Switched-current Gaussian low-pass filter based on IFLF configuration

Over the past few decades, convolutional neural networks (CNNs) have achieved outstanding results in addressing a broad scope of computer vision problems. Despite these improvements, fully convolutional Siamese neural networks (FCSNN) still hardly adapt to complex scenes, such as appearance change, scale change, similar objects interference, etc. The present study focuses on an enhanced FCSNN based on convolutional block hyperparameters optimization, a new activation function (ModReLU) and Gaussian low pass filter. The optimization of hyperparameters is an important task, as it has a crucial ascendancy on the tracking process performance, especially when it comes to the initialization of weights and bias. They have to work efficiently with the following activation function layer. Inadequate initialization can result in vanishing or exploding gradients. In the first method, we propose an optimization strategy for initializing weights and bias in the convolutional block to ameliorate the learning of features so that each neuron learns as much as possible. Next, the activation function normalizes the output. We implement the convolutional block hyperparameters optimization by setting the convolutional weights initialization to constant, the bias initialization to zero and the Leaky ReLU activation function at the output. In the second method, we propose a new activation, ModReLU, in the activation layer of CNN. Additionally, we also introduce a Gaussian low pass filter to minimize image noise and improve the structures of images at distinct scales. Moreover, we add a pixel-domain-based color adjustment implementation to enhance the capacity of the proposed strategies. The proposed implementations handle better rotation, moving, occlusion and appearance change problems and improve tracking speed. Our experimental results clearly show a significant improvement in the overall performance compared to the original SiamFC tracker. The first proposed technique of this work surpasses the original fully convolutional Siamese networks (SiamFC) on the VOT 2016 dataset with an increase of 15.42% in precision, 16.79% in AUPC and 15.93% in IOU compared to the original SiamFC. Our second proposed technique also reveals remarkable advances over the original SiamFC with 18.07% precision increment, 17.01% AUPC improvement and an increase of 15.87% in IOU. We evaluate our methods on the Visual Object Tracking (VOT) Challenge 2016 dataset, and they both outperform the original SiamFC tracker performance and many other top performers.

ABSTRACTThe pan-sharpening scheme combines high-resolution panchromatic imagery (HRPI) data and low-resolution multispectral imagery (LRMI) data to get a single merged high-resolution multispectral image (HRMI). The pan-sharpened image has extensive information that will promote the efficiency of image analysis methods. Pan-sharpening technique is considered as a pixel-level fusion scheme utilized for enhancing LRMI using HRPI while keeping LRMI spectral information. In this article, an efficient optimized integrated adaptive principal component analysis (APCA) and high-pass modulation (HPM) pan-sharpening method is proposed to get excellent spatial resolution within fused image with minimal spectral distortion. The proposed method is adjusted with multi-objective optimizationto determine the optimal window size and σfor the Gaussian low-pass filter (GLPF) and gain factor utilized for adding the high-pass details extracted from the HRPI to the LRMI principlecomponent of maximum correlation. Optimization results show that if the spatial resolution ratio of HRPI to LRMI is 0.50, then a GLPF of 5 × 5 window size and σ = 1.640 yields HRMI with low spectral distortion and high spatial quality. If the HRPI/LRMI spatial resolution ratio is 0.25, then a GLPF of 7 × 7 window size and σ = 1.686 yields HRMI with low spectral distortion and high spatial quality. Simulation tests demonstrated that the proposed optimized APCA–HPM fusion scheme gives adjustment between spectral quality and spatial quality and has small computational and memory complexity.

This paper describes a simple procedure for synthesizing an active distributed RC network which, by using dominant poles and zeros, realizes a very accurate approximation of an arbitrary stable rational transfer function. The network uses a single uniformly distributed RC line with taps spaced along its length. A linear combination of tap voltages is added to the input signal to form the driving voltage for the RC line; the output signal is also a linear combination of the tap voltages. The network offers a number of significant advantages. Since it realizes a nearly rational transfer function, the approximation problem can be conveniently solved using readily available results on rational function approximation. Also, the network uses only one uniform RC line, the transfer function can be changed simply by changing resistor values, and the frequency can be scaled by minor connection changes. Thus one standard network with minor modification is useful for a wide variety of applications. This paper develops the design procedure and derives the various sensitivity functions of importance. Two example designs are carried out: an approximation to a second-order low-pass transfer function and an approximation to a second-order band-pass transfer function with a Q of 100. The sensitivities for the examples are very reasonable and the measurements made on laboratory models indicate excellent agreement with theoretical predictions.

Gravity and gravity gradient data are widely used in geodesy, geodynamics, oil and mineral exploration, and aided navigation. The measured gravity and gravity gradient data include high-frequency noise caused by instrument system error, environmental conditions, and human factors. Separating noise from the measured gravity and gravity gradient data is one of the most challenging tasks in processing the measured data. Traditional low-pass digital filters can remove the noise of an individual component in real-time, which cannot realize the joint filtering of gravity and gravity gradient data. As a postprocessing method, the inversion-based methods can combine gravity and all the gradient components to remove the noise constrained by the Laplace equation. However, a real-time filter method that combines gravity and all gradient components is needed for some special applications, such as submarine gravity and gravity gradient-aided navigation. In this study, gravity and gravity gradient data are combined in establishing system equation and measurement equation of the standard Kalman filter, and denoised in real-time by the improved Kalman filter (IKF). Based on the model test, this method can simultaneously remove the noise in gravity and gravity gradient data in real-time, and ensure denoising performance. Finally, we apply this method to real gravity and gravity gradient data in St. George’s Bay, Canada, acquired by Bell Geospace, and compared the denoised results by full tensor noise reduction (FTNR) and Gaussian low-pass filter, which verified that the performance of IKF is well in real-time joint filtering of gravity and gravity gradient data.

Echocardiograms are inherently corrupted by the speckle noise. Elimination of the noise is usually treated with low-pass filters which can degrade edges in the image. Adaptive approaches employ masks for edges and restrict low-pass filtering mainly to homogeneous regions. Masks are based on statistical parameters or gradients. In this paper are applied local dimension matrices from fractal model as masks. Experimental tests are conducted for two simple low-pass filters (i) average filter and Gaussian filter (ii) and using three multifractal measures known from the literature - MIN, MAX and OSC measure. Obtained results for adaptive approaches show improvements over non-adaptive approaches in all analyzed scenarios.

This paper proposes a color filter array interpolation method, which expands the preceding gradient based scheme by adopting Gaussian low-pass filter. It starts from the assumption that high frequency components of the green plane in an image are almost the same as those of the red or blue planes in the same image. We identify that the conventional gradient method can make use of this idea and can be expanded by Gaussian low-pass filter to enhance its performance. To determine the reasonable mask size and the appropriate Gaussian sigma value, various values are tested with sample images, and used later to interpolate the green plane for other test images in the proposed method. Afterward, red and blue plane interpolations are performed, and directional median processing is applied along the flat edge lines. This process can effectively suppress false colors introduced during the interpolation of color planes. The proposed method provides a reasonable visual quality and generally higher peak-signal-to-noise-ratio compared to existing methods.

In this proposed work, a dual image watermarking algorithm is used to protect the data against copyright violations. In this work, the DICOM image is used as a host image. Two watermark images used are the MNNIT logo and the personal data of the patient. This method utilizes the advantages of Schur decomposition, lifting wavelet transform (LWT), discrete cosine transform (DCT) and singular value decomposition (SVD). The scaling factor is a vital parameter of watermarking technique. The firefly optimization technique is used to get the optimized scaling factor. The Speeded-up robust features (SURF) are used for watermarking authentication. To evaluate the performance of the proposed algorithm, peak signal-to-noise ratio (PSNR), normalized correlation coefficient (NCC), and structural similarity index measurement (SSIM) are used. The proposed method is tested against various attacks such as Salt and Pepper noise, Gaussian noise, Gaussian low pass filter, Average filter, Median filter, Histogram equalization, Sharpening, Rotation and Region of interest filtering. The proposed algorithm shows a high level of robustness and imperceptibility. It is found that the features of the input host image and the watermarked image are matching correctly on applying the SURF technique.

Early detection of Alzheimer’s disease (AD) has become one of the major research topics nowadays. The utilization of the computerized system may help medical experts to better understand and analyse the magnetic resonance imaging (MRI) images of AD patients for early detection. One of the commonly steps taken for the analysis of the image is image denoising using certain filters. However, finding shows that previous researchers use different approaches. This study aims to analyse the effect of different denoising techniques towards detection of Alzheimer’s disease. Data of two different groups (AD patients and Normal Control) were collected from Alzheimer's Disease Neuroimaging Initiative (ADNI). Then brain extraction and skull stripping were performed. Several image denoising techniques were implemented for both groups namely median filter, Wiener filter, histogram equalization filter and Gaussian low pass filter. After that, all images underwent texture feature extraction process and analysis were made to see the effect of those denoising techniques towards the features of Gray-Level Co-occurrence Matrix (GLCM) extracted which are the contract, correlation, energy and homogeneity features. The result shows that the use of mentioned denoising filters do not give effect to the extracted features. All values of contrast, correlation, energy and homogeneity cannot clearly distinguish between AD and NC groups. Without any filters on the other hand, contrast feature gives the best output in distinguishing between AD and NC groups with the normalized value of 0.1. The result from this study may help in thorough investigation of other features or hybrid features that could be used for the purpose of detection and classification of AD.

Undiagnosed polycystic diabetes based ovarian syndrome (PCOS) [Diabetes] can lead to infertility in females. Using a non-invasive transvaginal ultrasound machine, doctors can get a better look at the ovaries to determine if a woman has PCOS. Diabetes based ovarian images are distinguished primarily by the number and size of follicles present. By counting the follicles and measuring their diameters manually, PCOS is diagnosed. There are many steps to this procedure and error prone. The various studies that have been carried out since 2019 are examined in this publication. Gaussian low pass filter (GLPF), homogeneous region increasing mean (HRGMF) and contourlet transform are just some of the pre-processing methods that are examined. The segmentation methods that are discussed include Watershed transformation, edge-based approach, optimal thresholding, scanline thresholding, and active contour methods. Similarly, some of the classification methods discussed include the K-NN, linear discriminant, fuzzy, and SVM classifiers. Deep learning methods are used in this paper to identify follicles and PCOS diagnoses in ovarian ultrasound pictures. A comprehensive statistical analysis is presented in this review, which was carried out by gathering data from 30 publications released between the years 2019 to 2021. Some of the previous performances of the work are noted and compared. Finally, this paper offered ideas for future research methods.

Autotuners represent a combination of a relay feedback identification test and some control design method. In this contribution, models with up to three parameters are estimated by means of a single asymmetrical relay experiment. Then a stable low order transfer function with a time delay term is identified by a relay experiment. Autotuning principles then combine asymmetrical relay feedback tests with a control synthesis. Two algebraic control syntheses then are presented in this paper. The first one is based on the ring of proper and stable rational functions R PS. The second one utilizes a special ring R MS, a set of RQ-meromorphic functions. In both cases, controller parameters are derived through a general solution of a linear Diophantine equation in the appropriate ring. A final controller can be tuned by a scalar real parameter m>0. The presented philosophy covers a generalization of PID controllers and the Smith-like control structure. This contribution deals with the implementation of proposed autotuners and presents some illustrative examples. A Matlab toolbox for automatic design and simulation was developed and various simulations performed and analyzed.

In this paper we propose some techniques to design several types of 2D band-pass filters based on an ID prototype filter of a Gaussian type. First, a low-pass 2D Gaussian filter is obtained. Then, we show how a circular 2D band-pass filter is derived. A band-pass filter with two symmetric bands centered around a given pair of frequencies is also obtained. These filters have an elliptically or circularly-shaped horizontal section. Finally, a FIR ID Gaussian filter is designed, from which we derive a multi-band 2D FIR filter, with given peak frequencies.

The sigma-delta cellular neural network (SD-CNN) is a complete framework of a spatial domain sigma-delta modulator, and has a very high image reconstruction (AD-to-DA) performance. In this architecture, the A-template, given by a 2D low pass filter (LPF), is used for a digital to analogue converter (DAC), the C-template works as an integrator, and the nonlinear output function is for the bilevel output. By exploiting to the nonlinear optimization ability of CNN spatio-temporal dynamics, optimal binary and reconstruction image can be obtained. However, in the conventional SD-CNN, the Gaussian LPF, whose coefficients are real number, is used as the A-template. This filter coefficients requirement is one of major factors that restricts a hardware implementation. In this paper, a SD-CNN having hardware-friendly filter coefficients is proposed. Moreover its AD and DA performance is confirmed by some experiments.

The extraction of rotation invariant representation is important for many signal processing tasks such as image analysis, computer vision, pattern recognition and so forth. In this paper, we show that, under certain conditions, the Two-Dimensional Fractional Fourier Transform (2D-FRFT) possesses this attractive property through mathematical analysis and extensive computer simulations. Based on this property, we propose a novel digital image watermarking method which combines 2D chirp signal with the addition and rotation invariant properties of 2D-FRFT in order to improve robustness and security of digital image watermark in 2D-FRFT domain. Experimental results show that the proposed method is robust against numerous watermarking attacks including rotation geometrical transform, JPEG compression, crop, median filtering, histogram equalization, salt & pepper noise, Gaussian lowpass filter, shift, dithering and Gaussian noise, and secures against unauthorized information copying and redistribution.

Enhancing underwater image via color correction and Bi-interval contrast enhancement

This paper discussed consistency of long wavelength components of gravity field between the EGM96 and CHAMP gravity models and compared the long wavelength components of surface gravity data with ones from the models of CHAMP within the same spatial resolution, based on the 2-D Gaussian low-pass filter in China and its vicinity. The results show that the models of EGM96 and CHAMP are consistent up to about degree 35, while above this degrees the EIGEN-2 may have inferior estimates. The evaluation of the terrestrial gravity data for China and its vicinities by comparisons with the models of CHAMP has confirmed the existence of larger errors and systemic discrepancy.