Non-local Means Research Articles

Denoised Non-Local Means with BDDU-Net Architecture for Robust Retinal Blood Vessel Segmentation

Retinal blood vessels can be obtained by image segmentation. This study proposes combining image enhancement and segmentation to obtain retinal blood vessels. The image enhancement stages use CLAHE and Denoised Non-Local Means to increase contrast and reduce noise on the original image, and Bottom-Hat (BTH) filtering is used to lighten dark features in the image so the features become lighter and darken the bright features in the image. Bottom Hat is applied to make the features of the blood vessels in the retinal image more visible. The segmentation architecture proposes BDDU-Net architecture which combines U-Net in the encoder part, DenseNet in the bridge part, and Bi-ConvLSTM in the decoder part. Image enhancement performance results are PSNR and SSIM. The PSNR is more than 40 dB on both the DRIVE and STARE datasets. The SSIM results are close to 1 on the DRIVE and STARE datasets. These results show that the image enhancement stages in the proposed method can enhance the quality of the original image. The segmentation performance results of BDDU-Net architecture are measured based on accuracy, sensitivity, specificity, IoU, and F1-Score. The DRIVE dataset obtained 95.578% for accuracy, 85.75% for sensitivity, 96.75% for specificity, 67.407% for IoU, and 80.53% for F1-Score. The STARE dataset obtained 97.63% for accuracy, 84.33% for sensitivity, 98.66% for specificity, 75.67% for IoU, and 86.15% for F1-Score. Based on the image enhancement and image segmentation results, these results show that the proposed method is great for enhancing image quality and excellent for blood vessel segmentation in retinal images, although IoU results on the DRIVE dataset need to be improved.

Non-Local Means Hole Repair Algorithm Based on Adaptive Block

RGB-D cameras provide depth and color information and are widely used in 3D reconstruction and computer vision. In the majority of existing RGB-D cameras, a considerable portion of depth values is often lost due to severe occlusion or limited camera coverage, thereby adversely impacting the precise localization and three-dimensional reconstruction of objects. In this paper, to address the issue of poor-quality in-depth images captured by RGB-D cameras, a depth image hole repair algorithm based on non-local means is proposed first, leveraging the structural similarities between grayscale and depth images. Second, while considering the cumbersome parameter tuning associated with the non-local means hole repair method for determining the size of structural blocks for depth image hole repair, an intelligent block factor is introduced, which automatically determines the optimal search and repair block sizes for various hole sizes, resulting in the development of an adaptive block-based non-local means algorithm for repairing depth image holes. Furthermore, the proposed algorithm’s performance are evaluated using both the Middlebury stereo matching dataset and a self-constructed RGB-D dataset, with performance assessment being carried out by comparing the algorithm against other methods using five metrics: RMSE, SSIM, PSNR, DE, and ALME. Finally, experimental results unequivocally demonstrate the innovative resolution of the parameter tuning complexity inherent in-depth image hole repair, effectively filling the holes, suppressing noise within depth images, enhancing image quality, and achieving elevated precision and accuracy, as affirmed by the attained results.

Image Segmentation Analysis Using Otsu Thresholding and Mean Denoising for the Identification Coffee Plant Diseases

In Indonesia, coffee is one of the plantation products with a relatively high level of productivity and is a source of foreign exchange income for the country. However, unfortunately, certain factors can threaten productivity and quality in cultivating coffee plants, one of which is rust leaf disease. This disease causes disturbances in photosynthesis, thereby reducing plant yields. Therefore, to maintain and control productivity in coffee cultivation, this research carried out the process of observing coffee leaf images through segmentation using the Otsu Thresholding and Mean Denoising methods. The entire series of processes in this research was carried out using the Python programming language and succeeded in providing output in the form of image comparisons showing areas affected by Rust Leaf disease using the Otsu thresholding method alone and the Otsu thresholding method combined with a non-local means denoising algorithm. The test results prove that the Otsu thresholding method with the non-local means denoising algorithm has a smaller MSE value. It is the most optimal method for handling coffee leaf disease image segmentation with an accuracy level of 88%. It is hoped that this research can support farmers in providing insight into early detection of coffee plant diseases and increasing productivity through visual analysis.

Effective processing pipeline PACE 2.0 for enhancing chest x-ray contrast and diagnostic interpretability

Preprocessing is an essential task for the correct analysis of digital medical images. In particular, X-ray imaging might contain artifacts, low contrast, diffractions or intensity inhomogeneities. Recently, we have developed a procedure named PACE that is able to improve chest X-ray (CXR) images including the enforcement of clinical evaluation of pneumonia originated by COVID-19. At the clinical benchmark state of this tool, there have been found some peculiar conditions causing a reduction of details over large bright regions (as in ground-glass opacities and in pleural effusions in bedridden patients) and resulting in oversaturated areas. Here, we have significantly improved the overall performance of the original approach including the results in those specific cases by developing PACE2.0. It combines 2D image decomposition, non-local means denoising, gamma correction, and recursive algorithms to improve image quality. The tool has been evaluated using three metrics: contrast improvement index, information entropy, and effective measure of enhancement, resulting in an average increase of 35% in CII, 7.5% in ENT, 95.6% in EME and 13% in BRISQUE against original radiographies. Additionally, the enhanced images were fed to a pre-trained DenseNet-121 model for transfer learning, resulting in an increase in classification accuracy from 80 to 94% and recall from 89 to 97%, respectively. These improvements led to a potential enhancement of the interpretability of lesion detection in CXRs. PACE2.0 has the potential to become a valuable tool for clinical decision support and could help healthcare professionals detect pneumonia more accurately.

Optimization Method to Predict Optimal Noise Reduction Parameters for the Non-Local Means Algorithm Based on the Scintillator Thickness in Radiography.

The resulting image obtained from an X-ray imaging system depends significantly on the characteristics of the detector. In particular, when an X-ray image is acquired by thinning the detector, a relatively large amount of noise inevitably occurs. In addition, when a thick detector is used to reduce noise in X-ray images, blurring increases and the ability to distinguish target areas deteriorates. In this study, we aimed to derive the optimal X-ray image quality by deriving the optimal noise reduction parameters based on the non-local means (NLM) algorithm. The detectors used were of two thicknesses (96 and 140 μm), and images were acquired based on the IEC 62220-1-1:2015 RQA-5 protocol. The optimal parameters were derived by calculating the edge preservation index and signal-to-noise ratio according to the sigma value of the NLM algorithm. As a result, a sigma value of the optimized NLM algorithm (0.01) was derived, and this algorithm was applied to a relatively thin X-ray detector system to obtain appropriate noise level and spatial resolution data. The no-reference-based blind/referenceless image spatial quality evaluator value, which analyzes the overall image quality, was best when using the proposed method. In conclusion, we propose an optimized NLM algorithm based on a new method that can overcome the noise amplification problem in thin X-ray detector systems and is expected to be applied in various photon imaging fields in the future.

A Complete Strategy to Achieve High Precision Automatic Segmentation of Challenging Experimental X‐Ray Computed Tomography Data Using Low‐Resemblance Synthetic Training Data

It is shown that preconditioning of experimental X‐ray computed tomography (XCT) data is critical to achieve high‐precision segmentation scores. The challenging experimental XCT datasets and deep convolutional neural networks (DCNNs) are used that are trained with low‐resemblance synthetic XCT data. The material used is a 6‐phase Al–Si metal matrix composite‐reinforced with ceramic fibers and particles. To achieve generalization, in our past studies, specific data augmentation techniques were proposed for the synthetic XCT training data. In addition, two toolsets are devised: (1) special 3D DCNN architecture (3D Triple_UNet), slicing the experimental XCT data from multiple views (MultiView Forwarding), the i.S.Sy.Da.T.A. iterative segmentation algorithm, and (2) nonlocal means (NLM) conditioning (filtering) for the experimental XCT data. This results in good segmentation Dice scores across all phases compared to more standard approaches (i.e., standard UNet architecture, single view slicing, standard single training, and NLM conditioning). Herein, the NLM filter is replaced with the deep conditioning framework BAM SynthCOND introduced in a previous publication, which can be trained with synthetic XCT data. This leads to a significant segmentation precision increase for all phases. The proposed methods are potentially applicable to other materials and imaging techniques.

A novel chaotic weighted EHO-based methodology for retinal vessel segmentation

ABSTRACT Retinal image segmentation process deals withproblems like spurious vascularisation and thin vessel detection. In thispaper, a three-step methodology has been proposed for retinal vesselsegmentation. In first step, RGB to YIQ conversion is performed. In second step, Y component enhancement is performed. A novel Chaotic weighted Elephant HerdingOptimization (CWEHO) has been proposed to optimize the clip limit and blocksize values of Contrast Limited Adaptive Histogram Equalization (CLAHE). CWEHO-based CLAHE along with morphological operations, non-local means filter, and median filter is applied to enhanceretinal images. In third step, thin and thick vessel segmentation is performed.Top hat transformation, otsu thresholding algorithm, and vessel point selectionare applied for thick vessel extraction. The first-order Gaussian derivative in conjunction with the matchfilter is used to extract thin vessels. DRIVE and HRF datasets are used toassess the effectiveness of proposed methodology. The average values ofsegmentation accuracy, specificity, sensitivity, and Mathew CorrelationCoefficient (MCC) are observed to be 0.9650, 0.9895, 0.7007, 0.7650,respectively, for observer1 and 0.9696, 0.9912, 0.7390, 0.7901 for observer2using DRIVE dataset. Similarly, 0.9592, 0.9839, 0.6850, and 0.7116,respectively, metrics for HRF dataset. Compared to state-of-the-art methods, the proposed segmentation methodology providesbetter results .

Application of non-local mean image denoising algorithm based on machine learning technology in visual communication design

In Visual Communication Design (VCD), noise data is easy to appear, which reduces image quality and affects the effect of VCD. The non local mean image denoising algorithm is a good filtering denoising algorithm, but there are still issues of information interference and missing. To improve the performance of noise recognition and image denoising technology, this study proposes a non local mean image denoising algorithm based on machine learning technology. The whale optimization algorithm, as a machine learning technique, has good performance in seeking optimal solutions. Therefore, it is applied to optimize the filtering parameters of non local mean image denoising algorithms to improve the perforGAmance of non local mean image denoising algorithms. To address the shortcomings of the whale optimization algorithm, BP neural network is introduced for optimization. Finally, the experiment uses the improved particle swarm optimization algorithm to optimize the BPNN and applies it to the recognition and classification of noise data. Combining the above contents, the IBINLM image denoising algorithm is constructed experimentally. It is verified that the IPSO-BPNN model’s loss value is 0.12; The recognition accuracy of the model for noise pixels is 98.64%; F1 value reaches 96.32%; The fitting degree reaches 0.983. The PSNR of IBINLM algorithm is 35.86 dB; MSE is 0.29; AUC value reaches 0.903. The results show that the IPSO-BPNN model and IBINLM image denoising algorithm have better performance compared to other models, which can improve the quality of visual communication works, playing an essential role in image transmission and storage in visual communication design.

On the reduction of mixed Gaussian and impulsive noise in heavily corrupted color images

In this paper, a novel approach to the mixed Gaussian and impulsive noise reduction in color images is proposed. The described denoising framework is based on the Non-Local Means (NLM) technique, which proved to efficiently suppress only the Gaussian noise. To circumvent the incapacity of the NLM filter to cope with impulsive distortions, a robust similarity measure between image patches, which is insensitive to the impact of impulsive corruption, was elaborated. To increase the effectiveness of the proposed approach, the blockwise NLM implementation was applied. However, instead of generating a stack of output images that are finally averaged, an aggregation strategy combining all weights assigned to pixels from the processing block was developed and proved to be more efficient. Based on the results of comparisons with the existing denoising schemes, it can be concluded that the novel filter yields satisfactory results when suppressing high-intensity mixed noise in color images. Using the proposed filter the image edges are well preserved and the details are retained, while impulsive noise is efficiently removed. Additionally, the computational burden is not significantly increased, compared with the classic NLM, which makes the proposed modification applicative for practical image denoising tasks.

Tiling and PCA Strategy for Clustering-Based High-Dimensional Gaussian Filtering

Edge-preserving filtering is an essential tool for image processing applications and has various types of filtering. High-dimensional Gaussian filtering (HDGF) supports a wide range of edge-preserving filtering. This paper approximates HDGF by clustering with Nyström approximation, tiling, and principal component analysis (PCA) to accelerate HDGF. Also, we compare it with the conventional HDGF approximations and clarify its effective range. We accelerate HDGF by clustering-based constant-time algorithm, which has O(K) order for convolution, where K is the number of clusters. First, we perform PCA for dimensionality reduction and then cluster signals with k-means++. HDGF is decomposed to Gaussian filtering by approximate eigenvalue decomposition of Nyström approximation using the clusters. The Gaussian filtering is performed in a constant-time algorithm. The process is further accelerated by the tiling strategy cooperating with PCA. In our experimental results, we compared three approximated HDGFs: clustering-based HDGF, permutohedral lattice, and Gaussian KD-tree. Also, we evaluated six types of high dimensional signals: RGB, RGB-IR, RGB-D, flash/no-flash, hyperspectral image, and non-local means. The proposed clustering-based HDGF was effective for low/middle-dimensional cases: RGB, RGB-IR, RGB-D, flash/no-flash, and hyperspectral images. Also, tiling with PCA strategy is effective for the conventional permutohedral lattice and Gaussian KD-tree. In the approximation of HDGF, the clustering-based HDGF is the better solution for low/middle-dimensional signals. For the higher-dimensional case of non-local means filtering, the conventional HDGF of the permutohedral lattice with the proposed PCA tiling is effective. Our code and dataset are available at https://norishigefukushima.github.io/TilingPCA4CHDGF/.

Multi-threshold Image Segmentation based on an improved Salp Swarm Algorithm: Case study of breast cancer pathology images

Breast cancer poses a significant risk to women’s health, and it is essential to provide proper diagnostic support. Medical image processing technology is a key component of all supporting diagnostic techniques, with Image Segmentation (IS) being one of its primary steps. Among various methods, Multilevel Image Segmentation (MIS) is considered one of the most effective and straightforward approaches. Many researchers have attempted to improve the quality of image segmentation by combining different metaheuristic algorithms with MIS. However, these methods often suffer from issues such as low convergence accuracy and a proclivity for converging towards Local Optima (LO). To overcome these challenges, this study introduces an integrated approach that combines the Salp Swarm Algorithm (SSA), Slime Mould Algorithm (SMA) and Differential Evolution (DE) algorithm. In this manuscript, we introduce an innovative hybrid MIS model termed SDSSA, which leverages elements from the SSA, SMA and DE algorithms. The SDSSA model fundamentally relies on non-local means 2D histogram and 2D Kapur’s entropy. To evaluate the proposed method effectively, we compare it initially with similar algorithms using the IEEE CEC2014 benchmark functions. The SDSSA showcases enhanced convergence velocity and precision relative to similar algorithms. Furthermore, this paper proposes an excellent MIS method. Subsequently, IS experiments were conducted separately at both low and high threshold levels. The test results demonstrate that the segmentation outcomes of MIS, at both low and high threshold levels, outperform other methods. This validates SDSSA as a superior segmentation technique that provides practical assistance for future research in breast cancer pathology image processing.

Use MOOC to learn image denoising techniques

This article focuses on using MOOCs to learn image denoising techniques. It begins with an introduction to the concept of MOOCs - these innovative online learning platforms that offer a wide range of courses across disciplines, providing convenient and affordable learning opportunities for a global audience. It then explains the characteristics of MOOC's wide coverage, high flexibility, and different from traditional education models. It then introduces the advantages of MOOCs: accessibility and inclusiveness (open to anyone with an Internet connection), cost-effectiveness (a cost-effective alternative, many courses available for free), flexibility and self-paced learning (the ability to learn at your own pace), a diverse curriculum and global expertise. Then the concept of image denoising is introduced - image denoising is a basic process of digital image processing, and the common denoising methods are described: filter method and the applicable range of various filters, the advantages and disadvantages of wavelet change, the advantages of deep learning method and the principle of non-local mean denoising technology. It then describes how MOOCs can help learn image denoising: integrating course content, getting expert guidance, hands-on exercises and projects, and community and peer communication. In addition, it introduces the challenges encountered by MOOCs: high dropout rate, quality and credibility of MOOCs, lack of interaction and humanization in traditional classrooms, accessibility. The relationship between E-learning and MOOC is also introduced – E-learning and MOOC play complementary roles in modern education. MOOC provide a structured, flexible, cost-effective environment and a transformative educational experience for learning about biological image denoising.

Chickpea disease classification using hybrid method

Chickpea is one of the most important legumes in the world, however, it is prone to various diseases that can significantly reduce its yield and quality. Hence, the accurate classification of these diseases are crucial for effective disease management. In this study, we propose a combined approach for chickpea disease classification using GLCM-Color Histogram features with Bilateral filtering and non-local means filtering. Our research comprises three phases: image preprocessing, feature extraction, and classification. To enhance the model's robustness and reduce noise, we applied Bilateral filtering, non-local means filtering, and data augmentation techniques. We utilized a combination of gray-level co-occurrence matrix (GLCM) and Color Histogram for feature extraction, which can capture the texture and color features important for image classification tasks. The extracted features were then classified using Multi-Layer Perceptrons (MLPs), Support Vector Machine (SVM), K-Nearest Neighbors (KNN), and Random Forest (RF). The experimental results indicate that the combined features extracted using GLCM and Color Histogram with the SVM classifier outperformed individual feature extractors and classifiers, achieving a testing accuracy of 95.49 %. Our study demonstrates that proper image preprocessing, data augmentation, and feature extraction provide an efficient classification method for identifying and classifying chickpea disease.

Multiplane HiLo microscopy with speckle illumination and non-local means denoising.

HiLo microscopy synthesizes an optically sectioned image from two images, one obtained with uniform and another with patterned illumination, such as laser speckle. Speckle-based HiLo has the advantage of being robust to aberrations but is susceptible to residual speckle noise that is difficult to control. We present a computational method to reduce this residual noise without undermining resolution. In addition, we improve the versatility of HiLo microscopy by enabling simultaneous multiplane imaging (here nine planes). Our goal is to perform fast, high-contrast, multiplane imaging with a conventional camera-based fluorescence microscope. Multiplane HiLo imaging is achieved with the use of a single camera and z-splitter prism. Speckle noise reduction is based on the application of a non-local means (NLM) denoising method to perform ensemble averaging of speckle grains. We demonstrate the capabilities of multiplane HiLo with NLM denoising both with synthesized data and by imaging cardiac and brain activity in zebrafish larvae at 40Hz frame rates. Multiplane HiLo microscopy aided by NLM denoising provides a simple tool for fast optically sectioned volumetric imaging that can be of general utility for fluorescence imaging applications.

Color Remote Sensing Image Restoration through Singular-Spectra-Derived Self-Similarity Metrics

Color remote sensing images have key features of pronounced internal similarity characterized by numerous repetitive local patterns, so the capacity to effectively harness these self-similarity features plays a key role in the enhancement of color images. The main novelty of this study lies in that we utilized an unusual technique (singular spectrum) to derive brand-new similarity metrics inside the quaternion representation of color images and then incorporated these metrics into denoising algorithms. Color image denoising experiments demonstrated that compared with seven mainstream image restoration algorithms (homomorphic filtering (HPF), wavelet transforms (WT), non-local means (NLM), non-local total variation (NLTV), the color adaptation of non-local means (NLMC), quaternion Euclidean metric (QNLM), and quaternion Euclidean metric total variation (QNLTV)), our algorithms with two novel self-similarity metrics achieved maximum peak signal-to-noise ratio (PSNR), structural similarity index (SSIM), average gradient (AG), and information entropy index (IE) values, with average increases of 1.98 dB /2.12 dB, 0.1168/0.1244, 1.824/1.897, and 0.158/0.135. Moreover, for a complex, mixed-noise scenario, two versions of our algorithms also achieved average increases of 0.382 dB/0.394 dB and 0.0207/0.0210 under Motion and Gaussian mixed noise and average increases of 0.129 dB/0.154 dB and 0.0154/0.0158 under Average and Gaussian mixed noise compared with three quaternion-based restoration algorithms (QNLM, QNLTV, and quantization weighted nuclear norm minimization (QWNNM)).

Brain tumor classification and detection via hybrid alexnet-gru based on deep learning

Brain tumors are among the most dangerous types of brain cancer due to their aggressiveness. The development of aberrant brain tissue leads to brain tumors, which pose a major threat to people's health and welfare. Early detection of these malignancies is still fairly challenging, particularly when attempting to distinguish between various kinds including gliomas, meningioma, and pituitary tumors. The complexity of the brain's structure further increases the need for a speedy and accurate identification of irregularities. An innovative approach using a hybrid model that combines AlexNet and GRU (Gated Recurrent Unit) neural networks is presented to identify and characterize brain cancers using MRI data. The MRI images should first be sharpened and denoised using a non-local means filter to ensure the best input data. To avoid overfitting and achieve optimal model performance, the AlexNet architecture employs layers to extract specificfeatures from images. Model complexity and potential for generalization are regulated through hyperparameter modification. The GRU component resolves gradient vanishing in deep networks and uses the softmax activation function to categorize braintumorsinto four distinct classes. According to the findings, the model can categorize and diagnose brain cancers with 97% accuracy, 97.63% precision, a robust 96.78% recall rate, and an impressive 97.25% F1-Score. These findings show that theresearch has the potential to improve patient outcomes and create a more favorable healthcare environment in medical imaging and brain tumor detection.

Enhancement of Old Historical Document by Image Processing from Gray scale to RGB Scale Conversion

The enhancement of historical documents through image processing stands as a pivotal bridge between the past and the present. In this project, we embark on a journey to rejuvenate these treasured artifacts by utilizing cutting-edge techniques. Central to this endeavor is the conversion of grayscale documents into the vibrant realm of RGB, breathing new life into their visual presentation. The Nonlocal Mean Denoising algorithm takes center stage, diligently removing noise while preserving the document’s authenticity. Accompanied by image division code, we break down these historical scrolls and manuscripts into comprehensible segments, ensuring efficient processing without compromising their essence. At the heart of our methodology lies the profound significance of image histograms. Through these histograms, we delve into the intricacies of pixel intensities, unearthing valuable insights into the document’s characteristics. The outcome of our rigorous efforts is a transformation of these historical gems, making them not only aesthetically pleasing but also accessible to a broader audience, fostering a deeper appreciation of our cultural heritage. As technology and history intersect in this project, we highlight the transformative potential of image processing in preserving and reinvigorating the stories of the past. In an age where the digital realm converges with the analog, this endeavor reiterates the importance of ensuring that history remains alive and tangible for generations to come

Utilizing deep learning techniques to improve image quality and noise reduction in preclinical low-dose PET images in the sinogram domain.

Low-dose positron emission tomography (LD-PET) imaging is commonly employed in preclinical research to minimize radiation exposure to animal subjects. However, LD-PET images often exhibit poor quality and high noise levels due to the low signal-to-noise ratio. Deep learning (DL) techniques such as generative adversarial networks (GANs) and convolutional neural network (CNN) have the capability to enhance the quality of images derived from noisy or low-quality PET data, which encodes critical information about radioactivity distribution in the body. Our objective was to optimize the image quality and reduce noise in preclinical PET images by utilizing the sinogram domain as input for DL models, resulting in improved image quality as compared to LD-PET images. A GAN and CNN model were utilized to predict high-dose (HD) preclinical PET sinograms from the corresponding LD preclinical PET sinograms. In order to generate the datasets, experiments were conducted on micro-phantoms, animal subjects (rats), and virtual simulations. The quality of DL-generated images was weighted by performing the following quantitative measures: structural similarity index measure (SSIM), root mean squared error (RMSE), peak signal-to-noise ratio (PSNR), signal-to-noise ratio (SNR), and contrast-to-noise ratio (CNR). Additionally, DL input and output were both subjected to a spatial resolution calculation of full width half maximum (FWHM) and full width tenth maximum (FWTM). DL outcomes were then compared with the conventional denoising algorithms such as non-local means (NLM), block-matching, and 3D filtering (BM3D). The DL models effectively learned image features and produced high-quality images, as reflected in the quantitative metrics. Notably, the FWHM and FWTM values of DL PET images exhibited significantly improved accuracy compared to LD, NLM, and BM3D PET images, and just as precise as HD PET images. The MSE loss underscored the excellent performance of the models, indicating that the models performed well. To further improve the training, the generator loss (G loss) was increased to a value higher than the discriminator loss (D loss), thereby achieving convergence in the GAN model. The sinograms generated by the GAN network closely resembled real HD preclinical PET sinograms and were more realistic than LD. There was a noticeable improvement in image quality and noise factor in the predicted HD images. Importantly, DL networks did not fully compromise the spatial resolution of the images.

Improving BFS measurement accuracy of BOTDR based on Cauchy proximal splitting

A novel approach based on the Cauchy proximal splitting (CPS) algorithm is proposed to improve Brillouin frequency shift (BFS) measurement accuracy in Brillouin optical time domain reflectometry system. The CPS algorithm utilizes proximal splitting to handle the data and the penalty function based on Cauchy distribution to accurately estimate the target signal to promote sparsity, achieving significant improvement in signal-to-noise ratio (SNR). Experimental results confirm that with a SNR increase of 12.7 dB, an increase in BFS measurement accuracy from 4.78 MHz to 0.43 MHz is achieved over a 10.3 km sensing fiber. The denoising effects of the CPS, wavelet denoising (WD) and non-local mean (NLM) algorithms are further compared, demonstrating that the CPS algorithm has the lowest root mean square error (0.43 MHz) and no deterioration in spatial resolution rather than the WD and NLM algorithms does.

Brain tumour classification using MRI images based on lenet with golden teacher learning optimization

ABSTRACT Brain tumour (BT) is a dangerous neurological disorder produced by abnormal cell growth within the skull or brain. Nowadays, the death rate of people with BT is linearly growing. The finding of tumours at an early stage is crucial for giving treatment to patients, which improves the survival rate of patients. Hence, the BT classification (BTC) is done in this research using magnetic resonance imaging (MRI) images. In this research, the input MRI image is pre-processed using a non-local means (NLM) filter that denoises the input image. For attaining the effective classified result, the tumour area from the MRI image is segmented by the SegNet model. Furthermore, the BTC is accomplished by the LeNet model whose weight is optimized by the Golden Teacher Learning Optimization Algorithm (GTLO) such that the classified output produced by the LeNet model is Gliomas, Meningiomas, and Pituitary tumours. The experimental outcome displays that the GTLO-LeNet achieved an Accuracy of 0.896, Negative Predictive value (NPV) of 0.907, Positive Predictive value (PPV) of 0.821, True Negative Rate (TNR) of 0.880, and True Positive Rate (TPR) of 0.888.