Showing papers on "Edge enhancement published in 2021"

Efficient Transformer for Remote Sensing Image Segmentation

Abstract: Semantic segmentation for remote sensing images (RSIs) is widely applied in geological surveys, urban resources management, and disaster monitoring. Recent solutions on remote sensing segmentation tasks are generally addressed by CNN-based models and transformer-based models. In particular, transformer-based architecture generally struggles with two main problems: a high computation load and inaccurate edge classification. Therefore, to overcome these problems, we propose a novel transformer model to realize lightweight edge classification. First, based on a Swin transformer backbone, a pure Efficient transformer with mlphead is proposed to accelerate the inference speed. Moreover, explicit and implicit edge enhancement methods are proposed to cope with object edge problems. The experimental results evaluated on the Potsdam and Vaihingen datasets present that the proposed approach significantly improved the final accuracy, achieving a trade-off between computational complexity (Flops) and accuracy (Efficient-L obtaining 3.23% mIoU improvement on Vaihingen and 2.46% mIoU improvement on Potsdam compared with HRCNet_W48). As a result, it is believed that the proposed Efficient transformer will have an advantage in dealing with remote sensing image segmentation problems.

Edge detection of potential field sources using the softsign function

Abstract: Edge enhancement techniques have been widely used in mapping geologic features, such as faults, contacts and dikes The universal disadvantages of previously presented filters are that they cannot

Unsharp Mask Guided Filtering

Abstract: The goal of this paper is guided image filtering, which emphasizes the importance of structure transfer during filtering by means of an additional guidance image. Where classical guided filters transfer structures using hand-designed functions, recent guided filters have been considerably advanced through parametric learning of deep networks. The state-of-the-art leverages deep networks to estimate the two core coefficients of the guided filter. In this work, we posit that simultaneously estimating both coefficients is suboptimal, resulting in halo artifacts and structure inconsistencies. Inspired by unsharp masking, a classical technique for edge enhancement that requires only a single coefficient, we propose a new and simplified formulation of the guided filter. Our formulation enjoys a filtering prior from a low-pass filter and enables explicit structure transfer by estimating a single coefficient. Based on our proposed formulation, we introduce a successive guided filtering network, which provides multiple filtering results from a single network, allowing for a trade-off between accuracy and efficiency. Extensive ablations, comparisons and analysis show the effectiveness and efficiency of our formulation and network, resulting in state-of-the-art results across filtering tasks like upsampling, denoising, and cross-modality filtering. Code is available at https://github.com/shizenglin/Unsharp-Mask-Guided-Filtering .

Pixel-Level Non-local Image Smoothing With Objective Evaluation

Abstract: Recently, imagesmoothing has gained increasing attention due to its prerequisite role in other image processing tasks, e.g., image enhancement and editing. However, the evaluation of image smoothing algorithms is usually performed by subjective observation on images without corresponding ground truths. To promote the development of image smoothing algorithms, in this paper, we construct a novel Nankai Smoothing (NKS) dataset containing 200 images blended by versatile structure images and natural textures. The structure images are inherently smooth and naturally taken as ground truths. On our NKS dataset, we comprehensively evaluate 14 popular image smoothing algorithms. Moreover, we propose a Pixel-level Non-Local Smoothing (PNLS) method to well preserve the structure of the smoothed images, by exploiting the pixel-level non-local self-similarity prior of natural images. Extensive experiments on several benchmark datasets demonstrate that our PNLS outperforms previous algorithms on the image smoothing task. Ablation studies also reveal the work mechanism of our PNLS on image smoothing. To further show its effectiveness, we apply our PNLS on several applications such as semantic region smoothing, detail/edge enhancement, and image abstraction. The dataset and code are available at https://github.com/zal0302/PNLS .

Regions Preserving Edge Enhancement for Multisensor-Based Medical Image Fusion

Abstract: Multimodal medical image fusion technology has been widely used in various applications of clinical diagnosis, which aims to provide richer information by integrating effective features of multiple medical images. In this article, a novel fusion scheme based on region-preserving edge enhancement is proposed for medical images. The overlapping regions of source images that need to be fused are detected first. Next, according to the different visual features, the overlapping map is divided by Fuzzy c-means (FCM)-based algorithm. Then, different fusion strategies based on visual saliency and texture details are proposed for region-preserving and edge enhancement. Experimental results show that the proposed scheme can effectively highlight the visual features and retain key information. Furthermore, the performance of different medical images also demonstrates that the proposed method can obtain better results than those achieved by some of the state-of-the-art methods.

Multichannel Object Detection for Detecting Suspected Trees With Pine Wilt Disease Using Multispectral Drone Imagery

Abstract: In this article, a multichannel convolutional neural network (CNN) based object detection was used to detect suspected trees of pine wilt disease after acquiring aerial photographs through a rotorcraft drone equipped with a multispectral camera. The acquired multispectral aerial photographs consist of RGB, green, red, NIR, and red edge spectral bands per shooting point. The aerial photographs for each band performed image calibration to correct radiation distortion, image alignment to correct the distance error of the lenses of a multispectral camera, and image enhancement to edge enhancement to highlight the features of objects in the image. After that, a large amount of data obtained through data augmentation were put into multichannel CNN-based object detection for training and test. As a result of verifying the detection performance of the trained model, excellent detection results were obtained with mAP 86.63% and average intersection over union 71.47%.

Unsharp Mask Guided Filtering

Abstract: The goal of this paper is guided image filtering, which emphasizes the importance of structure transfer during filtering by means of an additional guidance image. Where classical guided filters transfer structures using hand-designed functions, recent guided filters have been considerably advanced through parametric learning of deep networks. The state-of-the-art leverages deep networks to estimate the two core coefficients of the guided filter. In this work, we posit that simultaneously estimating both coefficients is suboptimal, resulting in halo artifacts and structure inconsistencies. Inspired by unsharp masking, a classical technique for edge enhancement that requires only a single coefficient, we propose a new and simplified formulation of the guided filter. Our formulation enjoys a filtering prior from a low-pass filter and enables explicit structure transfer by estimating a single coefficient. Based on our proposed formulation, we introduce a successive guided filtering network, which provides multiple filtering results from a single network, allowing for a trade-off between accuracy and efficiency. Extensive ablations, comparisons and analysis show the effectiveness and efficiency of our formulation and network, resulting in state-of-the-art results across filtering tasks like upsampling, denoising, and cross-modality filtering. Code is available at \url{this https URL}.

Multi-Laplacian GAN with Edge Enhancement for Face Super Resolution

Abstract: Face image super-resolution has become a research hotspot in the field of image processing. Nowadays, more and more researches add additional information, such as landmark, identity, to reconstruct high resolution images from low resolution ones, and have a good performance in quantitative terms and perceptual quality. However, these additional information is hard to obtain in many cases. In this work, we focus on reconstructing face images by extracting useful information from face images directly rather than using additional information. By observing edge information in each scale of face images, we propose a method to reconstruct high resolution face images with enhanced edge information. In additional, with the proposed training procedure, our method reconstructs photo-realistic images in upscaling factor 8× and outperforms state-of-the-art methods both in quantitative terms and perceptual quality.

Edge and Contrast Enhancement Using Spatially Incoherent Correlation Holography Techniques

Abstract: Image enhancement techniques (such as edge and contrast enhancement) are essential for many imaging applications. In incoherent holography techniques such as Fresnel incoherent correlation holography (FINCH), the light from an object is split into two, each of which is modulated differently from one another by two different quadratic phase functions and coherently interfered to generate the hologram. The hologram can be reconstructed via a numerical backpropagation. The edge enhancement procedure in FINCH requires the modulation of one of the beams by a spiral phase element and, upon reconstruction, edge-enhanced images are obtained. An optical technique for edge enhancement in coded aperture imaging (CAI) techniques that does not involve two-beam interference has not been established yet. In this study, we propose and demonstrate an iterative algorithm that can yield from the experimentally recorded point spread function (PSF), a synthetic PSF that can generate edge-enhanced reconstructions when processed with the object hologram. The edge-enhanced reconstructions are subtracted from the original reconstructions to obtain contrast enhancement. The technique has been demonstrated on FINCH and CAI methods with different spectral conditions.

Normalized vertical derivatives in the edge enhancement of maximum-edge-recognition methods in potential fields

Abstract: Gravity and magnetic data have unique advantages for studying the lateral extents of geologic bodies There is a class of methods for edge recognition called maximum-edge-recognition method

Video Super-Resolution Based on Generative Adversarial Network and Edge Enhancement

Abstract: With the help of deep neural networks, video super-resolution (VSR) has made a huge breakthrough. However, these deep learning-based methods are rarely used in specific situations. In addition, training sets may not be suitable because many methods only assume that under ideal circumstances, low-resolution (LR) datasets are downgraded from high-resolution (HR) datasets in a fixed manner. In this paper, we proposed a model based on Generative Adversarial Network (GAN) and edge enhancement to perform super-resolution (SR) reconstruction for LR and blur videos, such as closed-circuit television (CCTV). The adversarial loss allows discriminators to be trained to distinguish between SR frames and ground truth (GT) frames, which is helpful to produce realistic and highly detailed results. The edge enhancement function uses the Laplacian edge module to perform edge enhancement on the intermediate result, which helps further improve the final results. In addition, we add the perceptual loss to the loss function to obtain a higher visual experience. At the same time, we also tried training network on different datasets. A large number of experiments show that our method has advantages in the Vid4 dataset and other LR videos.

3D reconstruction of weakly scattering objects from 2D intensity-only measurements using the Wolf transform.

Abstract: A new approach to optical diffraction tomography (ODT) based on intensity measurements is presented. By applying the Wolf transform directly to intensity measurements, we observed unexpected behavior in the 3D reconstruction of the sample. Such a reconstruction does not explicitly represent a quantitative measure of the refractive index of the sample; however, it contains interesting qualitative information. This 3D reconstruction exhibits edge enhancement and contrast enhancement for nanostructures compared with the conventional 3D refractive index reconstruction and thus could be used to localize nanoparticles such as lipids inside a biological sample.

An Advanced Noise Reduction and Edge Enhancement Algorithm.

Abstract: Complementary metal-oxide-semiconductor (CMOS) image sensors can cause noise in images collected or transmitted in unfavorable environments, especially low-illumination scenarios. Numerous approaches have been developed to solve the problem of image noise removal. However, producing natural and high-quality denoised images remains a crucial challenge. To meet this challenge, we introduce a novel approach for image denoising with the following three main contributions. First, we devise a deep image prior-based module that can produce a noise-reduced image as well as a contrast-enhanced denoised one from a noisy input image. Second, the produced images are passed through a proposed image fusion (IF) module based on Laplacian pyramid decomposition to combine them and prevent noise amplification and color shift. Finally, we introduce a progressive refinement (PR) module, which adopts the summed-area tables to take advantage of spatially correlated information for edge and image quality enhancement. Qualitative and quantitative evaluations demonstrate the efficiency, superiority, and robustness of our proposed method.

A Comparative Study of Various Filtering Techniques

Abstract: Image processing is a fast growing area of active research. It comprises methods to perform several useful operations on images, to modify/enhance the image or to tease out useful information from it. A very basic application of image processing is image filtering. Filtering is a technique of image modification or enhancement. We filter an image to enhance some features or to get rid of other features - the techniques include smoothing, sharpening, edge enhancement. Here we apply different smoothing and edge enhancement filtering methods to an image and evaluate the quality of the image in both cases using an image quality assessment technique called BRISQUE and by calculating the PSNR ratio of images.

Tunable edge enhancement by higher-order spiral Fresnel incoherent correlation holography system

Abstract: Tunable edge enhancement can selectively emphasize the edge features of objects. We demonstrate a higher-order spiral Fresnel incoherent correlation holography system to realize isotropic edge enhancement with tunable width. The spatial light modulator is space-division multiplexed by a conventional lens and a spiral lens with a series of higher-order Laguerre–Gaussian phases. The effects of the radial quantum number p and the angular quantum number l on the spatial filtering are theoretically discussed, as well as confirmed by simulations and experiments. Reconstruction images of resolution target, hairs and label-free onion cells all show obvious tunable edge enhancement effects, which makes the edge information easier to be identified. Furthermore, double-edge enhancement is also detected for the first time.

Isotropic and anisotropic edge enhancement with a superposed-spiral phase filter

Abstract: In this paper, we present edge detection schemes with specially designed superposed spiral phase plate (SSPP) filters in the Fourier domain both for intensity or phase objects. A special SSPP whose function is equivalent to Sobel operator in space domain is firstly designed by weighting different topological charge spiral phase plate (SPP) filters. Later, a SSPP with controllable direction parameters is then discussed to enhance the anisotropic edges by controlling the direction parameter. Numerical simulation and experimental results show that either isotropic or anisotropic edge information can be enhanced by using our proposed schemes. The signal-to-noise ratio and the root-mean-square-error performance are improved in comparison with those using traditional SPP filter. Importantly, it is the first time to present the special ways of superposing and the SSPP can be designed before the experiment so that a clear edge can be achieved at real time without the convolutional operation.

Mathematical Modeling for Ceramic Shape 3D Image Based on Deep Learning Algorithm

Abstract: Ceramic image shape 3D image modeling focuses on of ceramic that was obtained from the camera imaging equipment such as 2D images, by normalization, gray, filtering denoising, wavelet image sharpening edge enhancement, binarization, and shape contour extraction pretreatment processes such as extraction ceramic image shape edge profile, again, according to the image edge extraction and elliptic rotator ceramics phenomenon. The image distortion effect was optimized by self-application, and then the deep learning modeler was used to model the side edge contour. Finally, the 3D ceramic model of the rotating body was restored according to the intersection and central axis of the extracted contour. By studying the existing segmentation methods based on deep learning, the automatic segmentation of target ceramic image and the effect of target edge refinement and optimization are realized. After extracting and separating the target ceramics from the image, we processed the foreground image of the target into a three-dimensional model. In order to reduce the complexity of the model, a 3D contextual sequencing model is adopted to encode the hidden space features along the channel dimensions, to extract the causal correlation between channels. Each module in the compression framework is optimized by a rate-distortion loss function. The experimental results show that the proposed 3D image modeling method has significant advantages in compression performance compared with the optimal 2D 3D image modeling method based on deep learning, and the experimental results show that the performance of the proposed method is superior to JP3D and HEVC methods, especially at low bit rate points.

Eformer: Edge Enhancement based Transformer for Medical Image Denoising.

Abstract: In this work, we present Eformer - Edge enhancement based transformer, a novel architecture that builds an encoder-decoder network using transformer blocks for medical image denoising. Non-overlapping window-based self-attention is used in the transformer block that reduces computational requirements. This work further incorporates learnable Sobel-Feldman operators to enhance edges in the image and propose an effective way to concatenate them in the intermediate layers of our architecture. The experimental analysis is conducted by comparing deterministic learning and residual learning for the task of medical image denoising. To defend the effectiveness of our approach, our model is evaluated on the AAPM-Mayo Clinic Low-Dose CT Grand Challenge Dataset and achieves state-of-the-art performance, $i.e.$, 43.487 PSNR, 0.0067 RMSE, and 0.9861 SSIM. We believe that our work will encourage more research in transformer-based architectures for medical image denoising using residual learning.