Top-hat Filter Research Articles

Hybrid Feature Mammogram Analysis: Detecting and Localizing Microcalcifications Combining Gabor, Prewitt, GLCM Features, and Top Hat Filtering Enhanced with CNN Architecture.

Breast cancer is a prevalent malignancy characterized by the uncontrolled growth of glandular epithelial cells, which can metastasize through the blood and lymphatic systems. Microcalcifications, small calcium deposits within breast tissue, are critical markers for early detection of breast cancer, especially in non-palpable carcinomas. These microcalcifications, appearing as small white spots on mammograms, are challenging to identify due to potential confusion with other tissues. This study hypothesizes that a hybrid feature extraction approach combined with Convolutional Neural Networks (CNNs) can significantly enhance the detection and localization of microcalcifications in mammograms. The proposed algorithm employs Gabor, Prewitt, and Gray Level Co-occurrence Matrix (GLCM) kernels for feature extraction. These features are input to a CNN architecture designed with maxpooling layers, Rectified Linear Unit (ReLU) activation functions, and a sigmoid response for binary classification. Additionally, the Top Hat filter is used for precise localization of microcalcifications. The preprocessing stage includes enhancing contrast using the Volume of Interest Look-Up Table (VOI LUT) technique and segmenting regions of interest. The CNN architecture comprises three convolutional layers, three ReLU layers, and three maxpooling layers. The training was conducted using a balanced dataset of digital mammograms, with the Adam optimizer and binary cross-entropy loss function. Our method achieved an accuracy of 89.56%, a sensitivity of 82.14%, and a specificity of 91.47%, outperforming related works, which typically report accuracies around 85-87% and sensitivities between 76 and 81%. These results underscore the potential of combining traditional feature extraction techniques with deep learning models to improve the detection and localization of microcalcifications. This system may serve as an auxiliary tool for radiologists, enhancing early detection capabilities and potentially reducing diagnostic errors in mass screening programs.

Image Processing Techniques for Crack Detection in MPI of Springs

This study investigates image processing techniques for detecting surface cracks in spring steel components, with a focus on applications like Magnetic Particle Inspection (MPI) in industries such as railways and automotive. The research details a comprehensive methodology that covers data collection, software tools, and image processing methods. Various techniques, including Canny edge detection, Hough Transform, Gabor Filters, and Convolutional Neural Networks (CNNs), are evaluated for their effectiveness in crack detection. The study identifies the most successful methods, providing valuable insights into their performance. The paper also introduces a novel batch processing approach for efficient and automated crack detection across multiple images. The trade-offs between detection accuracy and processing speed are analyzed for the Morphological Top-hat filter and Canny edge filter methods. The Top-hat method, with thresholding after filtering, excelled in crack detection, with no false positives in tested images. The Canny edge filter, while efficient with adjusted parameters, needs further optimization for reducing false positives. In conclusion, the Top-hat method offers an efficient approach for crack detection during MPI. This research offers a foundation for developing advanced automated crack detection system, not only to spring sector but also extends to various industrial processes such as casting and forging tools and products, thereby widening the scope of applicability.

Deep Learning for Automatic Diagnosis of Skin Cancer Using Dermoscopic Images

Over the past few years, the healthcare industry has seen a dramatic increase in the use of intelligent automation enabled by AI technology. These developments are made to better the standard of medical decision making and the standard of treatment given to patients. Fuzzy boundaries, shifting sizes, and aberrations like hair or ruler lines all provide difficulties for automatic detection of skin lesions in dermoscopic images, slowing down the otherwise efficient process of diagnosing skin cancer. However, these difficulties may be conquered by employing image processing software. To address these issues, the authors of this paper provide a novel IMLT-DL model for intelligent dermoscopic image processing. Multi-level thresholding and deep learning are brought together in this model. Top hat filtering and inpainting have been included into IMLT-DL for use in image processing. In addition, Mayfly Optimization has been used in tandem with multilayer Kapur's thresholding to identify specific trouble spots. For further investigation, it uses an Inception v3-based feature extractor, and for data classification, it makes use of gradient boosting trees (GBTs). On the ISIC dataset, this model was shown to outperform state-of-the-art alternatives by a margin of 0.992% over the duration of trial iterations. These advances are a major step forwards in the quest for faster and more accurate skin lesion detection.

XANTHO – A simple basic program for fitting X-ray spectra

A code XANTHO for fitting X-ray spectra induced by photons or charge particles was developed as a Lazarus application. Background subtraction is performed by iterative filtering (brushing) of the source spectrum, based on the adapted Kolmogorov-Zurbenko approach. For comparison, a code with top-hat filtering was also developed. Critical comparison was made for a glass standard at PIXE analysis. XANTHO is intended for accurate fitting of individual spectra during analytical work and for sequential fitting at mapping experiments.

Region-based SVD processing of high-frequency ultrafast ultrasound to visualize cutaneous vascular networks

Observing alterations in cutaneous vasculature in response to any disease or pathology is considered as a potential diagnostic marker in the progression and cure of a disease. To observe skin morphologies and tissue conditions, high-frequency ultrasound (HFUS) has been used in dermatology, although its ability to selectively visualize micro-vessels is limited due to insufficient Doppler sensitivity to peripheral slow-speed blood flow. In recent studies, this issue has been improved by increasing the sensitivity of Doppler imaging to slow flow, leveraging advanced cutter filtering approaches based on singular value decomposition (SVD) techniques that aid to effectively extract flow signals overlapped with tissue echo signals. Nevertheless, in skin imaging, variations in flow speed, diameter, and depth of the blood vessels at different skin layers can make clutter filtering challenging because these variations are problematic in selecting the optimal cut-off value for the SVD filtering. In this study, we aimed to devise a novel region-based SVD filtering approach for ultrafast HFUS data to visualize cutaneous vascular networks. The proposed method divides the acquired high-framerate data into two regions based on B-mode cutaneous morphological identification (dermis layer and subcutaneous tissue). Singular value decomposition processing was performed on each region to effectively extract the desired flow signal, and the processed regions were merged to generate a single power Doppler image, thereby highlighting the appearance of a complete cutaneous vascular network. Finally, top-hat transform was applied to the power Doppler image to further suppress the background noises and enhances the visibility of the micro-vessels. Experimental observations of the human cutaneous circulation showed that the image quality (contrast-to-noise ratio) through the region-based SVD filtering was measured to be 4.1 dB (before top-hat filtering) and 5.2 dB (after top-hat filtering), which were improved from 3.4 dB and 4.0 dB obtained using the global SVD approach with and without top-hat filtering, respectively. We envisioned that this approach would provide diverse applications in the diagnosis of cutaneous disorders.

Optic disc localization using graph traversal algorithm along blood vessel in polar retinal image

The optic disc (OD) is an important landmark of the retina and its location is essential for computer-aided diagnosis of diabetic retinopathy and glaucoma. This paper presented a new method that applies the proposed graph traversal algorithm for vertical vascular infrastructure to detect root nodes representing the location of optical discs. The proposed algorithms were designed to process the terrific view of blood vessels from a polar image without depending on the prominent OD characteristic of circular/elliptical shape and brightness. Before constructing the vascular infrastructure, the new multi-scale and multi-orientation top-hat filters were proposed to properly approximate blood vessels of different sizes and directions. The proposed method provided efficiency and certainty for complex retinal images such as low contrast OD with low illumination and distorted OD shape due to complex vascular structure. The algorithms evaluation was performed on five public fundus image databases for retinal image analysis. Experimental results revealed that the proposed algorithm identified valid optical discs with high accuracy as 91.21%, 95.09%, 88.45%, 91.66%, and 95.01% for the five corresponding data sets and outperformed comparison methods.

Initial fault diagnosis of bearing based on AVMD-SE and multiscale enhanced morphological top-hat filter

Initial fault diagnosis of bearing based on AVMD-SE and multiscale enhanced morphological top-hat filter

Infrared Weak and Small Target Detection Based on Top-Hat Filtering and Multi-Feature Fuzzy Decision-Making

Infrared weak and small target detection in a complex background has always been a research hotspot in the fields of area defense and long-range precision strikes. Among them, the single-frame infrared weak and small target detection technology is even more difficult to study due to factors such as lack of target motion information, complex background, and low signal-to-noise ratio. Aiming at the problem of a high false alarm rate in infrared weak and small target detection caused by the complex background edges and noise interference in infrared images, this paper proposes an infrared weak and small target detection algorithm based on top-hat filtering and multi-feature fuzzy decision-making. The algorithm first uses the multi-structural element top-hat operator to filter the original image and then obtains the suspected target area through adaptive threshold segmentation; secondly, it uses image feature algorithms, such as central pixel contrast, regional gradient, and directional gradient, to extract the feature information of the suspected target at multiple scales, and the fuzzy decision method is used for multi-feature fusion to achieve the final target detection. Finally, the performance of the proposed algorithm and several existing comparison algorithms are compared using the measured infrared sequence image data of five different scenarios. The results show that the proposed algorithm has obvious advantages in various performance indicators compared with the existing algorithms for infrared image sequences in different interference scenarios, especially for complex background types, and has a lower performance under the condition of ensuring the same detection rate and false alarm rate and in meeting the real-time requirements of the algorithm.

Real-time detection and tracking of infrared small targets based on grid fast density peaks searching and improved KCF

Improving the accuracy and meeting the real-time requirement of detection and tracking for infrared small target is always a research hot-spot. In this paper, we propose a target detection approach based on grid-based density peaks searching. First, in view of the small size of infrared target, Top-hat filter is introduced for preprocessing of raw infrared images, to enhance the target region. Then, the image is divided into image blocks by grid division. Compared to the original method of density peaks searching on each pixel, grid-based density peaks searching algorithm improve the detection speed on the basis of ensuring the detection accuracy. Finally, the small candidate target area is detected by the gray-scale area growth method, and the final small targets are segmented through a threshold. For the infrared small targets tracking, the improved correlation filtering tracking algorithm KCF is used. To address the issue of target loss in the KCF tracking process, we incorporate Kalman filtering into KCF. In the case of the target loss, Kalman filtering is adopted to predict the target’s trajectory. The combination of detection and tracking algorithm could significantly improve the accuracy of infrared small targets tracking, while the fusion of detection algorithm and the tracking algorithm of correlation filtering makes the real-time performance of the algorithm better and more efficient. Experimental results show that compared with several currently typical infrared small targets detection and tracking algorithms, the method proposed in this paper has better detection accuracy and speed.

Performance analysis of diabetic retinopathy using diverse image enhancement techniques

ABSTRACT Most of the retinal disease can be manifested by retinal fundus images. However, the fundus image quality is not adequate for diagnosing the retinal disease such as diabetic retinopathy (DR) due to colour distortion, low contrast, uneven illumination, and blurring. Therefore, there is a need for enhancing the images by applying various enhancement techniques. This paper implements diverse methods for image enhancement such as wiener filter, median filter, Contrast Stretching, Histogram Equalisation, Contrast adjustment, Morphological top hat filter, morphological bottom hat filter, Adaptive Histogram Equalisation, Contrast limited Adaptive histogram Equalisation (CLAHE) on retinal images. The performance has been evaluated on DRIVE and STARE dataset, which includes Peak Signal to noise Ratio, Structural similarity Index, Mean Square Error, Maximum difference, Normalised cross correlation, structural Content, Normalised absolute error, Average difference and Entropy of the images.

Implementation of a real-time star centroid extraction algorithm with high speed and superior denoising ability.

Star tracker is the most precise attitude measuring device, and its advantages include a high resolution and high update rate. Star centroid extraction, which is a very time-consuming process, has great influence on the attitude update rate. This paper proposes a real-time star centroid extraction algorithm based on a field programmable gate array. First, a 1D top-hat filter is used for star segmentation, which is suitable for both uniform and nonuniform background conditions. Second, multichannel image data is reorganized together into a complete frame through image stitching, which prevents the star spots on the channel boundary from being divided into different parts. Finally, star coordinates are extracted by the center-of-mass algorithm. For an image sensor with a resolution of 2048×2048 pixels, simulation results conducted by a ModelSim simulator show that the star centroid processing time of a single frame is roughly 5.2 ms. Real night experiments demonstrate that the standard deviation of a star centroid error is within 10-2 pixel and the standard deviation of attitude is (2.6 2.2 12.0) arcseconds, which proves that the proposed star centroid extraction algorithm can work continuously and stably.

A Novel Method for Cataract Detection and Segmentation Using Nakagami Distribution

Early detection of cataract is considered as an important solution to prevent vision loss. An automatic detection of cataract is proposed in this work with the help of histogram approach. In the beginning, noises occur in an image which is also referred to as impulse noise. To eliminate this noise a non-linear type of median filter is matched especially for the morphological filter. These filtering methods help to extract the content of the image by edge detection and segmentation. The quality of the image is evaluated the image enhancing can be obtained by a histogram approach. A normalization method can be used to enhance the image which is also called Contrast stretching. To make morphological functions effective a top-hat filter is used to segment the cataract part in the given image. Nakagami distributions are usually used for extracting required important information of ultrasound details by matching histograms from the radio frequency signals. The extracted information from the Nakagami distribution is obtained by parameter values. The recent techniques used to improve the given image quality in histogram modification method are done by Intentional Camera Movement (ICM) and Unintentional Camera Movement (UCM) to recognize the real image more precisely. In the proposed method the result shows the noise reduction and a better contrast in the output image through parameters values such as Mean Squared Error (MSE) obtained as 17.23 and Peak-Signal-to-Noise Ratio (PSNR) obtained as 35.8.

A SIFT Description Approach for Non-Uniform Illumination and Other Invariants

The new improvement keypoint description technique of image-based recognition for rotation, viewpoint and non-uniform illumination situations is presented. The technique is relatively simple based on two procedures, i.e., the keypoint detection and the keypoint description procedure. The keypoint detection procedure is based on the SIFT approach, Top-Hat filtering, morphological operations and average filtering approach. Where this keypoint detection procedure can segment the targets from uneven illumination particle images. While the keypoint description procedures are described and implemented using the Hu moment invariants. Where the central moments are being unchanged under image translations. The sensitivity, accuracy and precision rate of data sets were evaluated and compared. The data set are provided by color image database with variants uniform and non-uniform illumination, viewpoint and rotation changes. The evaluative results show that the approach is superior to the other SIFTs in terms of uniform illumination, non-uniform illumination and other situations. Additionally, the paper demonstrates the high sensitivity of 100%, high accuracy of 83.33% and high precision rate of 80.00%. Comparisons to other SIFT approaches are also included.

COVID-19 Case Recognition from Chest CT Images by Deep Learning, Entropy-Controlled Firefly Optimization, and Parallel Feature Fusion.

In healthcare, a multitude of data is collected from medical sensors and devices, such as X-ray machines, magnetic resonance imaging, computed tomography (CT), and so on, that can be analyzed by artificial intelligence methods for early diagnosis of diseases. Recently, the outbreak of the COVID-19 disease caused many deaths. Computer vision researchers support medical doctors by employing deep learning techniques on medical images to diagnose COVID-19 patients. Various methods were proposed for COVID-19 case classification. A new automated technique is proposed using parallel fusion and optimization of deep learning models. The proposed technique starts with a contrast enhancement using a combination of top-hat and Wiener filters. Two pre-trained deep learning models (AlexNet and VGG16) are employed and fine-tuned according to target classes (COVID-19 and healthy). Features are extracted and fused using a parallel fusion approach—parallel positive correlation. Optimal features are selected using the entropy-controlled firefly optimization method. The selected features are classified using machine learning classifiers such as multiclass support vector machine (MC-SVM). Experiments were carried out using the Radiopaedia database and achieved an accuracy of 98%. Moreover, a detailed analysis is conducted and shows the improved performance of the proposed scheme.

Deconvolution of induced spatial discretization filters subgrid modeling in LES: application to two-dimensional turbulence

The paper presents a new approximate deconvolution subgrid model for Large Eddy Simulation in which corrections to implicit filtering due to spatial discretization are integrated explicitly. The top-hat filter implied by second-order central finite differencing is a key example, which is discretised using the discrete Fourier transform involving all the mesh points in the computational domain. This discrete filter kernel is inverted by inverse Wiener filtering. The inverse filter obtained in this way is used to deconvolve the resolved scales of the implicitly filtered velocity field on the computational grid. Subgrid stresses are subsequently calculated directly from the deconvolved velocity field. The model was applied to study decaying two-dimensional turbulence. Results were compared with predictions based on the Smagorinsky model and the dynamic Germano model. A posteriori testing in which Large Eddy Simulation is compared with filtered Direct Numerical Simulation obtained with a Fourier spectral method is included. The new model presented strictly speaking applies to periodic problems. The idea of recovering a high-order inversion of the numerically induced filter kernel can be extended to more general non-periodic problems, also in three spatial dimensions.

Excursion set peaks in energy as a model for haloes

ABSTRACT The simplest models of dark matter halo formation rely on the heuristic assumption, motivated by spherical collapse, that virialized haloes originate from initial regions that are maxima of the smoothed matter density field. Here, we replace this notion with the dynamical requirement that protohaloes be regions where the local gravitational flow converges to a point. For this purpose, we look for spheres whose acceleration at the boundary – relative to their centre of mass – points towards their geometric centre: that is, spheres with null dipole moment. We show that these configurations are minima of the energy, corresponding to the most energetically bound spheres. Therefore, we study peaks of the smoothed energy overdensity field. This significant conceptual change is technically trivial to implement: to change from density to energy one need only modify the standard top-hat smoothing filter. However, this comes with the important benefit that, for power spectra of cosmological interest, the model is no longer plagued by divergences: improving the physics mends the mathematics. In addition, the ‘excursion set’ requirement that the smoothed matter density crosses a critical value can be naturally replaced by a threshold in energy. Measurements in simulations of haloes more massive than 1013h−1M⊙ show very good agreement with a number of generic predictions of our model.

Green Channel and Top Hat based Image Enhancement for Diabetic Retinopathy Screening

Diabetic Retinopathy remains one of the most feared diabetes complications that could lead to blindness. Image processing techniques have been widely used all around the world for early detection of diabetic retinopathy. However, most techniques used do not focus on the low visual quality problems in the fundus image. Low visual quality of fundus image may lead to difficulty in evaluation by ophthalmologist before reading it out to the patients. Hence, Automated Screening for Diabetic Retinopathy was created to focus on image enhancement of the fundus image. In this study, two main algorithms for image processing have been used which are green channel conversion and top-hat filters. Green channel in fundus image is selected due to better contrast of the features and background compared to the red and blue channel. While Top-hat filter used to details out small features in the fundus image. The evaluation result of the techniques is compared by using Mean-Squared Error (MSE), Peak Signal-to-Noise Ratio (PSNR) and Entropy calculations to measure quality of the enhanced fundus images. Results of image enhancement techniques implemented has proved that quality of the fundus image is improved.

Pleural Line Detection Enhancement in Lung Ultrasonography (LUS) Based on Morphological and Adaptive Structural 2D Filter

Lung ultrasonography (LUS) imaging has been used intensively to investigate and assess the lung’s various pathological conditions. A diagnostic system of lung abnormalities is developed to detect and localize the pleural line that can be viewed as the artifacts in LUS image. The continuous pleural line indicates one crucial pattern of a healthy lung. The regular repeated horizontal A-line marks this pattern with a fixed distance between the lines and ideally, produces a higher contrast in the lung image. This work proposes an image processing framework for enhancing pleural line detection in healthy subjects and patients as an early stage of further lung image interpretations in pneumonia patients. The proposed image processing framework is based on a top-hat morphological grayscale 2D filter with a texture structure element and an adaptive structural 2D low pass filter. This framework is evaluated for open dataset video ultrasonography (USG) of Point-of-care ultrasound (POCUS) to enhance the pleural line detection for typical video LUS acquired using a linear and a convex transducer.

Fault diagnosis of rolling element bearings based on cascaded combination top-hat product filter and Teager energy spectrum

The fault features of rolling bearings are always difficult to detect due to the complex operating environment, especially when the fault is in the incipient stage with weak symptoms. For fault detection, this paper proposes a signal processing method based on cascaded combination top-hat product filter and Teager energy spectrum (CCTHPF-TES). First, combining the morphological top-hat operation and cascaded morphological operators, four cascaded combination morphological top-hat operators are presented for extracting the fault features in the vibration signal. Subsequently, by comprehensively investigating the filter characteristics of the proposed operators, a cascaded combination top-hat product operator (CCTHPO) is constructed to further highlight the fault feature information. Moreover, a high-order statistical analysis tool called TES is employed to further improve the detection ability of CCTHPO. Finally, an autocorrelation kurtosis criterion is defined to automatically determine the optimal output of CCTHPF-TES without prior knowledge of faults. Experimental data obtained from the bearing life-cycle test and engineering application are applied to testify the availability of CCTHPF-TES. The results show the superiority of the proposed CCTHPF-TES in bearing fault detection.

Automatic Diagnosis of Diabetic Retinopathy from Retinal Abnormalities: Improved Jaya-Based Feature Selection and Recurrent Neural Network

Abstract Accurate diagnosis of lesions bears the highest significance in the early detection of diabetic retinopathy (DR). In this paper, the combination of intelligent methods is developed for segmenting the abnormalities like ‘hard exudates, hemorrhages, microaneurysm and soft exudates’ to detect the DR. The proposed model involves seven main steps: (a) image pre-processing, (b) optic disk removal (c) blood vessel removal, (d) segmentation of abnormalities, (e) feature extraction, (f) optimal feature selection and (f) classification. The pre-processing of the input retinal fundus image is performed by two operations like contrast enhancement by histogram equalization and filtering by average filtering. For the segmentation of abnormalities, the same Circular Hough Transform followed by Top-hat filtering and Gabor filtering is used. Next, the entropy-scale-invariant feature transform (SIFT), grey level co-occurrence matrices and color morphological features are extracted in feature extraction. The optimally selected features are subjected to the classification part, which uses a modified deep learning algorithm called optimized recurrent neural network (RNN). As the main novelty, the optimal feature selection and optimized RNN depends on an improved meta-heuristic algorithm called fitness oriented improved Jaya algorithm. Hence, the beneficial part of the optimization algorithm improves the feature selection and classification.