Image Noise Research Articles

In vitro and in vivo optimized reconstruction for low-keV virtual monoenergetic photon-counting detector CT angiography of lower legs

BackgroundLower extremity peripheral artery disease frequently presents with calcifications which reduces the accuracy of computed tomography (CT) angiography, especially below-the-knee. Photon-counting detector (PCD)-CT offers improved spatial resolution and less calcium blooming. We aimed to identify the optimal reconstruction parameters for PCD-CT angiography of the lower legs.MethodsTubes with different diameters (1–5 mm) were filled with different iodine concentrations and scanned in a water container. Images were reconstructed with 0.4 mm isotropic resolution using a quantitative kernel at all available sharpness levels (Qr36 to Qr76) and using different levels of quantum iterative reconstruction (QIR-2–4). Noise and image sharpness were determined for all reconstructions. Additionally, CT angiograms of 20 patients, reconstructed with a medium (Qr44), sharp (Qr60), and ultrasharp (Qr72) kernel at QIR-2-4, were evaluated by three readers assessing noise, delineation of plaques and vessel walls, and overall quality.ResultsIn the phantom study, increased kernel sharpness led to higher image noise (e.g., 16, 38, 77 HU for Qr44, Qr60, Qr72, and QIR-3). Image sharpness increased with increasing kernel sharpness, reaching a plateau at the medium-high level 60. Higher QIR levels decreased image noise (e.g., 51, 38, 25 HU at QIR-2–4 and Qr60) without reducing vessel sharpness. The qualitative in vivo results confirmed these findings: the sharp kernel (Qr60) with the highest QIR yielded the best overall quality.ConclusionThe combination of a sharpness level optimized reconstruction kernel (Qr60) and the highest QIR level yield the best image quality for PCD-CT angiography of the lower legs when reconstructed at 0.4-mm resolution.Relevance statementUsing high-resolution PCD-CT angiography with optimized reconstruction parameters might improve diagnostic accuracy and confidence in peripheral artery disease of the lower legs.Key PointsEffective exploitation of the potential of PCD-CT angiography requires optimized reconstruction parameters.Too soft or too sharp reconstruction kernels reduce image quality.The highest level of quantum iterative reconstruction provides the best image quality.Graphical

DermoGAN: multi-task cycle generative adversarial networks for unsupervised automatic cell identification on in-vivo reflectance confocal microscopy images of the human epidermis.

Accurate identification of epidermal cells on reflectance confocal microscopy (RCM) images is important in the study of epidermal architecture and topology of both healthy and diseased skin. However, analysis of these images is currently done manually and therefore time-consuming and subject to human error and inter-expert interpretation. It is also hindered by low image quality due to noise and heterogeneity. We aimed to design an automated pipeline for the analysis of the epidermal structure from RCM images. Two attempts have been made at automatically localizing epidermal cells, called keratinocytes, on RCM images: the first is based on a rotationally symmetric error function mask, and the second on cell morphological features. Here, we propose a dual-task network to automatically identify keratinocytes on RCM images. Each task consists of a cycle generative adversarial network. The first task aims to translate real RCM images into binary images, thus learning the noise and texture model of RCM images, whereas the second task maps Gabor-filtered RCM images into binary images, learning the epidermal structure visible on RCM images. The combination of the two tasks allows one task to constrict the solution space of the other, thus improving overall results. We refine our cell identification by applying the pre-trained StarDist algorithm to detect star-convex shapes, thus closing any incomplete membranes and separating neighboring cells. The results are evaluated both on simulated data and manually annotated real RCM data. Accuracy is measured using recall and precision metrics, which is summarized as the -score. We demonstrate that the proposed fully unsupervised method successfully identifies keratinocytes on RCM images of the epidermis, with an accuracy on par with experts' cell identification, is not constrained by limited available annotated data, and can be extended to images acquired using various imaging techniques without retraining.

SeisRAFT: A recurrent deep learning network for 4D seismic registration and CO2 storage monitoring

The alignment or registration of seismic images is an important and extensively researched aspect in seismic data processing. This process plays a pivotal role in evaluating the evolution of CO2 plumes and assessing the potential for CO2 leakage from its reservoir storage when using 4D or time-lapse seismic methodology. The computer vision community has demonstrated considerable advantages in employing deep learning for such tasks, particularly when confronted with substantial shifts, mismatches, and noises in complex images. In this study, we leverage a cutting-edge recurrent deep learning network known as recurrent all-pairs field transforms (RAFT), incorporating tailored modifications to address seismic matching challenges. We evaluate the network's performance on both synthetic and field 4D CO2 seismic data sets, showcasing its superior accuracy and effectiveness compared to a widely used traditional method. Particularly, in some intricate and ambiguous instances, where even human vision may struggle to identify corresponding events between images, our deep learning method exhibits strong and reliable performance. Validated results confirm that this lightweight multiscale network, trained through self-supervised learning, offers a rapid, parameter-free, and end-to-end solution for 4D image matching in subsurface CO2 storage monitoring with potential applicability to many other seismic registration tasks.

Pseudo-ISP: Learning pseudo in-camera signal processing pipeline from a color image denoiser

Existing deep denoisers usually ignore the problem of noise discrepancy between training and test images caused by the different noise modeling of sensor and in-camera signal processing (ISP) pipeline, which inevitably degrades the denoising performance. In this paper, we present an unpaired learning scheme to adapt the color image denoisers for handling test images with noise discrepancy. To this end, we consider a practical training setting equipped with a pre-trained color denoiser, a set of test noisy sRGB images, and an unpaired set of clean sRGB images. Then, we propose to alternate between two modules, i.e., Pseudo-ISP training for learning noise modeling of sensor and in-camera signal processing (ISP) pipeline and denoiser adaption. Instead of modeling the complex noise in sRGB images, we assume the signal-dependent and spatially independent noise in rawRGB space, and specifically design the Pseudo-ISP to learn the pseudo ISP pipeline and pseudo rawRGB noise model jointly. Applying the learned Pseudo-ISP to the unpaired set of clean sRGB images, the corresponding realistic noisy sRGB observations can be easily obtained. Conversely, using the generated paired data for model fine-tuning, the color denoiser can be well adapted for test images. Through iterating between Pseudo-ISP training and denoiser adaption, denoising performance of deep denoisers can be further improved. Experiments show that our Pseudo-ISP not only can boost simple Gaussian blurring-based denoiser to achieve competitive performance against CBDNet, but also is effective in improving state-of-the-art deep denoisers, e.g., CBDNet and RIDNet.

Road-pavement classification by artificial neural network model based on tire-pavement noise and road-surface image

This study focuses on an artificial neural network (ANN) model for classifying pavement types using acoustic and image data. While conventional studies often use road-surface images for pavement classification, they face challenges with image quality degradation owing to external factors, such as sunlight angle, shadows, and lighting. Therefore, in this study, tire-pavement noise, which has different noise characteristics depending on the material and surface treatment, is used independently and in conjunction with image data for ANN training. To construct the training dataset, tire-pavement noise, and road-surface images are collected from 11 highway sampling sites in South Korea. Two simultaneous measurements are used: the tire-pavement noise is collected using the On-board sound intensity (OBSI) method, and the camera captures the road-surface images. 1/3 octave SIL, spectrum, MFCC, GLCM, and HOG are extracted from the raw data, and the ANN models are trained by these features. Using the spectrum as an input feature for the ANN yields a classification accuracy of 95.18%. However, the total number of parameters in the ANN is double that of the other models. To reduce the ANN size, 1/3 octave band SIL is used for training, and the model size is halved. However, the accuracy decreases by 13.47 percentage points. To overcome this significant decrease, the 1/3 octave bands SIL and image features were used to train ANN, simultaneously. This approach increases the accuracy by 93.85%. By training the ANN using MFCC, which is commonly used as an acoustic feature in other machine learning studies, the highest classification accuracy of 96.84% is achieved. Additionally, MFCC models are affected by the number of coefficients and the signal length. To include the dominant frequency of tire-pavement noise, more than 13 coefficients are used, a number generally known to be suitable for speech recognition. Increasing the number of coefficients from 13 to 40 improves accuracy by 1.17 percentage points. The interval for slicing raw WAV files is reduced to increase the training data and classify the pavement using shorter signals without statistically significant accuracy loss. Although accuracy does not decrease until the signal lengths reach 0.5 seconds, it rapidly decreases when the signal lengths become shorter than 0.4 seconds.

Enhanced domain transfer deep fuzzy echo state network for rotating machinery fault diagnosis based on current signal

Although vibration-based fault diagnosis methods have achieved remarkable results in rotating machinery, they are still limited by various factors, such as environment noise and additional sensor installation. Meanwhile, due to inevitable distribution differences in practical engineering, deep transfer learning models are commonly used in fault diagnostic fields. Although deep architectures can extract representative domain-invariant features, they typically result in substantial computational burdens and training time. Therefore, to address the above problems, an enhanced domain transfer deep fuzzy echo state network (EDFESN) is proposed for rotating machinery fault diagnosis based on current signals. Firstly, current signals derived from the driving motor are directly collected without additional sensors. Secondly, an enhanced domain mapping method is raised to solve the problem of data distribution discrepancies between cross domain. Furthermore, a deep fuzzy echo state network (DFESN) integrated with fuzzy clustering is constructed, which utilizes layer-wise fuzzy-tuning learning paradigm instead of backpropagation step to reduce training time. Two datasets from gearbox and bearing both verify the effectiveness of the proposed method. Compared with other popular transfer methods, EDFESN not only achieves highest accuracy, but also has fastest training speed.

Superobbing and Thinning Scales for All-Sky Humidity Sounder Assimilation

Abstract Humidity sounder radiances are currently thinned to 110-km spacing prior to assimilation at ECMWF and used with no averaging applied. In this paper, the thinning scale and possible averaging of all-sky humidity sounder observations into “superobs” are considered. The short- and medium-range forecast impacts of changing the thinning and averaging scales of humidity sounder radiances prior to the data assimilation are investigated separately and then together. Superobbing acts as a low-pass filter and provides smoother images of departures, decreasing the effective sensor noise and thus the standard deviation of background departures, marginally for 183-GHz channels (5%–15%) and significantly for 118-GHz channels (5%–55%). Observations are thus more representative of the model effective resolution, with a better utilization of total information content than thinning native-resolution radiances, as less information is discarded. Whether changed in isolation or combination, the additions of data via superobbing and finer thinning are both shown to markedly improve background fits to independent observations, indicative of better short-range forecasts of humidity and improved winds via the 4D-Var tracer effect. Wind forecasts in the Southern Hemisphere are slightly improved in the medium range. A final configuration is tested at the resolution of the current operational model, with humidity sounder radiances averaged into 50-km superobs with 70-km spacing. This provides about 140% more radiances for assimilation and more finely detailed maps to analyze mesoscale features. The forecast impact of this change is larger in testing with higher model and data assimilation resolutions, showing the scale dependence of such decisions and the expected performance in an operational configuration. Significance Statement This paper investigates thinning and averaging scales for humidity-sounding microwave observations in the ECMWF data assimilation system. The introduction of spatial averaging shows a positive impact, as does the assimilation of observations with finer spacing. These changes permit more total information on humidity into the system, and both are beneficial for short-range forecasts of humidity and winds in the mid- to upper troposphere. The results highlight the interplay between spatial scales of observations and those of the analysis system, with possibilities for improved utilization in this particular case. This is expected to remain a key consideration in assimilation systems going forward, given the continued increases in the resolution of assimilation systems and forecast models.

SomaSeg: a robust neuron identification framework for two-photon imaging video

Objective.Accurate neuron identification is fundamental to the analysis of neuronal population dynamics and signal extraction in fluorescence videos. However, several factors such as severe imaging noise, out-of-focus neuropil contamination, and adjacent neuron overlap would impair the performance of neuron identification algorithms and lead to errors in neuron shape and calcium activity extraction, or ultimately compromise the reliability of analysis conclusions.Approach.To address these challenges, we developed a novel cascade framework named SomaSeg. This framework integrates Duffing denoising and neuropil contamination defogging for video enhancement, and an overlapping instance segmentation network for stacked neurons differentiating.Main results.Compared with the state-of-the-art neuron identification methods, both simulation and actual experimental results demonstrate that SomaSeg framework is robust to noise, insensitive to out-of-focus contamination and effective in dealing with overlapping neurons in actual complex imaging scenarios.Significance.The SomaSeg framework provides a widely applicable solution for two-photon video processing, which enhances the reliability of neuron identification and exhibits value in distinguishing visually confusing neurons.

DEEP NEURAL MULTI WAVELET SEGMENTATION AND RESNET-50 IMAGE CLASSIFICATION (DNMWS-RESNET-50IC) BASED EARLY GLAUCOMA DETECTION

Glaucoma, a leading cause of irreversible blindness worldwide, results from progressive damage to the optic nerve, often linked to elevated Intra Ocular Pressure (IOP). Early detection is critical for preventing vision loss, yet traditional diagnostic methods can be limited in accessibility and effectiveness, particularly in the early stages of the disease. Addressing the need for early detection, we propose the Deep Neural Multi-Wavelet Segmentation and ResNet-50 Image Classification (DNMWS-ResNet-50IC) method, specifically designed to detect glaucoma at an early stage using retinal fundus images. In this work, we apply Anisotropic Gaussian Filtering for the preprocessing of retinal fundus images, effectively reducing image noise while preserving the original quality of the image pixels by creating an adaptive window size and scale space. We then utilize multi- wavelet-based image segmentation, leveraging wavelet transforms to analyze and decompose the image into its various frequency components. This technique is particularly advantageous for managing images with complex structures and textures. Subsequently, the segmented features are classified using the ResNet-50 model, which categorizes the images as normal, abnormal, or indicative of early- stage glaucoma. The effectiveness of the proposed method is assessed by measuring three key performance indicators sensitivity, specificity, and accuracy on digital retinal images from the HRF image database. Additionally, the model's performance is further evaluated on a separate test set, considering metrics such as accuracy, precision, recall, and prediction time.

SimNFND: A Forward-Looking Sonar Denoising Model Trained on Simulated Noise-Free and Noisy Data

Given the propagation characteristics of sound waves and the complexity of the underwater environment, denoising forward-looking sonar image data presents a formidable challenge. Existing studies often add noise to sonar images and then explore methods for its removal. This approach neglects the inherent complex noise in sonar images, resulting in inaccurate evaluations of traditional denoising methods and poor learning of noise characteristics by deep learning models. To address the lack of high-quality data for FLS denoising model training, we propose a simulation algorithm for forward-looking sonar data based on RGBD data. By utilizing rendering techniques and noise simulation algorithms, high-quality noise-free and noisy sonar data can be rapidly generated from existing RGBD data. Based on these data, we optimize the loss function and training process of the FLS denoising model, achieving significant improvements in noise removal and feature preservation compared to other methods. Finally, this paper performs both qualitative and quantitative analyses of the algorithm’s performance using real and simulated sonar data. Compared to the latest FLS denoising models based on traditional methods and deep learning techniques, our method demonstrates significant advantages in denoising capability. All inference results for the Marine Debris Dataset (MDD) have been made open source, facilitating subsequent research and comparison.

Ricci curvature based volumetric segmentation

The level set method has played a critical role among many image segmentation approaches. Several edge detectors, such as the gradient, have been applied to its regularisation term. However, traditional edge detectors lack high-order information and are sensitive to image noise. To tackle this problem, we introduce a method to calculate the Ricci curvature, a vital curvature in three-dimensional Riemannian geometry. In addition, we propose incorporating the curvature into the regularisation term. Experiments suggest that our method outperforms the state-of-the-art level set methods and achieves a comparable result with the Swin UNETR and Segment Anything.

Accurate UAV Small Object Detection Based on HRFPN and EfficentVMamba.

(1) Background: Small objects in Unmanned Aerial Vehicle (UAV) images are often scattered throughout various regions of the image, such as the corners, and may be blocked by larger objects, as well as susceptible to image noise. Moreover, due to their small size, these objects occupy a limited area in the image, resulting in a scarcity of effective features for detection. (2) Methods: To address the detection of small objects in UAV imagery, we introduce a novel algorithm called High-Resolution Feature Pyramid Network Mamba-Based YOLO (HRMamba-YOLO). This algorithm leverages the strengths of a High-Resolution Network (HRNet), EfficientVMamba, and YOLOv8, integrating a Double Spatial Pyramid Pooling (Double SPP) module, an Efficient Mamba Module (EMM), and a Fusion Mamba Module (FMM) to enhance feature extraction and capture contextual information. Additionally, a new Multi-Scale Feature Fusion Network, High-Resolution Feature Pyramid Network (HRFPN), and FMM improved feature interactions and enhanced the performance of small object detection. (3) Results: For the VisDroneDET dataset, the proposed algorithm achieved a 4.4% higher Mean Average Precision (mAP) compared to YOLOv8-m. The experimental results showed that HRMamba achieved a mAP of 37.1%, surpassing YOLOv8-m by 3.8% (Dota1.5 dataset). For the UCAS_AOD dataset and the DIOR dataset, our model had a mAP 1.5% and 0.3% higher than the YOLOv8-m model, respectively. To be fair, all the models were trained without a pre-trained model. (4) Conclusions: This study not only highlights the exceptional performance and efficiency of HRMamba-YOLO in small object detection tasks but also provides innovative solutions and valuable insights for future research.

Impact on Image Quality and Diagnostic Performance of Dual-Layer Detector Spectral CT for Pulmonary Subsolid Nodules: Comparison With Hybrid and Model-Based Iterative Reconstruction.

To evaluate the image quality and diagnostic performance of pulmonary subsolid nodules on conventional iterative algorithms, virtual monoenergetic images (VMIs), and electron density mapping (EDM) using a dual-layer detector spectral CT (DLSCT). This retrospective study recruited 270 patients who underwent DLSCT scan for lung nodule screening or follow-up. All CT examinations with subsolid nodules (pure ground-glass nodules [GGNs] or part-solid nodules) were reconstructed with hybrid and model-based iterative reconstruction, VMI at 40, 70, 100, and 130 keV levels, and EDM. The CT number, objective image noise, signal-to-noise ratio, contrast-to-noise ratio, diameter, and volume of subsolid nodules were measured for quantitative analysis. The overall image quality, image noise, visualization of nodules, artifact, and sharpness were subjectively rated by 2 thoracic radiologists on a 5-point scale (1 = unacceptable, 5 = excellent) in consensus. The objective image quality measurements, diameter, and volume were compared among the 7 groups with a repeated 1-way analysis of variance. The subjective scores were compared with Kruskal-Wallis test. A total of 198 subsolid nodules, including 179 pure GGNs, and 19 part-solid nodules were identified. Based on the objective analysis, EDM had the highest signal-to-noise ratio (164.71 ± 133.60; P < 0.001) and contrast-to-noise ratio (227.97 ± 161.96; P < 0.001) among all image sets. Furthermore, EDM had a superior mean subjective rating score (4.80 ± 0.42) for visualization of GGNs compared to other reconstructed images (all P < 0.001), although the model-based iterative reconstruction had superior subjective scores of overall image quality. For pure GGNs, the measured diameter and volume did not significantly differ among different reconstructions (both P > 0.05). EDM derived from DLSCT enabled improved image quality and lesion conspicuity for the evaluation of lung subsolid nodules compared to conventional iterative reconstruction algorithms and VMIs.

LDCT image denoising algorithm based on two-dimensional variational mode decomposition and dictionary learning

Low-dose X-CT scanning method effectively reduces radiation hazards, however, reducing the radiation dose will introduce noise and artifacts during the projection process, resulting in a decrease in the quality of the reconstructed image. To address this problem, we combined 2D variational modal decomposition and dictionary learning. We proposed a low-dose CT (LDCT) image denoising algorithm based on an improved K-SVD algorithm with image decomposition. The dictionary obtained by K-SVD training lacks consideration of image structure information. To address this problem, we employ the two-dimensional variational mode decomposition (2D-VMD) method to decompose the image into distinct modal components. Through the adaptive learning of dictionaries based on the characteristics of each modal component, independent denoising processing is applied to each component, avoiding the loss of structural and detailed information in the image. In addition, we introduce the regularized orthogonal matching pursuit algorithm (ROMP) and dictionary atom optimization method to improve the sparse representation ability of the dictionary and reduce the impact of noise atoms on denoising performance. The experiments show that the proposed method outperforms other denoising methods regarding peak signal-to-noise ratio and structural similarity. The proposed method maintains the denoised image details and structural information while removing LDCT image noise and artifacts. The image quality after denoising is significantly improved and facilitates more accurate detection and analysis of lesion areas.

Dual-Split CT to Simulate Multiple Radiation Doses From a Single Scan-Liver Lesion Detection Compared With Dose-Matched Single-Energy CT.

The aim of this study was to evaluate the potential use of simulated radiation doses from a dual-split CT scan for dose optimization by comparing their lesion detectability to dose-matched single-energy CT acquisitions at different radiation dose levels using a mathematical model observer. An anthropomorphic abdominal phantom with liver lesions (5-10 mm, both hyperattenuating and hypoattenuating) was imaged using a third-generation dual-source CT in single-energy dual-source mode at 100 kVp and 3 radiation doses (5, 2.5, 1.25 mGy). The tube current was 67% for tube A and 33% for tube B. For each dose, 5 simulated radiation doses (100%, 67%, 55%, 45%, 39%, and 33%) were generated through linear image blending. The phantom was also imaged using traditional single-source single-energy mode at equivalent doses. Each setup was repeated 10 times. Image noise texture was evaluated by the average spatial frequency (fav) of the noise power spectrum. Liver lesion detection was measured by the area under the receiver operating curve (AUC), using a channelized Hotelling model observer with 10 dense Gaussian channels. Fav decreased at lower radiation doses and differed between simulated and single-energy images (eg, 0.16 mm-1 vs 0.14 mm-1 for simulated and single-energy images at 1.25 mGy), indicating slightly blotchier noise texture for dual-split CT. For hyperattenuating lesions, the mean AUC ranged between 0.92-0.99, 0.81-0.96, and 0.68-0.89 for single-energy, and between 0.91-0.99, 0.78-0.91, and 0.70-0.85 for dual-split at 5 mGy, 2.5 mGy, and 1.25 mGy, respectively. For hypoattenuating lesions, the AUC ranged between 0.90-0.98, 0.75-0.93, and 0.69-0.86 for the single-energy, and between 0.92-0.99, 0.76-0.87, and 0.67-0.81 for dual-split at 5 mGy, 2.5 mGy, and 1.25 mGy, respectively. AUC values were similar between both modes at 5 mGy, and slightly lower, albeit not significantly, for the dual-split mode at 2.5 and 1.25 mGy. Lesion detectability was comparable between multiple simulated radiation doses from a dual-split CT scan and dose-matched single-energy CT. Noise texture was slightly blotchier in the simulated images. Simulated doses using dual-split CT can be used to assess the impact of radiation dose reduction on lesion detectability without the need for repeated patient scans.

Analisis Hasil Safire pada Imaging CT Scan Kepala

Background: Iterative Reconstruction (IR) method was first applied to CT in 1960 and successfully used for the first time in clinical research by reconstructing 128 x 128 images according to image metrics and using high-resolution images of 512 x 512 for special research activities such as image evaluation. artifacts and noise. In 2008, the development of IR can improve image quality and reduce the amount of radiation in clinical CT diagnosis. Iterative reconstruction promises to improve image quality while reducing radiation dose. This has been demonstrated in CT of the thorax, coronary arteries, abdomen, spine and neck, paranasal sinuses, and head. Sinogram-Afirmed Iterative Reconstruction (SAFIRE) is one of the iterative algorithm reconstruction methods that uses noise modeling techniques, Sinogram-Afirmed Iterative Reconstruction (SAFIRE), promises to improve Cranial CT (CCT). In this new technique, raw data-based iteration for artifact reduction is combined with image-based iteration using smooth regularization that estimates the variance of image noise in various directions at each image pixel and adjusts it with a spatial variance regularization function simultaneously. Methods: This study is a literature review, where literature exploration is carried out on various databases with keywords such as, Reference sources used in compiling this article include google scollar, as well as articles in English and Indonesian scientific journals. Results: Itarative Reconstruction (IR) Head CT Scan, SAFIRE includes reducing or adding noise to the image results, artifacts, acquisition time, increasing SNR and CNR and reducing dose in the examination. Conclusion: Analysis of Safire results in Head CT-Scan Imaging has an Itarative Reconstruction (SAFIRE) procedure, the role of safire in head CT scans is to optimize noise in the Reconstructed image and can reduce artifacts in the image and increase SNR, CNR in the Reconstructed results so that it can provide better information.

Speckle noise suppression of a reconstructed image in digital holography based on the BM3D improved convolutional neural network

In digital holographic measurement, when light waves pass through inhomogeneous media or surfaces, speckle noise is generated, resulting in random, granular light and dark spots in the hologram, which greatly reduces the image quality. Therefore, in order to improve the image quality of holographic reconstruction, a noise reduction method based on the BM3D improved convolutional neural network (CNN) is proposed in this paper. Firstly, the similarity and important statistical information between blocks can be obtained by using BM3D. Then, the denoising convolutional neural network (DnCNN) is used to learn the relationship between the noise of a large number of samples and the noise image, and further purify the image to retain the details for a better denoising effect. Finally, a reflective off-axis digital holographic optical path system is constructed to collect the holograms of the test samples, and the reconstructed images are obtained by the Fresnel diffraction method to constitute a dataset with the simulated holographic reconstructed images to validate the proposed method in this paper, compared to the other methods, such as DnCNN, convolutional blind denoising network (CBDNet), BM3D, and Wiener filtering. The experimental results of qualitative and quantitative analyses show that the proposed method combines the advantages of traditional algorithms and deep learning, significantly enhances the robustness of the system, optimizes the denoising performance, and preserves the details of the reconstructed image to the greatest extent.

Digital Medical Images Segmentation by Active Contour Model based on the Signed Pressure Force Function

The signed pressure force (SPF) function has recently become a popular function for guiding the curve evolution of the active contour model (ACM) for image segmentation. The aim is to extract the boundaries of digital medical images for shape and image analysis. The recent SPF-based ACM demonstrates effectiveness in image segmentation. However, it may fail if the targeted object is close to a neighbouring object. Additionally, the presence of intensity inhomogeneity and noise in medical images degrades segmentation accuracy and local target areas. Thus, we proposed a new SPF-based ACM, namely the Selective Segmentation with Signed Pressure Force 1 (SSPF1) model, by incorporating the ideas of the SPF function and the distance fitting term based on geometrical constraints. Then, the new SSPF1 model was extended by incorporating an image enhancement technique to develop our second new model, termed the Selective Segmentation with Signed Pressure Force 2 (SSPF2). Numerical results indicated that the SSPF2 model was more recommended than SSPF1 as the SSPF2 model was approximately 4.7% more accurate, as indicated by the Jaccard value and was about 112 times faster in segmenting noisy images compared to the existing selective segmentation model.

Negative photo conductivity triggered with visible light in wide bandgap oxide-based optoelectronic crossbar memristive array for photograph sensing and neuromorphic computing applications

Photoresponsivity studies of wide-bandgap oxide-based devices have emerged as a vibrant and popular research area. Researchers have explored various material systems in their quest to develop devices capable of responding to illumination. In this study, we engineered a mature wide-bandgap oxide-based bilayer heterostructure synaptic memristor to emulate the human brain for applications in neuromorphic computing and photograph sensing. The device exhibits advanced electric and electrophotonic synaptic functions, such as long-term potentiation (LTP), long-term depression (LTD), and paired-pulse facilitation (PPF), by applying successive electric and photonic pulses. Moreover, the device exhibits exceptional electrical SET and photonic RESET endurance, maintaining its stability for a minimum of 1200 cycles without any degradation. Density functional theory calculations of the band structures provide insights into the conduction mechanism of the device. Based on this memristor array, we developed an autoencoder and convolutional neural network for noise reduction and image recognition tasks, which achieves a peak signal-to-noise ratio of 562 and high accuracy of 84.23%, while consuming lower energy by four orders of magnitude compared with the Tesla P40 GPU. This groundbreaking research not only opens doors for the integration of our device into image processing but also represents a significant advancement in the realm of in-memory computing and photograph-sensing features in a single cell.

Digital Image Noise Reduction Based on Proposed Smoothing and Sharpening Filters

In order to reduce noise in digital photographs, this paper provides a thorough analysis of sophisticated sharpness enhancement and image smoothing approaches. The research compares and contrasts different approaches, including well-known filters like Gaussian filter, Mean filter, Weighted Averaging filter, Laplacian filters, and Unsharp mask, with suggested strategies aimed at achieving optimal efficiency. The performance of these techniques is evaluated in several circumstances with speckle noise and Gaussian noise corrupted images. The results show how well the suggested strategy performs in terms of reducing noise, preserving image features, and improving overall image quality. The comparative advantage of the suggested technique over conventional filters is highlighted by comparative analysis. The study's conclusion offers information on the possible uses and future developments of these methods in practical image processing situations.