Smart Surveillance Camera based on Pattern

We investigate the use of Fourier plane nonlinear filtering for phase-encoded images. We investigate the performance of the nonlinear joint transform correlator and the nonlinearly transformed matched filter for phase-encoded images with different types of input noise. We use the peak-to-output-energy ratio, peak-to-sidelobe ratio, and discrimination ratio as the metrics for measuring the performances. We mathematically analyze the peak-to-output-energy ratio of the nonlinearly transformed matched filter for phase-encoded images with spatially nonoverlapping white noise. Computer simulations are provided to show the performance improvements of the nonlinear filtering techniques for the phase-encoded images. In comparison with linear filtering techniques, we find that the nonlinear filtering techniques substantially improve the performance metrics. From the computer-simulation results it can be seen that the nonlinear joint transform correlator performs better than the nonlinearly transformed matched filter in detecting phase-encoded targets in the presence of different types of noise, such as additive overlapping white noise, spatially nonoverlapping white background noise, spatially nonoverlapping colored background noise, and nontarget objects.

Oscillator noise is generally modeled by a power law spectral density. Thus it is possible to characterize different noise sources, each of them corresponding to a particular power law. The measurement of the contribution of these sources is necessary to know their origin and to remedy these causes in order to improve oscillator performance. Usually, an estimation of the different types of noise present in a signal is obtained by using a variance. However, the sensitivity of these variances differs for each type of noise and then limits this method. On the other hand, the use of several variances, each of them more sensitive to one type of noise, permits one to notably improve the measurement accuracy. The method suggested here uses as many different variances as there are types of noise to measure. The improvement of measurement accuracy of the noise coefficient is discussed in this paper.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

In this work, the effects of background noises on nonlinear dynamics of a modelled standing-wave thermoacoustic system with subcritical Hopf bifurcation behaviors are studied. These noises include (1) pressure-coupled (acoustic), (2) velocity-coupled (flow), and (3) external combustion noise. It is found that these three types of background noises play important, but different roles in changing the hysteresis width and stability boundary. In addition, the stochastic transition from stability to instability is investigated, as the noise intensity is varied. Two different stochastic P-bifurcations are identified. One is related to a craterlike probability density distribution. The other is associated with a probability density distribution characterized with two peaks and one trough. With each type of noise affecting the system's stochastic behaviors being evaluated, the effect of two different types of noises is then studied. It is shown that the combined noises (types 1 and 2) cannot only destabilize global stable thermoacoustic system, but also stabilize linearly unstable system. This depends strongly on the superimposition form of the two types of noises. In addition, when the thermoacoustic system is disturbed by the combined noise (types 3 and 1 or types 3 and 2), the transition process is dominated by the combustion noise.

A displacement measurement technology using phase- encoded target joint transform correlator (PETJTC) is analyzed in detail. A phase mask is generated electronically and applied to encode the tar- get image. Input images include the phase-encoded target image and the reference image. The joint power spectrum of the input images are ob- tained and encoded by the same phase mask. Through another Fourier transform the brightest peak in relation to displacement between the ref- erence and target image appears in the correlation plane. In contrast to the displacement measurement based on traditional joint transform cor- relator, PETJTC could efficiently use the space of the input plane such as spatial light modulator, disperse the autocorrelation item into system noises, and leave the cross-correlation items only, which is convenient for detection. The effects of phase mask with different sizes and different types of noises are analyzed. Results based on digital computation show that PETJTC has a higher performance if the phase mask is bigger and has strong robustness under severe noise. Different displacement mea- surement technologies are contrasted. PETJTC could accurately detect the displacement. Root mean square errors can remain within 0.1 pixel. C 2011 Society of Photo-Optical Instrumentation Engineers (SPIE). (DOI: 10.1117/1.3552661) Subject terms: image stabilization; displacement measurement; joint transform correlator; phase-encoded.

Objective: to analyze speech perception in normally hearing adults when listening in silence and with different types of noise. Methods: 40 individuals of both sexes, aged 18 to 45 years, participated in the study. Speech perception was assessed with the Lists of Sentences in Portuguese test, without a competing noise and with speech-spectrum, babble, and cocktail party noise. A mixed-effects linear regression model and the 95% confidence interval were used. Results: the subjects’ performance was worse in the three types of noise than in silence. When comparing the types of noise, differences were found in all combinations (speech-spectrum X babble, speech-spectrum X cocktail party, and babble X cocktail party), with a worse performance in babble, noise, followed by cocktail party. Conclusion: all noises negatively influenced speech perception, with a worse performance in babble, followed by cocktail party and speech-spectrum.

In this work, we propose ShallowDeepNet, a novel system architecture that includes a shallow and a deep neural network. The shallow neural network has the duty of data preprocessing and generating adversarial samples. The deep neural network has the duty of understanding data and information as well as detecting adversarial samples. The deep neural network gets its weights from transfer learning, adversarial training, and noise training. The system is examined on the biometric (fingerprint and iris) and the pharmaceutical data (pill image). According to the simulation results, the system is capable of improving the detection accuracy of the biometric data from 1.31% to 80.65% when the adversarial data is used and to 93.4% when the adversarial data as well as the noisy data are given to the network. The system performance on the pill image data is increased from 34.55% to 96.03% and then to 98.2%, respectively. Training on different types of noise can benefit us in detecting samples from unknown and unseen adversarial attacks. Meanwhile, the system training on the adversarial data as well as noisy data occurs only once. In fact, retraining the system may improve the performance further. Furthermore, training the system on new types of attacks and noise can help in enhancing the system performance.

Noise induced hearing loss (NIHL) as one of the major avoidable occupational related health issues has been studied for decades. To assess NIHL, the excitation pattern (EP) has been considered as one of the mechanisms to estimate the movements of the basilar membrane (BM) in the cochlea. In this study, two auditory filters, dual resonance nonlinear (DRNL) filter and rounded-exponential (ROEX) filter are applied to create two EPs, the velocity EP and the loudness EP respectively. Two noise hazard metrics are proposed based on two proposed EPs to evaluate hazardous levels caused by different types of noise. Moreover Gaussian noise and tone signals are simulated to evaluate performances of the proposed EPs and the noise metrics. The results show that both EPs can reflect the responses of the BM to different types of noise. For Gaussian noise there is a frequency shift between the velocity EP and the loudness EP. The results suggest that both EPs can be used for assessment of NIHL.

Electrocardiogram (ECG) signals are electrical signals generated corresponding to activity of heart. ECG signals are recorded and analysed to monitor heart condition. In initial raw form, ECG signals are contaminated with different types of noises. These noises may be electrode motion artefact noise, baseline wander noise and muscle noise also known as electromyogram (EMG) noise etc. In this paper, a descendent structure consists of adaptive filters is used to eliminate the three different types of noises (i.e., motion artefact noise, baseline wander noise and muscle noise). The two different adaptive filtering algorithms have been implemented; least mean square (LMS) and recursive least square (RLS) algorithm. The performance of these filters are compared on the basis of different fidelity parameters such as mean square error (MSE), normalised root mean squared error (NRMSE), signal-to-noise ratio (SNR), percentage root mean squared difference (PRD), and maximum error (ME) has been observed.

Diverse Non-Fundamental Information and Trading Complementarities

Different types of noise are studied, in particular, the color noises, flicker noise, and self-similar (fractal) noise. The results of studies of statistical stability of various noises and processes are generalized and the causes of statistical stability violation are investigated. It is found that statistically unstable processes can arise in different ways: because of inflows from the outside in an open system of matter, energy, and (or) information, as a result of nonlinear and even linear transformations, and due to wave damping.

Noise is one of the prime factors which degrade the quality of an image. Hence, image denoising is an essential image enhancement technique in the image processing domain. In this paper, we use low-pass sparse banded filter matrices for image denoising. Sparsity is the key concept in this filter design. We applied the designed low-pass filter both row-wise and column-wise to denoise the image. The proposed method is experimented on standard test images corrupted with different types of noises namely Gaussian, White Gaussian, Salt & Pepper and Speckle with noise level equals to 0.01, 0.05 and 0.1. The effectiveness of the proposed method of denoising is evaluated by the computation of standard quality metric known as Peak Signal-to-Noise Ratio (PSNR). The experimental result analysis shows that the proposed image denoising technique based on sparse banded filter matrices results in significant improvement in PSNR around 2dB to 8dB for different type of noises with noise level equal to 0.1 and is also aided by the visual analysis.

Face recognition is a significant area of pattern recognition and computer vision research. Illumination in face recognition is obvious yet challenging task in pattern matching. Recent researchers introduced machine learning algorithms to solve illumination problems in both indoor and outdoor scenarios. The major challenge in machine learning is the lack of classification accuracy. Thus, the novel Optimized Neural Network Algorithm (ONNA) is used to solve the aforementioned drawback. First, we propose a novel Weight Transfer Ideal Filter (WTIF) which is employed for pre-processing to remove the dark spots and shadows in an image by normalizing low frequency and high frequency of illumination. Secondly, Robust Principal Component Analysis (RPCA) is employed to perform efficient extraction of features based on image area representation. These features are given as input to ONNA which classifies the given input image under illumination. Thus we achieve the recognition of the face under various illumination conditions. Our approach is analyzed and compared with existing approaches such as Support Vector Machine (SVM) and Random Forest (RF). ONNA is better in terms of high accuracy and low error rate.

A learning strategy in Learning Classifier Systems (LCSs) defines how classifiers cover a state-action space in a problem. Previous analyses in classification problems have empirically claimed an adequate learning strategy can be decided depending on the types of noise in the problem. This issue is still arguable from two aspects. First, there lacks comparison of learning strategies in reinforcement learning problems with different types of noise. Second, when we can claim so, a further issue is how should classifiers cover the state-action space in order to improve the stability of LCS performance on as many types of noise as possible? This paper first attempts to empirically conclude these issues on a version of LCSs (i.e., the XCS classifier system). That is, we present a new concept of learning strategy for LCSs, and complement that claim by comparing it with the existing learning strategies on a reinforcement learning problem. Our learning strategy covers all state-action pairs but assigns more classifiers to the highest-return action at each state than other actions. Our results support that claim that existing learning strategies have dependencies on the types of noise in reinforcement learning problems. However, our learning strategy improves the stability of XCS performance compared with the existing strategies on all types of noise employed in this paper.

Moving object detection under varying illumination is a prominent area of research in the field of computer vision. The detected object results from moving object framework, suffers from factors like noise, change in object scene, shadow, changes in illumination etc. So there is a growing interest to develop a robust moving object detection framework under varying illumination scenario. A significant amount of methods have been proposed over recent years on moving object detection under varying illumination condition. In this paper some of the recent effective methods based on accuracy have been reviewed. In this paper, methods reviewed include illumination sensitive feature and illumination invariant feature approaches for moving object detection under illumination varying background conditions. Methods reviewed in this paper include qualitative and quantitative comparison to guide the reader a clear insight to the computer vision community, those who are especially working in moving object detection under different illumination conditions.

Superpixels have gradually become popular in computer vision and image processing applications. However, no comprehensive study has been performed to evaluate the robustness of superpixel algorithms in regard to common forms of noise in natural images. We evaluated the robustness of 11 recently proposed algorithms to different types of noise. The images were corrupted with various degrees of Gaussian blur, additive white Gaussian noise, and impulse noise that either made the object boundaries weak or added extra information to it. We performed a robustness analysis of simple linear iterative clustering (SLIC), Voronoi Cells (VCells), flooding-based superpixel generation (FCCS), bilateral geodesic distance (Bilateral-G), superpixel via geodesic distance (SSS-G), manifold SLIC (M-SLIC), Turbopixels, superpixels extracted via energy-driven sampling (SEEDS), lazy random walk (LRW), real-time superpixel segmentation by DBSCAN clustering, and video supervoxels using partially absorbing random walks (PARW) algorithms. The evaluation process was carried out both qualitatively and quantitatively. For quantitative performance comparison, we used achievable segmentation accuracy (ASA), compactness, under-segmentation error (USE), and boundary recall (BR) on the Berkeley image database. The results demonstrated that all algorithms suffered performance degradation due to noise. For Gaussian blur, Bilateral-G exhibited optimal results for ASA and USE measures, SLIC yielded optimal compactness, whereas FCCS and DBSCAN remained optimal for BR. For the case of additive Gaussian and impulse noises, FCCS exhibited optimal results for ASA, USE, and BR, whereas Bilateral-G remained a close competitor in ASA and USE for Gaussian noise only. Additionally, Turbopixel demonstrated optimal performance for compactness for both types of noise. Thus, no single algorithm was able to yield optimal results for all three types of noise across all performance measures. Conclusively, to solve real-world problems effectively, more robust superpixel algorithms must be developed.