Anisotropic Diffusion Filter Research Articles

Analysis of methods and algorithms for image filtering and quality enhancement

This paper addresses the prevalent issue of image noise and presents methods for its mitigation. The paper describes, analyses and tests a variety of image filtering techniques, with specific reference to their use in different contexts. The filtering methods can be classified into two principal categories: linear filters, which include the Gaussian and mean filters, and non-linear filters, which comprise the median filter, the Fast Fourier Transform (FFT), the Non-Local Means (NLM) filter, and the anisotropic diffusion filter. The efficacy of each filter is mathematically described and evaluated on RGB images using the Python programming language. The study delineates the evaluation metrics and their respective advantages and disadvantages. The Root Mean Square Error (RMSE) and Peak Signal-to-Noise Ratio (PSNR) are employed as criteria for the analysis of algorithm efficiency. Furthermore, the mean execution time for each algorithm is also monitored. The experimental data suggests that linear filters are relatively fast but produce inferior results and are best employed as preparatory measures. Non-linear filters have been demonstrated to be more robust and applicable to a variety of noise types, although it has been established that they require parameter fine-tuning. The study demonstrates that anisotropic diffusion is suitable for both manual image processing and real-time applications, offering an optimal balance between processing speed and denoised image quality. NLM is optimal for high-quality single image processing due to its superior results, despite a slower processing speed. FFT is noted for its efficiency in eliminating periodic noise. Further research will be conducted on advancing filtering techniques for different real-world scenarios and autonomous systems.

Enhancing photoacoustic imaging for lung diagnostics and BCI communication: simulation of cavity structures artifact generation and evaluation of noise reduction techniques.

Pandemics like COVID-19 have highlighted the potential of Photoacoustic imaging (PAI) for Brain-Computer Interface (BCI) communication and lung diagnostics. However, PAI struggles with the clear imaging of blood vessels in areas like the lungs and brain due to their cavity structures. This paper presents a simulation model to analyze the generation and propagation mechanism within phantom tissues of PAI artifacts, focusing on the evaluation of both Anisotropic diffusion filtering (ADF) and Non-local mean (NLM) filtering, which significantly reduce noise and eliminate artifacts and signify a pivotal point for selecting artifact-removal algorithms under varying conditions of light distribution. Experimental validation demonstrated the efficacy of our technique, elucidating the effect of light source uniformity on artifact-removal performance. The NLM filtering simulation and ADF experimental validation increased the peak signal-to-noise ratio by 11.33% and 18.1%, respectively. The proposed technique adds a promising dimension for BCI and is an accurate imaging solution for diagnosing lung diseases.

An improved method for upscaling 2D images using adaptive edge sharpening and an optimized directional anisotropic diffusion filter

Image upscaling employs various polynomial techniques, including bicubic and Lanczos, to minimize computing load for various real-time applications. Polynomial interpolation, on the other hand, results in blurring artifacts in high resolution (HR) images due to edge degradation. Many other interpolation approaches, including edge-based and dictionary learning-based schemes, result in blurring in the image’s high frequency (HF) region. As a result, a novel post-processing technique is proposed that uses the Lanczos method to upscale the low resolution (LR) image. To eliminate blur along the image’s edge, the edge component of the interpolated image is retrieved. Adaptive sharpening is used to make the edges more prominent, as predicting pixels in the high variance region is challenging. After the edge is extracted, the smooth region is filtered with an optimized directional anisotropic diffusion (ODAD) filter to preserve texture details and geometric regularity. The sharpened edge image is aggregated with the ODAD filtered image to generate an improved HR (IHR) image. The IHR is then scaled up and down to reduce blurring even further, resulting in a blurred HR image (BHR). The residual image is obtained by subtracting the BHR from the IHR images, which represent the undetected HF. Finally, the residual image and the IHR image are combined to generate the final restored image, which includes all prediction loss details. The results of the experiments show that the proposed algorithm outperforms existing methodologies, particularly in terms of visuality and parameter-wise measurement.

Novel fuzzy type-II driven modified Anisotropic Diffusion filter framework for restoration and enhancement of Rician noise corrupted MR images

Novel fuzzy type-II driven modified Anisotropic Diffusion filter framework for restoration and enhancement of Rician noise corrupted MR images

On-machine correction of form error for structured surfaces with anisotropic diffusion filter

Structured surfaces with high aspect ratio are promising in optical components, healthcare devices, and microelectronics. A preferable method to create precise structured surfaces is using single point diamond turning with on-machine surface measurement (OMSM). However, fabricating these surfaces often pose challenges due to steep gradients and discontinuous slopes, leading to significant form errors in machining. We propose an innovative solution by employing partial differential equation (PDE) filtration in a closed loop compensation process to enhance form accuracy and surface roughness compared to traditional methods. We tackle the problem of over-smoothing induced profile error encountered with traditional Gaussian filters. The proposed compensation strategy adapts to surface curvature and reduces instrument noise during on-machine measurements. Experimental of fabricating a segment spherical artefact, demonstrate improved precision. After adopting the proposed method, the form error is reduced from 1.2 µm to 0.5 µm and vibration ripples are mitigated, and a better surface finish is achieved.

Study on Reservoir Characteristics and 3D Spatial Carving of Fault Solution Reservoirs Based on Geophysical Methods.

At present, research studies on the description of fracture characterization elements in fault solution reservoirs are relatively limited, and further research is needed on contour recognition and characterization methods. In this paper, first, the regional fault system is investigated and the faults are finely identified and characterized. Second, the volume of contour-sensitive attributes of the fault solver is optimized using tensor attributes, amplitude variation, discontinuity detection, and other attributes. Finally, a comprehensive evaluation of the fault solution reservoir is carried out by combining the dynamic production characteristics. Results show that (a) the interior details of fractured reservoirs can be mainly divided into two categories: cave-type reservoirs and fracture-pore-type reservoirs. (b) Fractured and porous reservoirs mainly utilize discontinuous properties and combine well data to calibrate and determine threshold values, ultimately achieving the characterization of interior details of fractured solution bodies. (c) After anisotropic diffusion filtering and fault enhancement, the seismic data was subjected to amplitude gradient disorder detection attribute calculation for multiscale fractures.

Brain tumor X-ray images enhancement and classification using anisotropic diffusion filter and transfer learning models

Brain tumor X-ray images enhancement and classification using anisotropic diffusion filter and transfer learning models

Scale-Aware Edge-Preserving Full Waveform Inversion with Diffusion Filter for Crosshole Sensor Arrays.

Full waveform inversion (FWI) is recognized as a leading data-fitting methodology, leveraging the detailed information contained in physical waveform data to construct accurate, high-resolution velocity models essential for crosshole surveys. Despite its effectiveness, FWI is often challenged by its sensitivity to data quality and inherent nonlinearity, which can lead to instability and the inadvertent incorporation of noise and extraneous data into inversion models. To address these challenges, we introduce the scale-aware edge-preserving FWI (SAEP-FWI) technique, which integrates a cutting-edge nonlinear anisotropic hybrid diffusion (NAHD) filter within the gradient computation process. This innovative filter effectively reduces noise while simultaneously enhancing critical small-scale structures and edges, significantly improving the fidelity and convergence of the FWI inversion results. The application of SAEP-FWI across a variety of experimental and authentic crosshole datasets clearly demonstrates its effectiveness in suppressing noise and preserving key scale-aware and edge-delineating features, ultimately leading to clear inversion outcomes. Comparative analyses with other FWI methods highlight the performance of our technique, showcasing its ability to produce images of notably higher quality. This improvement offers a robust solution that enhances the accuracy of subsurface imaging.

Deep learning with adaptive convolutions for classification of retinal diseases via optical coherence tomography

Optical coherence tomography (OCT) uses interferometry to capture high-resolution cross-sectional images of the retina to diagnose retinal diseases. Convolutional neural networks (CNNs) have become essential for developing efficient computer-aided diagnostic algorithms, but noisy images can hinder their performance. This study introduces an innovative image preprocessing strategy that involves a new method of representing images to reduce image noise and a new adaptive convolution layer. The adaptive convolution layer aims to replace traditional convolution layers for OCT image classification by relying on local’Feature Content’. The proposed image representation is based on Zeckendorf's theorem, which states that every positive integer may be split into a unique sum of distinct, non-adjacent Fibonacci numbers. The proposed approach enables the generation of two separate images, known as the ‘base’ and ‘fine,’ where the ‘base’ image is the denoised image. We assessed our methodology by evaluating against ten filters, comprising a Low-pass filter, Gaussian filter, Wiener filter, Wavelet filter, Guided filter, Lee filter, Frost filter, Kuan filter, Detail Preserving Anisotropic Diffusion (DPAD) filter, and Non-Local Means (NLM) filter. In our study, we found that the proposed filter produced the most favorable results in five of the six no-reference parameters (Blur Percent (BP), Blind/Referenceless Image Spatial Quality Evaluator (BRISQUE), Naturalness Image Quality Evaluator (NIQE), Wavelet Variance (WAVV), Wavelet Variance Radial (WAVR)) used to assess the effectiveness of the proposed image enhancement technique. The OCT dataset utilized in the study was compiled by the University of California San Diego. The proposed adaptive convolution layer and its accompanying activation function were tested using seven OCT image classification CNN architectures. The test architectures comprise OctNET, NT-CNN, AOCT-NET, M-CNN, LightOCT, RetiNet, and DeepOCT. Experiments were conducted to assess the impact of the new preprocessing algorithm and the placement of the adaptive convolution layer as a substitute for the conventional convolution layer. Implementing the proposed approaches resulted in accuracy improvements ranging from 0.44% to 2.44% across architectures. Our findings highlight the efficacy of the proposed indirect noise reduction technique and a texture-sensitive adaptive convolution layer.

Automated diagnosis of acute cerebral ischemic stroke lesions from diffusion-weighted magnetic resonance images in assessment with modified Rankin Scale

Purpose: Automated diagnosis of acute cerebral ischemic stroke lesions (ACISL) is an evolving science. Early detection and exact delineation of ACISL automatically from diffusion-weighted magnetic resonance (DWMR) images are crucial for initiating prompt treatment. Thus, this work aims to determine the appropriate slice out of 60 pieces using multi-fractal analysis (MFA) and to segment the lesions in DWMR images using a hybrid optimization method. Features extracted from the segmented images were clinically correlated with the modified Rankin Scale (mRS). Methods: Thirty-one real-time stroke patients’ images were collected from Rajiv Gandhi Government General Hospital, Chennai, India. Multiple MRI slices were taken from each patient and filtered using an anisotropic diffusion filter (ADF). These filtered images were skull-stripped automatically by the maximum entropy thresholding technique incorporating mathematical morphological operations (MEM). The multi-fractal analysis (MFA) identifies the prominent slice with the significant infarct lesion. An isodata algorithm that integrated differential evolution with the particle swarm optimization method based on Kapur’s (IDPK) and Otsu’s (IDPO) approaches was attempted to segment the ACISL. Finally, the geometric and moment features extracted from the segmented lesions categorized the stroke severity and were correlated with the mRS. Results: The findings of the experimental work confirm that the suggested IDPK approach achieved usual normalized values for image similarity indices such as Sokal-Michener Coefficient (98.51%), Roger-Tanimoto Coefficient (90.16%), Sokel-Sneath-2 (91.04%), and Sorenson Index (90.04%) are superior to IDPO. Statistical significance proved that the segmented lesions’ area (r = 0.820, p < 0.0001) and perimeter (r = 0.928, p < 0.0001) were strongly correlated with the mild and moderate criteria of mRS. Conclusion: The proposed work effectively detected ischemic stroke lesions and their severity within the studied image groups. It could be a promising and potential tool to aid radiologists in validating their diagnosis.

Automatic 3D coronary artery segmentation based on local region active contour model.

Segmentation of coronary arteries in computed tomography angiography (CTA) images plays a key role in the diagnosis and treatment of coronary-related diseases. However, manually analyzing the large amount of data is time-consuming, and interpreting this data requires the prior knowledge and expertise of radiologists. Therefore, an automatic method is needed to separate coronary arteries from a given CTA dataset. Firstly, an anisotropic diffusion filter was employed to smooth the noise while preserving the vessel boundaries. The coronary skeleton was then extracted using a two-step process based on the intensity of the coronary. In the first step, the thick vessel skeleton was extracted by clustering, improved vesselness filtering and region growing, while in the second step, the thin vessel skeleton was extracted by the height ridge traversal method guided by the cylindrical model. Next, the vesselness measure, representing vessel a priori information, was incorporated into the local region active contour model based on the vessel geometry. Finally, the initial contour of the active contour model was generated using the coronary artery skeleton for effective segmentation of the three-dimensional (3D) coronary arteries. Experimental results on chest CTA images show that the method is able to segment coronary arteries effectively with an average precision, recall and dice similarity coefficient (DSC) of 86.64%, 91.26% and 79.13%, respectively, and has a good performance in thin vessel extraction. The method does not require manual selection of vessel seeds or setting of initial contours, and allows for the extraction of a successful coronary artery skeleton and eventual effective segmentation of the coronary arteries.

Enhanced lung cancer detection: Integrating improved random walker segmentation with artificial neural network and random forest classifier

BackgroundMedical image segmentation is a vital yet difficult job because of the multimodality of the acquired images. It is difficult to locate the polluted area before it spreads. MethodsThis research makes use of several machine learning tools, including an artificial neural network as well as a random forest classifier, to increase the system's reliability of pulmonary nodule classification. Anisotropic diffusion filtering is initially used to remove noise from a picture. After that, a modified random walk method is used to get the region of interest inside the lung parenchyma. Finally, the features corresponding to the consistency of the picture segments are extracted using texture-based feature extraction for pulmonary nodules. The final stage is to identify and classify the pulmonary nodules using a classifier algorithm. ResultsThe studies employ cross-validation to demonstrate the validity of the diagnosis framework. In this instance, the proposed method is tested using CT scan information provided by the Lung Image Database Consortium. A random forest classifier showed 99.6 percent accuracy rate for detecting lung cancer, compared to a artificial neural network's 94.8 percent accuracy rate. ConclusionsDue to this, current research is now primarily concerned with identifying lung nodules and classifying them as benign or malignant. The diagnostic potential of machine learning as well as image processing approaches are enormous for the categorization of lung cancer.

Thermal fault diagnosis of complex electrical equipment based on infrared image recognition

This paper realizes infrared image denoising, recognition, and semantic segmentation for complex electrical equipment and proposes a thermal fault diagnosis method that incorporates temperature differences. We introduce a deformable convolution module into the Denoising Convolutional Neural Network (DeDn-CNN) and propose an image denoising algorithm based on this improved network. By replacing Gaussian wrap-around filtering with anisotropic diffusion filtering, we suggest an image enhancement algorithm that employs Weighted Guided Filtering (WGF) with an enhanced Single-Scale Retinex (Ani-SSR) technique to prevent strong edge halos. Furthermore, we propose a refined detection algorithm for electrical equipment that builds upon an improved RetinaNet. This algorithm incorporates a rotating rectangular frame and an attention module, addressing the challenge of precise detection in scenarios where electrical equipment is densely arranged or tilted. We also introduce a thermal fault diagnosis approach that combines temperature differences with DeeplabV3 + semantic segmentation. The improved RetinaNet's recognition results are fed into the DeeplabV3 + model to further segment structures prone to thermal faults. The accuracy of component recognition in this paper achieved 87.23%, 86.54%, and 90.91%, with respective false alarm rates of 7.50%, 8.20%, and 7.89%. We propose a comprehensive method spanning from preprocessing through target recognition to thermal fault diagnosis for infrared images of complex electrical equipment, providing practical insights and robust solutions for future automation of electrical equipment inspections.

Residual U-Net approach for thyroid nodule detection and classification from thyroid ultrasound images

With so many thyroid knobs (nodules) discovered by accident, it is critical to recognize as many aberrant knobs (nodules) as possible from fine-needle aspiration (FNA) biopsies or other medical procedures while excluding those that are virtually certainly benign. Thyroid ultrasonography, on the other hand, is prone to interobserver variability and subjective translations. An effective deep learning model for segmenting and categorizing thyroid nodules in this study follows the stages below: data collection from a well-known archive, The Thyroid Digital Image Database (TDID), which comprises ultrasound pictures from 298 patients, preprocessing using anisotropic diffusion filter (ADF) for removing noise and enhancing the images, segmentation using a bilateral filter for segmenting images, feature extraction using grey level occurrence matrix (GLCM), feature selection using Multi-objective Particle Swarm with Random Forest Optimization (MbPSRA) and finally classification happens were Residual U-Net will be used. Experiment evaluation states the proposed model outperforms well than other state-of-art models.

Fusion of Multimodal Medical Images Based on Fine-Grained Saliency and Anisotropic Diffusion Filter.

A clinical medical image provides vital information about a person's health and bodily condition. Typically, doctors monitor and examine several types of medical images individually to gather supplementary information for illness diagnosis and treatment. As it is arduous to analyze and diagnose from a single image, multi-modality images have been shown to enhance the precision of diagnosis and evaluation of medical conditions. Several conventional image fusion techniques strengthen the consistency of the information by combining varied image observations; nevertheless, the drawback of these techniques in retaining all crucial elements of the original images can have a negative impact on the accuracy of clinical diagnoses. This research develops an improved image fusion technique based on fine-grained saliency and an anisotropic diffusion filter to preserve structural and detailed information of the individual image. In contrast to prior efforts, the saliency method is not executed using a pyramidal decomposition, but rather an integral image on the original scale is used to obtain features of superior quality. Furthermore, an anisotropic diffusion filter is utilized for the decomposition of the original source images into a base layer and a detail layer. The proposed algorithm's performance is then contrasted to those of cutting-edge image fusion algorithms. The proposed approach cannot only cope with the fusion of medical images well, both subjectively and objectively, according to the results obtained, but also has high computational efficiency. Furthermore, it provides a roadmap for the direction of future research.

Atelectasis detection in chest X-ray images using convolutional neural networks and transfer learning with anisotropic diffusion filter

Atelectasis is the loss of volume caused by decreasing gas in a specific area of the lung. It occurs when the lung sacs (alveoli) do not fully inflate, resulting in a lack of oxygen to the blood, tissues, organs, and fill with alveolar fluid. It can be caused by pressure outside of your lung, an obstruction, poor airflow, or scarring. It is critical to diagnose this lung condition as soon as possible. Chest X-rays are the most commonly utilized diagnostic tool for this condition. Examining chest X-rays, however, is difficult even for a professional radiologist. There is a need to improve diagnosis accuracy. As a result, this study proposes a novel detection and classification approach for rapid diagnosis of atelectasis utilizing patient chest X-ray data. To diagnose atelectasis from chest X-ray images, we used state-of-the-art models like VGG19, Inception, and a deep learning method (CNN). This study presents an effective method for categorizing chest X-ray images as normal or atelectasis-infected. This study offers a convolutional neural network (CNN) method to aid medical experts in identifying atelectasis disease. The anisotropic diffusion filtering (ADF) approach was used to improve image edge preservation, reduce noise, and contrast limited adaptive histogram equalization (CLAHE) for improving the contrast of low-intensity images. After evaluating the CNN model, it achieved 99.88 % training accuracy, 99 % validation accuracy, and 99 % test accuracy. In this study, CNN achieved a result that outperformed state-of-the-art models (VGG19 and Inception). As a result of the findings, deep features provided consistent and reliable features for detecting atelectasis. Therefore, the suggested method expedites atelectasis diagnosis and radiologists' screening of atelectasis patients.

Coherence-enhancing anisotropic diffusion filter for 3D high-resolution reconstruction of P-wave velocity and density using full-waveform inversion: Application to a North Sea ocean bottom cable data set

Regularization is a central topic in the study of the solutions of ill-posed inverse problems. High-resolution seismic imaging using full-waveform inversion (FWI) belongs to this category of problems. Regularization through anisotropic diffusion, a technique that emerged in the field of image processing, is an interesting alternative to conventional regularization strategies. Exploiting the structural information of a given image, it has the capability to smooth this image along its main structures. The main difficulty is how to design the anisotropic diffusion operator. The concept of coherence enhancing proposed in 2D is extended in 3D and applied so as to filter and enhance the structural coherence of the model updates within an FWI algorithm. The benefits of this strategy are investigated on a 2D synthetic experiment before considering the multiparameter inversion of a 3D field data set from the North Sea up to 10 Hz. From this data, the vertical velocity and the density are simultaneously reconstructed. Compared with a conventional nonstationary Gaussian regularization strategy, the models obtained using the coherence-enhancing anisotropic diffusion strategy indicate an enhanced resolution, especially for the density model. The high-resolution reflectivity image computed from the impedance volume clearly illustrates the benefit this filtering approach can deliver in terms of structural interpretation.

Anisotropic diffusion filter based fusion of NSST transformed medical images

In this paper, an image fusion method is proposed for the fusion of MR and CT images to obtain high contrast fused image that contains complementary information from both the input images. Proposed method uses NSST based fusion method to fuse the information from the two input images, whereas to enhance the edge information and to increase the contrast in the fused image, anisotropic diffusion based fusion method is used and its result is added to the NSST based fusion method. Proposed method is analyzed and compared with five state-of-the-art fusion methods in terms of both visual perception and objective assessment. Minimum percentage improvement of the proposed method over the five state-of-the-art methods are 5.99%, 129.84%, 7.48%, 7.52%, and 5.25% respectively, whereas maximum percentage improvement of the proposed method over the five state-of-the-art methods are 18.51%, 196.52%, 29.64%, 26.35%, and 16.05% respectively.

An underwater image enhancement by reducing speckle noise using modified anisotropic diffusion filter

Underwater images are usually suffering from the issues of quality degradation, such as low contrast due to blurring details, color deviations, non-uniform lighting, and noise. Since last few decades, many researches are undergoing for restoration and enhancement for degraded underwater images. In this paper, we proposed a novel algorithm using modified anisotropic diffusion filter with dynamic color balancing strategy. This proposed algorithm performs based on an employing effective noise reduction as well as edge preserving technique with dynamic color correction to make uniform lighting and minimize the speckle noise. Furthermore, reanalyze the contributions and limitations of existing underwater image restoration and enhancement methods. Finally, in this research provided the detailed objective evaluations and compared with the various underwater scenarios for above said challenges also made subjective studies, which shows that our proposed method will improve the quality of the image and significantly enhanced the image.

An Early Detection and Classification of Alzheimer's Disease Framework Based on ResNet-50.

The objective of this study is to develop a more effective early detection system for Alzheimer's disease (AD) using a Deep Residual Network (ResNet) model by addressing the issue of convolutional layers in conventional Convolutional Neural Networks (CNN) and applying image preprocessing techniques. The proposed method involves using Contrast Limited Adaptive Histogram Equalizer (CLAHE) and Boosted Anisotropic Diffusion Filters (BADF) for equalization and noise removal and K-means clustering for segmentation. A ResNet-50 model with shortcut links between three residual layers is proposed to extract features more efficiently. ResNet-50 is preferred over other ResNet types due to its intermediate depth, striking a balance between computational efficiency and improved performance, making it a widely adopted and effective architecture for various computer vision tasks. While other ResNet variations may offer higher depths, they are more prone to overfitting and computational complexity, which can hinder their practical application. The proposed method is evaluated on a dataset of MRI scans of AD patients. The proposed method achieved high accuracy and minimum losses of 95% and 0.12, respectively. While some models showed better accuracy, they were prone to overfitting. In contrast, the suggested framework, based on the ResNet-50 model, demonstrated superior performance in terms of various performance metrics, providing a robust and reliable approach to Alzheimer's disease categorization. The proposed ResNet-50 model with shortcut links between three residual layers, combined with image preprocessing techniques, provides an effective early detection system for AD. The study demonstrates the potential of deep learning and image processing techniques in developing accurate and efficient diagnostic tools for AD. The proposed method improves the existing approaches to AD classification and provides a promising framework for future research in this area.