R)-proximal non-self contractions and prove best proximity point theorems in complete metric spaces endowed with an arbitrary binary relation. An example is given to vindicate our claims. We also show that the edge preserving structure is a particular case of the binary relation R. Moreover, an application to variational inequality problem is given in order to demonstrate the efficacy of our results.

Edge preserving infrared and visible image fusion with three layer decomposition based on multi-level co-occurrence filtering

By merging different portraits of a particular scene, image fusion attempts to create a blended image that combines details from all the images. Infrared (IR) and visible image fusion can be accomplished in a variety of ways, including recent deep-learning-based techniques. However, edge-preserving filter (EPF) based fusion works well since it retains all the information from both images. Local filtering-based techniques, on the other hand, limit the fusion performance by introducing multiple gradient reversal artifacts and halos. This work presents an advanced IR and visible image fusion approach depending on three-level decomposition using multi-level co-occurrence filtering, which aims to overcome the common shortfalls such as halo effects seen in existing EPF based fusion. The reference images are decomposed in to base layer, small-scale layers and large-scale layers using multi-level co-occurrence filtering (MLCoF). Since most of the low frequency details are contained in the base layer, the conventional merging strategy by averaging is replaced with novel foreground information map (FIM) based fusion strategy. Small-scale layers are combined by applying max-absolute fusion strategy. A novel weight-map guided edge preserving fusion strategy is put forward for the integration of large-scale layers. Later, fused image is generated by the superposition of these different layers. Subjective visual and objective quantitative analysis shows that the suggested technique attains more notable performance in contrast with other modern fusion methods including many deep-learning techniques. In terms of visual perspective view, the results produced by the proposed approach are superior and include all details from both images. Additionally, it produces outcomes free of gradient reversal and halo artifacts.

Color Image Compression Using Wavelet Compression and Zero-MeanCoding

Thousands pictures require a very large amount of storage. So differenttechniques of digital image compression is used to reduce the storage requirementsfor these images. In this paper an adaptive compression method applied on colorimage. Firstly the color image is transformed to the RGB system, and then convertsthe color data to a luminance/chrominance color space (YIQ).The adaptivecompression method is applied on Y. The image may contain a uniform region andedge region; the uniform regions compress depending on zero-mean coding and theedge region compress depending on Daubechies wavelet transform, then returnedthe final image to RGB system. The proposed algorithms has many advantageswhich make it very efficient, these are, low bit rate, low computational complexity,fast processing and edge preservation with good reconstructed image quality.

Evaluation of low-dose computed tomography reconstruction using spatial-radon domain total generalized variation regularization

The x-ray radiation dose in computed tomography (CT) examination has been a major concern for patients. Lowing the tube current and exposure time in data acquisition is a straightforward and cost-effective strategy to reduce the x-ray radiation dose. However, this will inevitably increase the noise fluctuations in measured projection data, and the corresponding CT image quality will be severely degraded if noise suppression is not performed during image reconstruction. To reconstruct high-quality low-dose CT image, we present a spatial-radon domain total generalized variation (SRDTGV) regularization for statistical iterative reconstruction based on penalized weighted least-squares (PWLS) principle, which is called PWLS-SRDTGV for simplicity. The presented PWLS-SRDTGV model can simultaneously reconstruct high-quality CT image in space domain and its corresponding projection in radon domain. An efficient split Bregman algorithm was applied to minimize the cost function of the proposed reconstruction model. Qualitative and quantitative studies were performed to evaluate the effectiveness of the PWLS-SRDTGV image reconstruction algorithm using a digital 3D XCAT phantom and an anthropomorphic torso phantom. The experimental results demonstrate that PWLS-SRDTGV algorithm achieves notable gains in noise reduction, streak artifact suppression, and edge preservation compared with competing reconstruction approaches.

A novel improved total variation algorithm for the elimination of scratch-type defects in high-voltage cable cross-sections.

In the quality inspection process of high-voltage cables, several commonly used indicators include cable length, insulation thickness, and the number of conductors within the core. Among these factors, the count of conductors holds particular significance as a key determinant of cable quality. Machine vision technology has found extensive application in automatically detecting the number of conductors in cross-sectional images of high-voltage cables. However, the presence of scratch-type defects in cut high-voltage cable cross-sections can significantly compromise the precision of conductor count detection. To address this problem, this paper introduces a novel improved total variation (TV) algorithm, marking the first-ever application of the TV algorithm in this domain. Considering the staircase effect, the direct use of the TV algorithm is prone to cause serious loss of image edge information. The proposed algorithm firstly introduces multimodal features to effectively mitigate the staircase effect. While eliminating scratch-type defects, the algorithm endeavors to preserve the original image's edge information, consequently yielding a noteworthy enhancement in detection accuracy. Furthermore, a dataset was curated, comprising images of cross-sections of high-voltage cables of varying sizes, each displaying an assortment of scratch-type defects. Experimental findings conclusively demonstrate the algorithm's exceptional efficiency in eradicating diverse scratch-type defects within high-voltage cable cross-sections. The average scratch elimination rate surpasses 90%, with an impressive 96.15% achieved on cable sample 4. A series of conducted ablation experiments in this paper substantiate a significant enhancement in cable image quality. Notably, the Edge Preservation Index (EPI) exhibits an improvement of approximately 20%, resulting in a substantial boost to conductor count detection accuracy, thus effectively enhancing the quality of high-voltage cable production.

An Adaptive Semantic Segmentation Network for Adversarial Learning Domain Based on Low-Light Enhancement and Decoupled Generation

Nighttime semantic segmentation due to issues such as low contrast, fuzzy imaging, and low-quality annotation results in significant degradation of masks. In this paper, we introduce a domain adaptive approach for nighttime semantic segmentation that overcomes the reliance on low-light image annotations to transfer the source domain model to the target domain. On the front end, a low-light image enhancement sub-network combining lightweight deep learning with mapping curve iteration is adopted to enhance nighttime foreground contrast. In the segmentation network, the body generation and edge preservation branches are implemented to generate consistent representations within the same semantic region. Additionally, a pixel weighting strategy is embedded to increase the prediction accuracy for small targets. During the training, a discriminator is implemented to distinguish features between the source and target domains, thereby guiding the segmentation network for adversarial transfer learning. The proposed approach’s effectiveness is verified through testing on Dark Zurich, Nighttime Driving, and CityScapes, including evaluations of mIoU, PSNR, and SSIM. They confirm that our approach surpasses existing baselines in segmentation scenarios.

Digital IIR filters: Effective in edge preservation?

Infinite Impulse Response (IIR) filtering stands as a fundamental technique in various signal processing applications. Despite its widespread use, the scientific community widely acknowledges the suboptimal nature of IIR filters in preserving edges or abrupt transitions in piecewise signals. In situations where meticulous preservation of abrupt signal transitions is crucial, signal processing practitioners often explore alternative methodologies tailored to specific application demands. Consequently, the effectiveness of digital IIR filters in preserving signal edges while filtering out undesirable noise components continues to be a topic of active debate.In response to this limitation (or answering the question posed by the above title), the paper demonstrates that the suboptimal nature of IIR filters in preserving edges arises from the conventional methodology used to compute the output of zero-phase IIR filters. The standard method of output computation equates to solving an unconstrained optimization problem with an ℓ2-norm penalty term. Following this analysis, the paper introduces a refined approach to compute the output of digital IIR filters, aiming to overcome the challenge of preserving abrupt signal transitions. This innovative proposal replaces the ℓ2-norm with an ℓ1-norm, resulting in the development of an IIR filter that dynamically adjusts its coefficients based on the input signal. As a result, this novel approach to output computation effectively preserves essential signal features while simultaneously reducing noise, highlighting the efficacy of digital IIR filters in edge preservation. Therefore, the answer to the aforementioned question greatly depends on the chosen method for computing the output. By employing the suggested approach, the answer is unequivocally yes.