Enhancement Filter Research Articles

Quality Assessment of Degraded PalmprintsUsing Enhancement Filters

Quality Assessment of Degraded PalmprintsUsing Enhancement Filters

Speech recognition in videos using features of different enhancement filters

Video Speech Recognition (VSR) is the ability of software to extract spoken text from input sources, such as offline videos and YouTube. It achieves a good recognition accuracy rate for videos with clean environments. However, with unwanted noisy elements in speech, this presents a major challenge. Depending on where the noise originates from, there are considerable differences in the impact of various noise kinds on video speech recognition, including background music, multiple speakers, microphone quality, and dialects. It is not possible to create a filter for every kind of noise because the sources of noise might differ greatly and the speech environment’s circumstances can change over time. Hence, instead of using a single filter for each type of noise, this study proposed to combine features from a small number of noise removal filters applied to the same video speech signal, resulting in a better VSR output. According to experimental results, using the proposed framework increases the accuracy of video speech recognition when evaluated on YouTube videos with different noise levels. In test experiments, the proposed framework was evaluated against state-of-the-art approaches. The accuracy mean of the relevant current approaches was improved by 16.67% and against the best accuracy of them by 7.78%. This research contributes to the video speech recognition topic as the proposed framework can facilitate the extraction of spoken phrases in millions of hours of video available online, indexing them, and then searching for them through their index.

Automatic vessel attenuation measurement for quality control of contrast-enhanced CT: Validation on the portal vein.

Adequate image enhancement of organs and blood vessels of interest is an important aspect of image quality in contrast-enhanced computed tomography (CT). There is a need for an objective method for evaluation of vessel contrast that can be automatically and systematically applied to large sets of CTexams. The purpose of this work was to develop a method to automatically segment and measure attenuation Hounsfield Unit (HU) in the portal vein (PV) in contrast-enhanced abdomen CTexaminations. Input CT images were processed by a vessel enhancing filter to determine candidate PV segmentations. Multiple machine learning (ML) classifiers were evaluated for classifying a segmentation as corresponding to the PV based on segmentation shape, location, and intensity features. A public data set of 82 contrast-enhanced abdomen CT examinations was used to train the method. An optimal ML classifier was selected by training and tuning on 66 out of the 82 exams (80% training split) in the public data set. The method was evaluated in terms of segmentation classification accuracy and PV attenuation measurement accuracy, compared to manually determined ground truth, on a test set of the remaining 16 exams (20% test split) held out from public data set. The method was further evaluated on a separate, independently collected test set of 21examinations. The best classifier was found to be a random forest, with a precision of 0.892 in the held-out test set to correctly identify the PV from among the input candidate segmentations. The mean absolute error of the measured PV attenuation relative to ground truth manual measurement was 13.4HU. On the independent test set, the overall precision decreased to 0.684. However, the PV attenuation measurement remained relatively accurate with a mean absolute error of 15.2HU. The method was shown to accurately measure PV attenuation over a large range of attenuation values, and was validated in an independently collected dataset. The method did not require time-consuming manual contouring to supervise training. The method may be applied to systematic quality control of contrast-enhanced CTexaminations.

Design of optimized fourth order PDE filter for restoration and enhancement of Microbiopsy images of breast Cancer

Design of optimized fourth order PDE filter for restoration and enhancement of Microbiopsy images of breast Cancer

Tectonics and seismicity of the Gulf of Aden: Contributions of edge detection filters applied to potential field data

Several studies have applied edge detection filters based on potential field derivatives, ratios and statistical-based tools to evaluate structures and provide interpretations. These edge filters provide different responses that may lead to false interpretations, making the selection of an effective filter that can provide optimum response difficult for users. Evaluating the reliability of the edge filters and avoiding false interpretations of the geologic structures requires simultaneous evaluation of filters applied to the same set of theoretical models. By using 2.5D models of gravity and magnetic synthetic data, we evaluate the performance of 21 edge detection filters based on different scenarios. The outcome of the various tests shows that filters of the third class give best results, with reference to the second and first class, and present good to moderate resolution in gravity and magnetic models. This comparison provides a means of inferring the tectono-structural styles, having generated multiple results from different filters and screening for artefacts (i.e., false impressions). Thereafter, we applied the edge enhancement filters to the magnetic and free-air gravity data of Aden Rift. Boundaries corresponding to seafloor spreading, divergent plate and transform faults were identified. The boundaries correlate well with the source locations of earthquakes at shallow depths. In addition to the dominant extensional tectonic regime, we suggest that the local fault system influenced by the Afar plume provides insights to the complex interaction between magmatic, sedimentary, and tectonic forces, shaping the geology of the Arabian-Nubian triple junction and contributes to the dynamics of the Gulf of Aden. The occurrence of earthquake activities along normal and transform fault zones which correlates with identified structural boundaries resulting from the application of edge detection filters provides a novel application to the study of rifting processes by multiple observation techniques.

Skin Cancer Image Segmentation Based on Midpoint Analysis Approach.

Skin cancer affects people of all ages and is a common disease. The death toll from skin cancer rises with a late diagnosis. An automated mechanism for early-stage skin cancer detection is required to diminish the mortality rate. Visual examination with scanning or imaging screening is a common mechanism for detecting this disease, but due to its similarity to other diseases, this mechanism shows the least accuracy. This article introduces an innovative segmentation mechanism that operates on the ISIC dataset to divide skin images into critical and non-critical sections. The main objective of the research is to segment lesions from dermoscopic skin images. The suggested framework is completed in two steps. The first step is to pre-process the image; for this, we have applied a bottom hat filter for hair removal and image enhancement by applying DCT and color coefficient. In the next phase, a background subtraction method with midpoint analysis is applied for segmentation to extract the region of interest and achieves an accuracy of 95.30%. The ground truth for the validation of segmentation is accomplished by comparing the segmented images with validation data provided with the ISIC dataset.

Development and validation of a semi-automated and unsupervised method for femur segmentation from CT

Quantitative computed tomography (QCT)-based in silico models have demonstrated improved accuracy in predicting hip fractures with respect to the current gold standard, the areal bone mineral density. These models require that the femur bone is segmented as a first step. This task can be challenging, and in fact, it is often almost fully manual, which is time-consuming, operator-dependent, and hard to reproduce. This work proposes a semi-automated procedure for femur bone segmentation from CT images. The proposed procedure is based on the bone and joint enhancement filter and graph-cut algorithms. The semi-automated procedure performances were assessed on 10 subjects through comparison with the standard manual segmentation. Metrics based on the femur geometries and the risk of fracture assessed in silico resulting from the two segmentation procedures were considered. The average Hausdorff distance (0.03 ± 0.01 mm) and the difference union ratio (0.06 ± 0.02) metrics computed between the manual and semi-automated segmentations were significantly higher than those computed within the manual segmentations (0.01 ± 0.01 mm and 0.03 ± 0.02). Besides, a blind qualitative evaluation revealed that the semi-automated procedure was significantly superior (p < 0.001) to the manual one in terms of fidelity to the CT. As for the hip fracture risk assessed in silico starting from both segmentations, no significant difference emerged between the two (R2 = 0.99). The proposed semi-automated segmentation procedure overcomes the manual one, shortening the segmentation time and providing a better segmentation. The method could be employed within CT-based in silico methodologies and to segment large volumes of images to train and test fully automated and supervised segmentation methods.

Enhancing filter efficiency of polyimide/polyethersulfone nanofiber membranes via novel treatments of high pressure processing, thermocompression, atmospheric plasma, and corona discharge

In this study, novel post-treatments contained of high pressure processing (HPP), thermocompression, atmospheric plasma, and corona discharge were used to progress the filter quality of polyimide/polyethersulfone (PI/PES) nanofiber membranes in the conditions of 50/50 % PI/PES, 0.15 ml/hr flow rate, 22.5 kV, and 20 min. The filter quality of nanofiber membrane did not get progress after HPP and thermocompression treatments, so high temperature and pressure did not improve the filter quality. Otherwise, atmospheric plasma destroyed the morphology of fiber surface, caused loss of filter efficiency and filter quality. However, corona discharge treatment presented different result with the above three treatments, and the filter efficiency and filter quality of the fiber membrane was improved after corona discharge treatment. Furthermore, factor influence order was ranged as operational voltage, discharge time, and discharge distance from result of filter quality on comparison of S/N value and level difference via Taguchi method. The application of corona discharge resulted in fiber acquired surface electric potential of 0.315 ± 0.56 kV at the optimized conditions of operational voltage (25 kV), discharge distance (7 cm), and discharge time (60 min), and filter efficiency of fiber enhanced from 95.66 ± 0.96 % to 98.70 ± 0.36 %. Further, the optimized PI/PES nanofiber membranes with corona discharge not only had a remarkable filter quality (2.214 Pa−1) but also maintained an effective filtration efficiency of ultra-fine particles (98.70 %) and a low pressure loss of 1.961 Pa for creating a promising filter of air purification and N95 Masks of USA NIOSH Standard.

A cognitive deep learning approach for medical image processing

In ophthalmic diagnostics, achieving precise segmentation of retinal blood vessels is a critical yet challenging task, primarily due to the complex nature of retinal images. The intricacies of these images often hinder the accuracy and efficiency of segmentation processes. To overcome these challenges, we introduce the cognitive DL retinal blood vessel segmentation (CoDLRBVS), a novel hybrid model that synergistically combines the deep learning capabilities of the U-Net architecture with a suite of advanced image processing techniques. This model uniquely integrates a preprocessing phase using a matched filter (MF) for feature enhancement and a post-processing phase employing morphological techniques (MT) for refining the segmentation output. Also, the model incorporates multi-scale line detection and scale space methods to enhance its segmentation capabilities. Hence, CoDLRBVS leverages the strengths of these combined approaches within the cognitive computing framework, endowing the system with human-like adaptability and reasoning. This strategic integration enables the model to emphasize blood vessels, accurately segment effectively, and proficiently detect vessels of varying sizes. CoDLRBVS achieves a notable mean accuracy of 96.7%, precision of 96.9%, sensitivity of 99.3%, and specificity of 80.4% across all of the studied datasets, including DRIVE, STARE, HRF, retinal blood vessel and Chase-DB1. CoDLRBVS has been compared with different models, and the resulting metrics surpass the compared models and establish a new benchmark in retinal vessel segmentation. The success of CoDLRBVS underscores its significant potential in advancing medical image processing, particularly in the realm of retinal blood vessel segmentation.

Impact of enhancement filters of a CMOS system on halo artifact expression at the bone-to-implant interface.

To assess the impact of enhancement filters on the formation of halo artifacts in radiographs of dental implants obtained with a complementary metal oxide semiconductor (CMOS) system. Digital radiographs of dental implants placed in dry human mandibles were processed with the Noise Reduction smoothing filter, as well as the Sharpen 1, Sharpen 4, and Sharpen UM high-pass filters available in the CLINIVIEW™ software (Instrumentarium Dental, Tuusula, Finland). Subjective analysis involved evaluating the left, right, and apical surfaces of each implant for the presence of much, few, or no halo. The objective analysis involved measurement of the halo area using the Trainable Weka Segmentation plugin (ImageJ, National Institutes of Health, Bethesda, MD, USA). Data were analyzed using Friedman's test (subjective analysis) and ANOVA (objective analysis) (α = 5%). In the subjective evaluation, the Sharpen 4 filter produced more radiographs with much halo present, and in the objective evaluation, a bigger halo area when compared to the original images and the Noise Reduction filter for all surfaces (p < 0.05). When evaluating dental implants, priority should be given to original images and those enhanced with smoothing filters since they exhibit fewer halo artifacts. Post-processing tools, such as enhancement filters, may improve the image quality and assist some diagnostic tasks. However, little is known regarding the impact of enhancement filters in halo formation on CMOS systems, which have been increasingly used in dental offices.

Spectral Total-variation Processing of Shapes—Theory and Applications

We present a comprehensive analysis of total variation (TV) on non-Euclidean domains and its eigenfunctions. We specifically address parameterized surfaces, a natural representation of the shapes used in 3D graphics. Our work sheds new light on the celebrated Beltrami and Anisotropic TV flows and explains experimental findings from recent years on shape spectral TV [Fumero et al. 2020 ] and adaptive anisotropic spectral TV [Biton and Gilboa 2022 ]. A new notion of convexity on surfaces is derived by characterizing structures that are stable throughout the TV flow, performed on surfaces. We establish and numerically demonstrate quantitative relationships between TV, area, eigenvalue, and eigenfunctions of the TV operator on surfaces. Moreover, we expand the shape spectral TV toolkit to include zero-homogeneous flows, leading to efficient and versatile shape processing methods. These methods are exemplified through applications in smoothing, enhancement, and exaggeration filters. We introduce a novel method that, for the first time, addresses the shape deformation task using TV. This deformation technique is characterized by the concentration of deformation along geometrical bottlenecks, shown to coincide with the discontinuities of eigenfunctions. Overall, our findings elucidate recent experimental observations in spectral TV, provide a diverse framework for shape filtering, and present the first TV-based approach to shape deformation.

Fuzzy Image Target Recognition Algorithm Based on Visual Similarity in the Internet of Things Environment

Abstract Because of the low accuracy of fuzzy image target recognition, an algorithm of fuzzy image target recognition based on visual similarity was researched. First, the method of adaptive weighted mean threshold was used to deal with fuzzy images, and then the adaptive threshold was obtained by a full scan of a fuzzy image. Second, the pixel point enhancement equation was established. Moreover, the new gradient operator used the points after filtering enhancement to reconstruct pixels and obtain the deblurred image. In addition, the visual similarity method was used to extract target features of the deblurred image, and then the color image was converted to a relatively uniform color space. On the basis of visual spatial response characteristics, brightness, contrast function, and chroma were used to adjust the image and thus to obtain the structure similarity index of each dimension image. By comprehensively considering the information of each dimension in color space, the structure similarity index was used to extract the image target features. Finally, the support vector machine model learned the target feature samples. Experimental results show that the proposed algorithm can effectively identify the fuzzy image target.

Illumination Methods for the Stereomicroscope, Including Use of Colored Filters for Image Contrast Enhancement

Stereo light microscopes (SLM) or dissecting microscopes are used in many different sciences, industries, and technologies. The objective for the SLM falls into two major categories: common main objective (CMO) using a single objective with prisms that split the image for each eye, and the Greenough style employing one microscope for each eye. In Europe, in the late 1800s, Carl Zeiss in conjunction with Otto Schott, designed a SLM using an Italian prism design that made images of the object correctly oriented. Two main illumination methods used with the SLM are transmitted and reflected light. Transmitted light illumination using a light source built into the base or with an attachable substage base utilizing an external light source. Some manufacturers provide additional illumination methods such as darkfield and polarizing light filters. Reflected illumination using visible light can be divided into five common illumination methods and two different ways to achieve fluorescent illumination. After a brief discussion of types of filters and sources, practical application of reflected light with the SLM substage attachable base with diffuse reflector and colored filters is shown to enhance visibility of certain colored particles while minimizing the visibility of unwanted colored particles.

Unsharp Masking of Medical Images using Rolling Guidance Filter

Medical Images consists of both high frequency and low frequency information needed by Physician for diagnostics and treatment purpose. Since, human eye is sensitive to high frequency information, the enhancement of high frequency information of medical image is very important. Most image enhancement techniques use the traditional unsharp mask filter to enhance the detail and edge information of medical image. While enhancing the detail and edge information, Gaussian Filter in traditional Unsharp Masking Filter introduces halo effects around edges. To remove this halo effects in enhanced images, this paper proposes a novel image enhancement filter in which Gaussian Filter is replaced by rolling guidance filter. This method provides satisfying results over Traditional Unsharp Mask Filter, Amended Unsharp Mask Filter, Anisotropic Diffusion based Unsharp Mask Filter and Guided Filtering based Unsharp Mask Filter in terms of high frequency information measures like mean gradient, spatial frequency and sharpness.

Deep Learning-Based Reconstruction Algorithm With Lung Enhancement Filter for Chest CT: Effect on Image Quality and Ground Glass Nodule Sharpness.

To assess the effect of a new lung enhancement filter combined with deep learning image reconstruction (DLIR) algorithm on image quality and ground-glass nodule (GGN) sharpness compared to hybrid iterative reconstruction or DLIR alone. Five artificial spherical GGNs with various densities (-250, -350, -450, -550, and -630 Hounsfield units) and 10 mm in diameter were placed in a thorax anthropomorphic phantom. Four scans at four different radiation dose levels were performed using a 256-slice CT (Revolution Apex CT, GE Healthcare). Each scan was reconstructed using three different reconstruction algorithms: adaptive statistical iterative reconstruction-V at a level of 50% (AR50), Truefidelity (TF), which is a DLIR method, and TF with a lung enhancement filter (TF + Lu). Thus, 12 sets of reconstructed images were obtained and analyzed. Image noise, signal-to-noise ratio, and contrast-to-noise ratio were compared among the three reconstruction algorithms. Nodule sharpness was compared among the three reconstruction algorithms using the full-width at half-maximum value. Furthermore, subjective image quality analysis was performed. AR50 demonstrated the highest level of noise, which was decreased by using TF + Lu and TF alone (P = 0.001). TF + Lu significantly improved nodule sharpness at all radiation doses compared to TF alone (P = 0.001). The nodule sharpness of TF + Lu was similar to that of AR50. Using TF alone resulted in the lowest nodule sharpness. Adding a lung enhancement filter to DLIR (TF + Lu) significantly improved the nodule sharpness compared to DLIR alone (TF). TF + Lu can be an effective reconstruction technique to enhance image quality and GGN evaluation in ultralow-dose chest CT scans.

On the practical implementation of the enhanced horizontal derivative filter for potential field data

The enhanced horizontal derivative (EHD) is an enhancement filter whose maxima provide estimated locations of the sources' boundaries. This filter is defined as the total horizontal derivative (THDR) of a weighted sum of vertical derivatives of increasing order. We consider some aspects of the practical implementation of the EHD filter, especially its robustness. A slightly different version of EHD, which we refer to as mEHD, is obtained when we switch the order of THDR and the weighted sum; that is, when we consider the weighted sum of total horizontal derivatives of the successive vertical derivatives. It turns out that mEHD can be more stable and provide a clearer enhanced map than the original filter, as demonstrated with examples of synthetic data and aeromagnetic data from Southern Brazil. Moreover, we address the choice of the weighting coefficients of the vertical derivatives, emphasizing that the standard choice of unitary weights may not be the most appropriate one. The enhanced horizontal derivative (EHD) is an enhancement filter whose maxima provide estimated locations of the sources' boundaries. This filter is defined as the total horizontal derivative (THDR) of a weighted sum of vertical derivatives of increasing order. We consider some aspects of the practical implementation of the EHD filter, especially its robustness. A slightly different version of EHD, which we refer to as mEHD, is obtained when we switch the order of THDR and the weighted sum; that is, when we consider the weighted sum of total horizontal derivatives of the successive vertical derivatives. It turns out that mEHD can be more stable and provide a clearer enhanced map than the original filter, as demonstrated with examples of synthetic data and aeromagnetic data from Southern Brazil.

Simulation and real time implementation of shunt active power filter for power quality enhancement using adaptive neural network topology

With the rise in non-linear loads, the need for a veracious power filter to alleviate voltage and current harmonics for meeting power quality has been a challenging requirement of the existing power system. This paper presents a systematic approach to improve power quality with a shunt active power filter (SAPF). The controller consists of a neural network approach to enhance the switching control of SAPF under dynamic and non-linear loading conditions. DC link voltage has been regulated using proportional-Integral (PI) control. To extract reference current, instantaneous-reactive power (IRP) theory has been used. IRP theory employing indirect current control strategy provides reference source current signals as well as regulated PWM switching signals for hysteresis control. An ADALINE network has been devised to extract fundamental signals from the polluted supply voltage. The model has been simulated on the MATLAB®/Simulink platform and validated by SAPF prototype in the laboratory using the TMS320F28335 floating-point DSP controller.

Fast Local Laplacian Filter Based on Modified Laplacian through Bilateral Filter for Coronary Angiography Medical Imaging Enhancement

Contrast enhancement techniques serve the purpose of diminishing image noise and increasing the contrast of relevant structures. In the context of medical images, where the differentiation between normal and abnormal tissues can be quite subtle, precise interpretation might become challenging when noise levels are relatively elevated. The Fast Local Laplacian Filter (FLLF) is proposed to deliver a more precise interpretation and present a clearer image to the observer; this is achieved through the reduction of noise levels. In this study, the FLLF strengthened images through its unique contrast enhancement capabilities while preserving important image details. It achieved this by adapting to the image’s characteristics and selectively enhancing areas with low contrast, thereby improving the overall visual quality. Additionally, the FLLF excels in edge preservation, ensuring that fine details are retained and that edges remain sharp. Several performance metrics were employed to assess the effectiveness of the proposed technique. These metrics included Peak Signal-to-Noise Ratio (PSNR), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Normalization Coefficient (NC), and Correlation Coefficient. The results indicated that the proposed technique achieved a PSNR of 40.12, an MSE of 8.6982, an RMSE of 2.9492, an NC of 1.0893, and a Correlation Coefficient of 0.9999. The analysis highlights the superior performance of the proposed method when contrast enhancement is applied, especially when compared to existing techniques. This approach results in high-quality images with minimal information loss, ultimately aiding medical experts in making more accurate diagnoses.

Optimal Solution for Segmentation of Malignant Melanoma Dermoscopic Images

Melanoma Malignant (MM) is the most common and dangerous form of skin cancer, which is analyzed by using Dermoscopic images in computer sciences. Segmentation technique is used to separate lesion part from healthy part in Dermoscopic images. In this research, comparison of different most popular segmented Dermoscopic image technique like Type-2 Fuzzy, Hybrid Threshold, Wavelet, Gradient Vector Flow (GVF), and Watershed etc. is approached and then better segmentation technique is proposed. In these segmentation techniques different issues like problem of hair, different color lesion, specular reflection and smoothing transaction between lesion and skin were not taken under consideration. Our methodology involves three levels of hierarchy. In the preprocessing step, it deals with problem of hair, bubble noise, smoothing and reflection noise in Dermoscopic images. These noise removals are achieved by using different filters like “Derivative of Gaussian filter and Bootomhat filter”. After region of interest is extracted then combination of threshold, image enhancement and morphological filter are used to produce the efficient algorithm for segmentation. At the end step, segmented crop image is compared with dice coefficient and experimental results of gross error rate are evaluated. For this purpose, PH² Dataset is used that contains 200 Dermoscopic images with the lesion images. The lesion images are extracted by the expert dermatologists.

EVALUATION OF UPWARD CONTINUATION AND REDUCTION TOEVALUATION OF UPWARD CONTINUATION AND REDUCTION TO MAGNETIC EQUATOR ON AIRBORNE MAGNETIC DATA MAGNETIC EQUATOR ON AIRBORNE MAGNETIC DATA

This research work is aimed at interpreting the airborne magnetic data of the study area for mapping the basement geologic structures using magnetic image enhancement filters. It focus on performing filtering techniques to expose and identify the magnetic properties of the basement structures at various continuation distances. The procedure applied to Total Magnetic Intensity (TMI) data of the study area using Oasis MontanjTM software were Reduction to Magnetic Equator (RTME) to remove the inclination effect as well as positioning the peak of the anomalies over their sources so as to improve the orientation of the magnetic sources, separation of regional and residual magnetic anomalies. These was followed by application of upward continuation at 500 m, 1000 m, 2000 m and 3000 m height. The results of the RTME shows the amplitude of the magnetic anomalies ranging from -37.577 nT to 27.398 nT. High magnetic anomaly is dominated in the northwest, southeast through southern part of the study location. Furthermore the results of the Upward Continuation (UC) revealed a wider wavenumber anomalies as well as height above the near surface. Hence the results of this research has displayed an enhanced geological magnetic structures located in the study area and also shows an improved quality of magnetic anomalies as the continuation distances increases.