Preserve Edge Information Research Articles

Image interpolation with spiking neural network based pixel similarity

Image interpolation is an important topic in the field of image processing. It is defined as the process of transforming low-resolution images into high-resolution ones using image processing methods. Recent studies on interpolation have shown that researchers are focusing on successful interpolation techniques that preserve edge information. Therefore, the edge detection phase plays a vital role in interpolation studies. However, these approaches typically rely on gradient-based linear computations for edge detection. On the other hand, non-linear structures that effectively simulate the human visual system have gained attention. In this study, a non-linear method was developed to detect edge information using a pixel similarity approach. Pixel similarity-based edge detection approach offers both lower computational complexity and more successful interpolation results compared to gradient-based approaches. 1D cubic interpolation was applied to the pixels identified as edges based on pixel similarity, while bicubic interpolation was applied to the remaining pixels. The algorithm was tested on 12 commonly used images and compared with various interpolation techniques. The results were evaluated using metrics such as SSIM and PSNR, as well as visual assessment. The experimental findings clearly demonstrated that the proposed method outperformed other approaches. Additionally, the method offers significant advantages, such as not requiring any parameters and having competitive computational cost.

Dynamic Downsampling Algorithm for 3D Point Cloud Map Based on Voxel Filtering

In response to the challenge of handling large-scale 3D point cloud data, downsampling is a common approach, yet it often leads to the problem of feature loss. We present a dynamic downsampling algorithm for 3D point cloud maps based on an improved voxel filtering approach. The algorithm consists of two modules, namely, dynamic downsampling and point cloud edge extraction. The former adapts voxel downsampling according to the features of the point cloud, while the latter preserves edge information within the 3D point cloud map. Comparative experiments with voxel downsampling, grid downsampling, clustering-based downsampling, random downsampling, uniform downsampling, and farthest-point downsampling were conducted. The proposed algorithm exhibited favorable downsampling simplification results, with a processing time of 0.01289 s and a simplification rate of 91.89%. Additionally, it demonstrated faster downsampling speed and showcased improved overall performance. This enhancement not only benefits productivity but also highlights the system’s efficiency and effectiveness.

Detection and Removal of Assymmetrical Skin Lesions Using DU-Net for Patch Extraction

The incidence of melanoma, a highly fatal kind of malignant tumor, is exhibiting an upward trend in its progression. Timely intervention and management of skin cancer significantly enhance the likelihood of survival. Analyzing dermoscopic images poses challenges for dermatologists due to various distracting factors, including fluctuations in lighting and reflections on the skin's surface. Accurately delineating the area of skin pathology is crucial for diagnosing the specific skin condition. This study introduces DU-net, a method for identifying and removing pigmented skin lesions. The DU-net framework incorporates deep convolutional neural networks, notably YOLOv5, to perform patch detection. It also employs asymmetrical patch contouring methods to preserve edge information. Additionally, clustering algorithms are utilized to identify pixel groups and extract patches from the image. The De Trop Noise Exclusion technique, in conjunction with the process of in-painting, is employed to successfully eliminate hair from the images within the ISIC-2018 and 2019 datasets. Rigorous annotation of skin images with lesions of various sizes and shapes using rectangle bounding is carried out, and YOLOv5 hyper-parameters are fine-tuned to achieve high-confidence multiple lesion detection in dermoscopic images. Despite complex textures and unclear boundaries, our approach consistently detects and labels patches, accurately segmenting the areas of skin pathology. The model's performance is assessed on these datasets using various parameter metrics, the results of the study indicate that the segmentation strategies described in this research exhibit an average accuracy ranging from about 92% to 94%.

ReeGAN: MRI image edge-preserving synthesis based on GANs trained with misaligned data.

As a crucial medical examination technique, different modalities of magnetic resonance imaging (MRI) complement each other, offering multi-angle and multi-dimensional insights into the body's internal information. Therefore, research on MRI cross-modality conversion is of great significance, and many innovative techniques have been explored. However, most methods are trained on well-aligned data, and the impact of misaligned data has not received sufficient attention. Additionally, many methods focus on transforming the entire image and ignore crucial edge information. To address these challenges, we propose a generative adversarial network based on multi-feature fusion, which effectively preserves edge information while training on noisy data. Notably, we consider images with limited range random transformations as noisy labels and use an additional small auxiliary registration network to help the generator adapt to the noise distribution. Moreover, we inject auxiliary edge information to improve the quality of synthesized target modality images. Our goal is to find the best solution for cross-modality conversion. Comprehensive experiments and ablation studies demonstrate the effectiveness of the proposed method.

Research on a multi-dimensional image information fusion algorithm based on NSCT transform

Traditional inspection cameras determine targets and detect defects by capturing images of their light intensity, but in complex environments, the accuracy of inspection may decrease. Information based on polarization of light can characterize various features of a material, such as the roughness, texture, and refractive index, thus improving classification and recognition of targets. This paper uses a method based on noise template threshold matching to denoise and preprocess polarized images. It also reports on design of an image fusion algorithm, based on NSCT transform, to fuse light intensity images and polarized images. The results show that the fused image improves both subjective and objective evaluation indicators, relative to the source image, and can better preserve edge information and help to improve the accuracy of target recognition. This study provides a reference for the comprehensive application of multi-dimensional optical information in power inspection.Graphical

RepDNet: A re-parameterization despeckling network for autonomous underwater side-scan sonar imaging with prior-knowledge customized convolution

Side-scan sonar (SSS) is now a prevalent instrument for large-scale seafloor topography measurements, deployable on an autonomous underwater vehicle (AUV) to execute fully automated underwater acoustic scanning imaging along a predetermined trajectory. However, SSS images often suffer from speckle noise caused by mutual interference between echoes, and limited AUV computational resources further hinder noise suppression. Existing approaches for SSS image processing and speckle noise reduction rely heavily on complex network structures and fail to combine the benefits of deep learning and domain knowledge. To address the problem, RepDNet, a novel and effective despeckling convolutional neural network is proposed. RepDNet introduces two re-parameterized blocks: the Pixel Smoothing Block (PSB) and Edge Enhancement Block (EEB), preserving edge information while attenuating speckle noise. During training, PSB and EEB manifest as double-layered multi-branch structures, integrating first-order and second-order derivatives and smoothing functions. During inference, the branches are re-parameterized into a 3 × 3 convolution, enabling efficient inference without sacrificing accuracy. RepDNet comprises three computational operations: 3 × 3 convolution, element-wise summation and Rectified Linear Unit activation. Evaluations on benchmark datasets, a real SSS dataset and Data collected at Lake Mulan aestablish RepDNet as a well-balanced network, meeting the AUV computational constraints in terms of performance and latency.

Infrared-visible image fusion method based on multi-scale shearing Co-occurrence filter

Infrared-visible image fusion aims to achieve salient targets and abundant texture details. However, most of fusion methods based on multi-scale decomposition fail to effectively preserve detailed and texture information. To avoid these issues, a novel fusion method is proposed by means of multi-scale shearing Co-occurrence filter (MSCOF). This multi-scale decomposition tool possesses the flexible multi-direction and shift-invariant properties of the Shearlet, as well as the smoothing advantages of the Co-occurrence filter (COF). In this study, we obtain approximate and detail subbands by performing MSCOF decomposition on the original images. A weighted fusion rule based on the saliency intensity value (SIV) is performed to combine approximate subbands. Notably, COF is employed on the saliency intensity maps to better preserve edge information of the original image on the fused approximate subbands. Meanwhile, the improved local gradient energy (ILGE) method is utilized to fuse the detail subbands. The results of experimental analysis fully prove that our method is reliable and feasible, and that the obtained objective evaluation metrics are superior to those of some typical methods.

Robust multi-scale weighting-based edge-smoothing filter for single image dehazing

The guided image filter (GIF) and weighted guided image filter (WGIF) are local linear model-based good edge-preserving filters. However, due to fixed regularization parameter, they suffer from halo artifacts (morphological artifacts) in the sharp regions. To overcome this issue, a robust multi-scale weighting-based edge-smoothing filter (RMWEF) for single image dehazing is proposed in this paper. It removes morphological artifacts and over-smoothness strongly and preserves edge information precisely in both flat and sharp regions. The proposed dehaze method has four-steps. First, initial transmission map and atmospheric map are estimated by using a novel dark channel prior (DCP) method. Then, the morphological artifacts of initial transmission map are reduced by using non-local haze line averaging (NL-HLA) method. In the third step, transmission map is refined by using the proposed RMWEF. Finally, the haze free image is restored. Theoretical and experimental analysis proves that the proposed algorithm produce effective dehaze results quicker than the existing methods.

ViT-DexiNet: a vision transformer-based edge detection operator for small object detection in SAR images

ABSTRACTThis paper introduces a novel edge detection operator called ‘vision transformer-based Dexinet (ViT-DexiNet)’ to address the challenges of detecting small objects in synthetic aperture radar (SAR) images. SAR images are typically impacted by strong multiplicative noise, making edge detection difficult. Existing traditional methods have limited spectral data preservation capabilities and often result in a loss of clarity and integrity of salient features in SAR images. The proposed ViT-DexiNet operator employs a series of interconnected layers to extract and refine salient edge features from SAR images. It utilizes a vision transformer self-attention layer to capture the pattern and structural details of image features crucial for determining edges. The extracted feature maps are then processed by the DexiNet architecture, which consists of a dense block, transfer block, and upsampling network. This architecture helps preserve edge information at different scales in deeper layers. The series of layered blocks generate edge maps, which are concatenated and averaged through smoothing to remove noise and enhance edge details in SAR images, resulting in a final high-quality edge map. To evaluate the proposed ViT-DexiNet method, both qualitative and quantitative analyses are conducted using standard edge detection operators such as Canny and Sobel. The empirical results demonstrate that the ViT-DexiNet surpasses baseline edge detection operators. The achieved values of proposed edge detection operator are 97.92%, 97.72%, 97.64% and 97.41%, respectively for the metrics accuracy, precision, recall and f1-score. The ViT-DexiNet offers high-quality edge maps, simplifying the interpretation of data for small object detection. Overall, the ViT-DexiNet method shows promise in overcoming the limitations of traditional approaches and improving the detection of edges in SAR images.

Difference-guided multiscale graph convolution network for unsupervised change detection in PolSAR images

Image change detection is important in polarimetric synthetic aperture radar (PolSAR) image analysis and interpretation. However, improving its accuracy is challenging because of the interference of multiplicative speckle noise. To address this issue, we propose an unsupervised PolSAR image change detection method based on a multiscale graph convolutional network (GCN). First, a Shannon entropy difference image is introduced and improved to obtain an enhanced difference image (EDI) that can effectively suppress speckle noise while preserving edge information. The generated EDI can be further utilised to construct a pseudo-label set required for unsupervised change detection. Subsequently, a difference constraint joint graph construction (DCJGC) module is proposed to obtain the object-level input information of the network. This uses the joint superpixels of multitemporal PolSAR images as graph nodes, and then introduces the difference information in the EDI to constrain the formation process of the edges between the nodes, efficiently and accurately constructing undirected graphs. Finally, a difference-guided multiscale GCN (DGMGCN) is designed for PolSAR image change detection. The network utilises difference information to eliminate the adverse effect of speckle noise on change detection and fully capture the change-aware features of multitemporal PolSAR images at fine and coarse scales, thereby improving feature discriminability. Experimental results on six real Gaofen-3 PolSAR datasets validate the superiority of the proposed approach over other state-of-the-art methods.

Low-light image enhancement based on Retinex theory for beam-splitting prism system

The existing color image enhancement methods are utilized for the most part to directly improve the color image that is obtained through the use of a Bayer array camera, whereas the color image that is obtained through the use of a prism camera is the result of the fusion of three primary color images that have been collected independently. As a result, a method for enhancing color photographs based on three images of primary colors that have a low level of light has been proposed. In this paper, we first transfer RGB to HSV space for image enhancement. In the V channel, we use guided filtering combined with improved SSR method to better preserve edge information. Then the S channel is adjusted adaptively to make the image look more natural. Finally, the image is transferred from HSV space back to RGB space. Compared with other traditional methods, our method achieves better results in PSNR, SSIM and NIQE, and has less computational complexity.

A survey of algorithm and hardware architecture for bilateral filter and application

In original images/videos, disturbance and noise are inevitable. Therefore, image and video filtering technology has been proposed and developed rapidly. In recent years, bilateral filtering has been widely utilized as an efficient filtering method that can effectively preserve edge information while reducing noise. Researchers have extensively studied the bilateral filtering algorithm and its hardware structures, generating several excellent optimization methods. This paper will comprehensively analyze typical bilateral filtering algorithms and hardware structure optimization design. Some directions for future bilateral filtering optimization will be provided, including algorithms and hardware structures, with analysis and discussion.

Segmentation of High‐Resolution Remote Sensing Images Using the Gabor Texture Feature‐Based Mean Shift Method

High‐resolution remote sensing images (HRRSIs) play an important role in the construction and development of society with their rich and detailed information. In the process of remote sensing image segmentation, the conventional method of mean shift usually involves spatial features and spectral features to preserve edge information and reduce the effect of noise. However, this traditional method often misses some important information in HRRSIs processing and reduces the segmentation accuracy. Thus, we proposed an improved mean shift image segmentation method based on Gabor texture features to make full use of the delicate information in HRRSIs. Specifically, the multiscale and multidirectional Gabor filters were employed in this study to extract pixel‐to‐pixel features from the QuickBird and GeoEye‐1 images, and the local variance was used to determine the optimal texture bandwidth. Two parameters, global segmentation (GS) quality index and error rate (ER), were adopted to evaluate the segmentation quality of these two HRRSIs. Results showed that the proposed approach in this study outperforms the traditional mean shift method on both remote sensing datasets. Compared with the traditional method, the improved mean shift approach corresponded to higher GS values and smaller ER values. This study confirms that the improved mean shift approach based on Gabor filtering has a potential for HRRSIs segmentation.

1D-DGAN-PHM: A 1-D denoising GAN for Prognostics and Health Management with an application to turbofan

The performance of prognostics is closely related to the quality of condition monitoring signals (e.g., temperature, pressure, or vibration signals), which reveal the degradation of the system of interest. However, typical condition monitoring signals include noise and outliers. Disentangling noise from these signals is essential to obtain the actual degradation trajectories. Different denoising methods have been proposed in prognostics. Conventional denoising methods have low complexity but usually do not preserve edge information and do not involve physical considerations. A promising deep learning approach is denoising generative models. This approach is popular in Computer Vision, which has been shown to outperform other classical techniques but has seldom been used in prognostics on 1-D signals. In this paper, we propose the 1-D Denoising Generative Adversarial Network for Prognostics and Health Management (1D-DGAN-PHM). The 1D-DGAN-PHM is trained on synthetic data generated by a custom data generator that infuses physics-of-failure knowledge in paired samples of noisy and noise-free trajectories. The network consists of two components, a denoising generator and a discriminator. The denoising generator aims to learn to denoise a 1-D input signal. The discriminator guides the learning by comparing noise-free signals with signals from the denoising generator. Advantages of the 1D-DGAN-PHM include the physics-of-failure information in the synthetic data generator and the model sophistication. In this work, we apply the 1D-DGAN-PHM to denoise the raw signals derived from NASA’s C-MAPSS simulator of an aircraft turbofan engine. Baseline methods are Moving Average, Median filter, Savitzky–Golay filter, and a denoising autoencoder. The 1D-DGAN-PHM produces smooth trajectories and preserves the initial linear degradation of the signals. The 1D-DGAN-PHM has the most significant improvement in prognosability (on average, 0.73 to 0.81). Data from the 1D-DGAN-PHM resulted in the best MAE (29 to 25 cycles) and RMSE (score of 39 to 36) for a Random Forest.The code is publicly available at 1D-DGAN-PHM.

Nonlinearly scaled prior image-controlled frequency split for high-frequency metal artifact reduction in computed tomography.

This paper introduces a new approach for the dedicated reduction of high-frequency metal artifacts, which applies a nonlinear scaling (NLS) transfer function on the high-frequency projection domain to reduce artifacts, while preserving edge information and anatomic detail by incorporating prior image information. An NLS function is applied to suppress high-frequency streak artifacts, but to restrict the correction to metal projections only, scaling is performed in the sinogram domain. Anatomic information should be preserved and is excluded from scaling by incorporating a prior image from tissue classification. The corrected high-frequency sinogram is reconstructed and combined with the low-frequency component of a normalized metal artifact reduction (NMAR) image. Scans of different anthropomorphic phantoms were acquired (unilateral hip, bilateral hip, dental implants, and embolization coil). Multiple regions of interest (ROIs) were drawn around the metal implants and hounsfield unit (HU) deviations were analyzed. Clinical data sets including single image slices of dental fillings, a bilateral hip implant, spinal fixation screws, and an aneurysm coil were reconstructed and assessed. The prior image-controlled NLS can remove streak artifacts while preserving anatomic detail within the bone and soft tissue. The qualitative analysis of clinical cases showed a tremendous enhancement within dental fillings and neuro coils, and a significant enhancement within spinal screws or hip implants. The phantom scan measurements support this observation. In all phantom setups, the NLS-corrected result showed lowest HU derivation and the best visualization of thedata. The prior image-controlled NLS provides a method to reduce high-frequency streaks in metal-corrupted computed tomography (CT)data.

Joint self-supervised and reference-guided learning for depth inpainting

Depth information can benefit various computer vision tasks on both images and videos. However, depth maps may suffer from invalid values in many pixels, and also large holes. To improve such data, we propose a joint self-supervised and reference-guided learning approach for depth inpainting. For the self-supervised learning strategy, we introduce an improved spatial convolutional sparse coding module in which total variation regularization is employed to enhance the structural information while preserving edge information. This module alternately learns a convolutional dictionary and sparse coding from a corrupted depth map. Then, both the learned convolutional dictionary and sparse coding are convolved to yield an initial depth map, which is effectively smoothed using local contextual information. The reference-guided learning part is inspired by the fact that adjacent pixels with close colors in the RGB image tend to have similar depth values. We thus construct a hierarchical joint bilateral filter module using the corresponding color image to fill in large holes. In summary, our approach integrates a convolutional sparse coding module to preserve local contextual information and a hierarchical joint bilateral filter module for filling using specific adjacent information. Experimental results show that the proposed approach works well for both invalid value restoration and large hole inpainting.

Tensor Dictionary Learning with an Enhanced Sparsity Constraint for Sparse-View Spectral CT Reconstruction

Spectral computed tomography (CT) can divide collected photons into multi-energy channels and gain multi-channel projections synchronously by using photon-counting detectors. However, reconstructed images usually contain severe noise due to the limited number of photons in the corresponding energy channel. Tensor dictionary learning (TDL)-based methods have achieved better performance, but usually lose image edge information and details, especially from an under-sampling dataset. To address this problem, this paper proposes a method termed TDL with an enhanced sparsity constraint for spectral CT reconstruction. The proposed algorithm inherits the superiority of TDL by exploring the correlation of spectral CT images. Moreover, the method designs a regularization using the L0-norm of the image gradient to constrain images and the difference between images and a prior image in each energy channel simultaneously, further improving the ability to preserve edge information and subtle image details. The split-Bregman algorithm has been applied to address the proposed objective minimization model. Several numerical simulations and realistic preclinical mice are studied to assess the effectiveness of the proposed algorithm. The results demonstrate that the proposed method improves the quality of spectral CT images in terms of noise elimination, edge preservation, and image detail recovery compared to the several existing better methods.

Low-light image enhancement via deep Retinex decomposition and bilateral learning

Low-light images enhancement is a challenging task because enhancing image brightness and reducing image degradation should be considered simultaneously. Although existing deep learning-based methods improve the visibility of low-light images, many of them tend to lose details or sacrifice naturalness. To address these issues, we present a multi-stage network for low-light image enhancement, which consists of three sub-networks. More specifically, inspired by the Retinex theory and the bilateral grid technique, we first design a reflectance and illumination decomposition network to decompose an image into reflectance and illumination maps efficiently. To increase the brightness while preserving edge information, we then devise an attention-guided illumination adjustment network. The reflectance and the adjusted illumination maps are fused and refined by adversarial learning to reduce image degradation and improve image naturalness. Experiments are conducted on our rebuilt SICE low-light image dataset, which consists of 1380 real paired images and a public dataset LOL, which has 500 real paired images and 1000 synthetic paired images. Experimental results show that the proposed method outperforms state-of-the-art methods quantitatively and qualitatively.

Edge-preserving MRI image synthesis via adversarial network with iterative multi-scale fusion

Magnetic resonance imaging (MRI) is a major imaging technique for studying neuroanatomy. By applying different pulse sequences and parameters, different modalities can be generated regarding the same anatomical structure, which can provide complementary information for diagnosis. However, limited by the scanning time and related cost, multiple different modalities are often not available for the same patient in clinic. Recently, many methods have been proposed for cross-modality MRI synthesis, but most of them only consider pixel-level differences between the synthetic and ground-truth images, ignoring the edge information, which is critical to provide clinical information. In this paper, we propose a novel edge-preserving MRI image synthesis method with iterative multi-scale feature fusion based generative adversarial network (EP_IMF-GAN). Particularly, the generator consists of a shared encoder and two specific decoders to carry out different tasks: 1) a primary task aiming to generate the target modality and 2) an auxiliary task aiming to generate the corresponding edge image of target modality. We assume that infusing the auxiliary edge image generation task can help preserve edge information and learn better latent representation features through the shared encoder. Meanwhile, an iterative multi-scale fusion module is embedded in the primary decoder to fuse supplementary information of feature maps at different scales, thereby further improving quality of the synthesized target modality. Experiments on the BRATS dataset indicate that our proposed method is superior to the state-of-the-art image synthesis approaches in both qualitative and quantitative measures. Ablation study further validates the effectiveness of the proposed components.

Multi-modal medical image fusion based on equilibrium optimizer algorithm and local energy functions

Multi-modal medical image fusion brings many benefits to clinical diagnosis and analysis because it creates favorable conditions for diagnostic imaging practitioners to make a more accurate diagnosis. According to our current knowledge, there are still some disadvantages to current image fusion approaches. The first one is that the fused images often have low contrast. The reason for this is several approaches use a weighted average rule for fusing low-frequency components. The second drawback is that the loss of detailed information in the fused image. This can be explained by the fact that the high-frequency components synthesized by the rules are not really effective. In this paper, two novel algorithms are proposed to tackle the above two disadvantages. The first algorithm is based on the Equilibrium optimizer algorithm (EOA) to find optimal parameters to fuse low-frequency components. This allows the fused image to have good contrast. The second algorithm is based on the sum of local energy functions using the Prewitt compass operator to create an efficient rule for the fusion of high-frequency components. This allows the fused image to significantly preserve details transferred from input images. Experimental results show that the proposed approach not only effective in significantly enhancing the quality of the fusion image but also preserving edge information carried from input images.