Invariance properties of gabor filter-based features--overview and applications.

For almost three decades the use of features based on Gabor filters has been promoted for their useful properties in image processing. The most important properties are related to invariance to illumination, rotation, scale, and translation. These properties are based on the fact that they are all parameters of Gabor filters themselves. This is especially useful in feature extraction, where Gabor filters have succeeded in many applications, from texture analysis to iris and face recognition. This study provides an overview of Gabor filters in image processing, a short literature survey of the most significant results, and establishes invariance properties and restrictions to the use of Gabor filters in feature extraction. Results are demonstrated by application examples.     

A novel robust filtering strategy for systems with Non-Gaussian noises

For estimating the states of moving targets in the nonlinear system with non-Gaussian noise, the combination of Gaussian Sum Filter (GSF) and other nonlinear filters has been chosen as the filtering algorithm conventionally. The Smooth Variable Structure Filter (SVSF) is a new predictor-corrector method used for state and parameter estimation, which has good stability and robustness. In this paper we propose a new strategy called the modified GS-EKF-SVSF, which inherits good robustness of Gaussian Sum and Smooth Variable Structure Filter (GS-SVSF) and high accuracy of Gaussian Sum and Extended Kalman Filter (GS-EKF). A nonlinear system with non-Gaussian noise for target tracking is used to test the proposed new strategy. The simulation results demonstrate that our proposed strategy has higher accuracy and better robustness when there are modelling uncertainties existing in the system.     

An Energy Efficient Protocol to Mitigate Hot Spot Problem Using Unequal Clustering in WSN

Iris recognition under less constrained environment poses a challenge to be considered for high-security applications. In this paper, discrete orthogonal moment-based features including Tchebichef, Krawtchouk and Dual-Hahn are proposed which prove to be effective for both near-infrared and visible images. The local as well as global features are extracted from localized iris regions till 15th order with invariance (scale, rotation, translation and illumination) properties and tolerance to noise. The performance of the moment-based features is evaluated on four publicly available databases: CASIA-IrisV4-Interval, IITD.v1, UPOL and UBIRIS.v2. It is found that the proposed method gives encouraging results in terms of accuracy, equal error rate and decidability index as compared to the competing techniques available in the literature.     

Optimization-based methodology for training set selection to synthesize composite correlation filters for face recognition

Face recognition has been addressed with pattern recognition techniques such as composite correlation filters. These filters are synthesized from training sets which are representative of facial classes. For this reason, the filter performance depends greatly on the appropriate selection of the training set. This set can be selected either by a filter designer or by a conventional method. This paper presents an optimization-based methodology for the automatic selection of the training set. Given an optimization algorithm, the proposed methodology uses its main mechanics to iteratively examine a given set of available images in order to find the best subset for the training set. To this end, three objective functions are proposed as optimization criteria for training set selection. The proposed methodology was evaluated by undertaking face recognition under variable illumination and facial expressions. Four optimization algorithms and three composite correlation filters were used to test the proposed methodology. The Maximum Average Correlation Height filter designed by Grey Wolf Optimizer obtained the best performance under homogeneous illumination and facial expressions, while the Unconstrained Nonlinear Composite Filter designed by either Grey Wolf Optimizer or (1+1)-Evolution Strategy obtained the best performance under variable illumination. The proposed methodology selects training sets for the synthesis of composite filters with competitive results comparable to the results reported in the face recognition literature.     

Scale and Rotation Invariant Optical ID Tags for Automatic Vehicle Identification and Authentication

We present a scale and/or rotation invariant ID tag to achieve real time automatic vehicle identification for inventory or security purposes. We focus our attention to achieve invariance with respect to scale variations and in-plane rotations of the ID tag. Both distortions must be taken into account in the design of a vehicle identification system operating from above the area of interest (e.g., aerial detection and authentication). In our proposal, distortion invariance is achieved by both multiplexing the ID tag a priori information, and developing an appropriate topology for encoding the information on the ID tag. To increase security, the designed ID tag consists of an optical code containing an encrypted signature which identifies the vehicle. The applied encryption procedure follows the double phase encoding technique, which provides robustness to different degradation sources such as noise, occlusion, scratches, etc. that may affect the ID tag. Once the ID tag is captured by the processor, decryption of the hidden signature is carried out, and its correlation with a previously stored reference signal allows either the identification or the rejection of the authorized vehicle. Numerical results are provided to show the feasibility of the system. The proposed system may have broad applications in transportation, homeland security, and remote vehicle inventory control.     

Band-pass correlation filter for illumination- and noise-tolerant face recognition

The paper proposes a band-pass correlation filter in frequency domain for frontal face recognition task under both poor illumination and noisy condition. The band-pass nature of the proposed filter is achieved through combination of a modified high-pass filter and a continuous wavelet filter. An optimal range of scale is selected for this wavelet filter. The performance of the proposed band-pass correlation filter for face recognition tasks under variations in illumination and noise is evaluated and compared with other filters using standard databases (YaleB and PIE). High recognition accuracy is achieved in this proposed technique.     

Using Zernike moments for the illumination and geometry invariantclassification of multispectral texture

We develop a method for recognizing color texture independent of rotation, scale, and illumination. Color texture is modeled using spatial correlation functions defined within and between sensor bands. Using a linear model for surface spectral reflectance with the same number of parameters as the number of sensor classes, we show that illumination and geometry changes in the scene correspond to a linear transformation of the correlation functions and a linear transformation of their coordinates. A several step algorithm that includes scale estimation and correlation moment computation is used to achieve the invariance. The key to the method is the new result that illumination, rotation, and scale changes in the scene correspond to a specific transformation of correlation function Zernike moment matrices. These matrices can be estimated from a color image. This relationship is used to derive an efficient algorithm for recognition. The algorithm is substantiated using classification results on over 200 images of color textures obtained under various illumination conditions and geometric configurations.     

基于颜色对抗和旋转对称的路标检测算法

本文针对禁止和警告标志提出了一种基于颜色对抗和旋转中心投影的检测方法。颜色对抗来源于人眼视觉机制中存在的相互对立的红/绿、黄/蓝色素对,以此突出红色和黄色区域。投影阶段则利用交通标志规则多边形的特征将点对的梯度向量向其旋转中心投影,得到多边形的中心位置和尺度信息。另外,采用多边形的几何特征进一步区分交通标志的类别。实验证明该方法能够满足实时需求,并对光照、旋转、尺度变化具有一定的不变性。     

Robust watermarking against print and scan attack through efficient modeling algorithm

This article proposes a blind discrete wavelet transform-discrete cosine transform (DWT-DCT) composite watermarking scheme that is robust against print and scan distortions. First, two-dimensional DWT is applied to the original image to obtain the mid-frequency subbands. Then, a one-dimensional DCT is applied to the selected mid-frequency subbands to extract the final coefficients for embedding the watermark. To specify watermarking parameters, we utilize a Genetic Algorithm to achieve a predefined image quality after watermark insertion. Suitable locations for watermarking are determined by analyzing the effect of a modeling algorithm. This model simulates noise and nonlinear attacks in printers and scanners through noise estimation and system identification methods. The experimental results demonstrate that the proposed algorithm has a high robustness against print and scan attack such that its robustness is higher than related watermarking algorithms.     

采用Gabor-Hough变换的自适应滤波人眼定位

人眼定位是人脸识别方法的第一步。传统人眼定位方法需要将人脸裁切,情况单一,对于复杂背景、倾斜等情况,精度低,宽容度差。指出将改进的滤波器与改进的定位方法相结合,首先对原图像进行Gabor变换,寻找图像凹陷,凹陷区域通过边缘像素向量改进的Hough变换检测瞳孔,得到参考坐标,经过训练得到滤波器并在角度[-0.1,0,0.1]旋转两次得到3个相关滤波器,通过相关滤波器滤出3个目标,选择最小误差位置作为最终的目标。相比传统方法,改进方法避免了矩阵盲目计算,具备传统方法的普适性,学习过程使定位误差减小为0.0404,计算量减少为传统方法的1/5。该方法对不同光照、光照不均、不同表情、复杂背景、头部倾斜等情况有较好的鲁棒性,避免了单一方法定位不到和不准的情况。     

基于Zernike矩和SVM的不变性目标识别

在图像目标识别中,目标图像平移、尺度和旋转不变性是一个重要前提.文中采用稳定性好的低阶几何矩特征实现目标的平移、尺度不变性变换;然后利用Zemike矩提取目标的旋转不变性特征;最后在目标不变特征空间通过支持向量机(SVM)分类器实现目标识别.实验证实了算法的有效性.     

模拟路标识别及其FPGA实现

针对路标信号的多变性给驾驶员行车途中带来诸多隐患,提出了基于FPGA辅助驾驶中的模拟路标识别系统,该系统实现了实时检测和识别路标信号,并将识别结果显示出来,以便驾驶员做出相应的响应,在一定程度上维护了交通安全。实验结果表明,基于硬件编程语言Verilog设计的硬件电路可快速、稳定地对图像进行二值化处理,且该系统可实现识别向左、向右、禁止停车、禁止通行4种路标,对辅助驾驶系统的研究具有一定的意义。     

Road traffic sign detection and classification

A vision-based vehicle guidance system for road vehicles can have three main roles: (1) road detection; (2) obstacle detection; and (3) sign recognition. The first two have been studied for many years and with many good results, but traffic sign recognition is a less-studied field. Traffic signs provide drivers with very valuable information about the road, in order to make driving safer and easier. The authors think that traffic signs most play the same role for autonomous vehicles. They are designed to be easily recognized by human drivers mainly because their color and shapes are very different from natural environments. The algorithm described in this paper takes advantage of these features. It has two main parts. The first one, for the detection, uses color thresholding to segment the image and shape analysis to detect the signs. The second one, for the classification, uses a neural network. Some results from natural scenes are shown     

A Filter Bank Based Approach for Rotation Invariant Fingerprint Recognition

This paper presents a systematic approach for image-based fingerprint recognition. The proposed method first enhances an input fingerprint image using a contextual filtering based method in the frequency domain. Complex filters are used for the detection of the core point, and a region of interest (ROI) of a predefined size centered at the detected core point is extracted. The resulting ROI is rotated based on the angle of the detected core point to ensure rotation invariance. Subsequently, the proposed system extracts the average absolute deviation (AAD) from the outputs of a Gabor filter bank. To reduce the dimensionality of the extracted features whilst generating more discriminatory representation, this paper compares the unsupervised Principal Component Analysis (PCA) and the supervised Linear Discriminant Analysis (LDA) methods for dimensionality reduction. User-specific thresholding schemes are investigated to improve the verification performance. The effectiveness of the proposed method is demonstrated through extensive experimentation on the FVC2002 set_a public database, in both identification and verification scenarios.     

关于数字混沌系统保密通信的探讨

本文对D.R.Frey(1993)提出的基于非线性递归数字滤波器的混沌保密通信系统的参数选取、适用条件、抗噪声能力以及保密能力等进行了分析,并采用混沌密码序列来提高该通信系统的保密性。模拟结果表明,该系统具有一定的可靠性和保密性,而且结构简单、容易实现。     

Frontalization and adaptive exponential ensemble rule for deep-learning-based facial expression recognition system

Automatic facial expression recognition (FER) is an important technique in human–computer interfaces and surveillance systems. It classifies the input facial image into one of the basic expressions (anger, sadness, surprise, happiness, disgust, fear, and neutral). There are two types of FER algorithms: feature-based and convolutional neural network (CNN)-based algorithms. The CNN is a powerful classifier, however, without proper auxiliary techniques, its performance may be limited. In this study, we improve the CNN-based FER system by utilizing face frontalization and the hierarchical architecture. The frontalization algorithm aligns the face by in-plane or out-of-plane, rotation, landmark point matching, and removing background noise. The proposed adaptive exponentially weighted average ensemble rule can determine the optimal weight according to the accuracy of classifiers to improve robustness. Experiments on several popular databases are performed and the results show that the proposed system has a very high accuracy and outperforms state-of-the-art FER systems.     

Permutation filter lattices: a general order-statistic filteringframework

A general nonlinear filtering framework-permutation order-statistic filter lattices is introduced which defines a highly modular and robust class of filters which effectively addresses both the nonlinear characteristics of a system as well as the possible noise contamination. Permutation filters, much like polynomial filters, are flexible and modular where instead of having polynomial expansions we have permutation lattice expansions. At the simplest level in the filter lattice, permutation filters reduce to either a simple linear (FIR) or to an order statistic (OS) filter, but at higher levels in the lattice the obtained filters can model complicated nonlinear systems more accurately while still preserving their robust properties. In order to enhance the robustness of permutation fitters, we develop α-trimmed permutation indicators and their associated filter lattices. We conclude by presenting simulation examples where permutation filters are used in nonlinear system identification and in the rejection of narrowband interference in a direct sequence multiple access system. This paper, thus extends the potential of order-statistic filters which have been shown to be somewhat limited in general nonlinear estimation problems     

层次轮廓计算机视角的交通道路标识别

随着我国科学技术的进一步优化,计算机视觉应用范围变得越来越广,尤其是交通道路路标识别中。但面对现阶段计算机视觉对交通路标识别存在的复杂性与不稳定性等问题,随之提出了通过图像轮廓识别技术运用的解决方法。同时,文章也将针对层次轮廓计算机视角的交通道路标识别进行研究,进而保证路标识别上的稳定性。     

Nonlinear adaptive bilinear filters for active noise control systems

The reference and error channels of active noise control (ANC) systems may be saturated in real-world applications if the noise level exceeds the dynamic range of the electronic devices. This nonlinear saturation degrades the performance of ANC systems that use linear adaptive filters with the filtered-X least-mean-square (FXLMS) algorithm. This paper derives a bilinear FXLMS algorithm for nonlinear adaptive filters to solve the problems of signal saturation and other nonlinear distortions that occur in ANC systems used for practical applications. The performance of this bilinear adaptive filter is evaluated in terms of convergence speed, residual noise in steady state, and the computational complexity for different filter lengths. Computer simulations verify that the nonlinear adaptive filter with the associated bilinear FXLMS algorithm is more effective in reducing saturation effects in ANC systems than a linear filter and a nonlinear Volterra filter with the FXLMS algorithm.