Palmprint Recognition by Applying Wavelet-Based Kernel PCA

This paper presents a wavelet-based kernel Principal Component Analysis (PCA) method by integrating the Daubechies wavelet representation of palm images and the kernel PCA method for palmprint recognition. Kernel PCA is a technique for nonlinear dimension reduction of data with an underlying nonlinear spatial structure. The intensity values of the palmprint image are first normalized by using mean and standard deviation. The palmprint is then transformed into the wavelet domain to decompose palm images and the lowest resolution subband coeffcients are chosen for palm representation. The kernel PCA method is then applied to extract non-linear features from the subband coeffcients. Finally, similarity measurement is accomplished by using weighted Euclidean linear distance-based nearest neighbor classifier. Experimental results on PolyU Palmprint Databases demonstrate that the proposed approach achieves highly competitive performance with respect to the published palmprint recognition approaches.     

Kernel-based nonlinear discriminant analysis for face recognition

Linear subspace analysis methods have been successfully applied to extract features for face recognition.But they are inadequate to represent the complex and nonlinear variations of real face images,such as illumination,facial expression and pose variations,because of their linear properties.In this paper,a nonlinear subspace analysis method,Kernel-based Nonlinear Discriminant Analysis (KNDA),is presented for face recognition,which combines the nonlinear kernel trick with the linear subspace analysis method-Fisher Linear Discriminant Analysis (FLDA).First,the kernel trick is used to project the input data into an implicit feature space,then FLDA is performed in this feature space.Thus nonlinear discriminant features of the input data are yielded.In addition,in order to reduce the computational complexity,a geometry-based feature vectors selection scheme is adopted.Another similar nonlinear subspace analysis is Kernel-based Principal Component Analysis (KPCA),which combines the kernel trick with linear Principal Component Analysis (PCA).Experiments are performed with the polynomial kernel,and KNDA is compared with KPCA and FLDA.Extensive experimental results show that KNDA can give a higher recognition rate than KPCA and FLDA.     

Halftoning based algorithms for image hiding

Digital halftoning is an important process to convert a continuous-tone image into a binary image with pure black and white pixels. This process is necessary when printing a monochrome or color image by a printer with limited number of ink colors. The main contribution of this paper is to present a halftoning method that conceals a binary image into two binary images. More specifically, three distinct gray scale images are given, such that one of them should be hidden in the other two gray scale images. Our halftoning method generates three binary images that reproduce the tone of the corresponding original three gray scale images. Quite surprisingly, the secret binary image can be seen by overlapping the other two binary images. In other words, the secret binary image is hidden in two public binary images. Also, it is very hard to guess the secret images using only one of the two public images, and both of these two public images are necessary to get the secret image. Another contribution of this paper is to extend our halftoning method to hide one image and more than one image into more than two images. The resulting images show that our halftoning method hides and recovers the original images. Hence, our halftoning technique can be used for watermarking as well as amusement purpose.     

Vehicle license plate character segmentation

Vehicle license plate (VLP) character segmentation is an important part of the vehicle license plate recognition system (VLPRS). This paper proposes a least square method (LSM) to treat horizontal tilt and vertical tilt in VLP images. Auxiliary lines are added into the image (or the tilt-corrected image) to make the separated parts of each Chinese character to be an interconnected region. The noise regions will be eliminated after two fusing images are merged according to the minimum principle of gray values.Then, the characters are segmented by projection method (PM) and the final character images are obtained. The experimental results show that this method features fast processing and good performance in segmentation.     

Phase Correlation Based Iris Image Registration Model

Iris recognition is one of the most reliable personal identification methods. In iris recognition systems, image registration is an important component. Accurately registering iris images leads to higher recognition rate for an iris recognition system. This paper proposes a phase correlation based method for iris image registration with sub-pixel accuracy. Compared with existing methods, it is insensitive to image intensity and can compensate to a certain extent the non-linear iris deformation caused by pupil movement. Experimental results show that the proposed algorithm has an encouraging performance.     

Movie Scene Recognition Using Panoramic Frame and Representative Feature Patches简

Recognizing scene information in images or has attracted much attention in computer vision or videos, such as locating the objects and answering ＂Where am research field. Many existing scene recognition methods focus on static images, and cannot achieve satisfactory results on videos which contain more complex scenes features than images. In this paper, we propose a robust movie scene recognition approach based on panoramic frame and representative feature patch. More specifically, the movie is first efficiently segmented into video shots and scenes. Secondly, we introduce a novel key-frame extraction method using panoramic frame and also a local feature extraction process is applied to get the representative feature patches （RFPs） in each video shot. Thirdly, a Latent Dirichlet Allocation （LDA） based recognition model is trained to recognize the scene within each individual video scene clip. The correlations between video clips are considered to enhance the recognition performance. When our proposed approach is implemented to recognize the scene in realistic movies, the experimental results shows that it can achieve satisfactory performance.     

Vessel Extraction on Ocular Fundus Images by Using Gabor Filter Bank

Fundus diagnosis is an important part of the whole body examination that may provide rich clinical information to doctors for diagnostic reference. Manual fundus vessel extraction is helpful to quantitative measurement of diseases but obviously it is a tough work for physicians. This paper presents an automatic method by using Gabor filter bank to extract the artery and vein separately in the ocular fundus images. After preprocessing steps that include gray-scale transform, gray value inversion and contrast enhancement, the Gabor filter bank is applied to the extraction of the artery and vein in the ocular fundus images. Finally these two different width types of vessels are selected by post-processing methods such as labeling, corrosion, binarization, etc. Evaluation results show an accurate rate of 90% in vein and 82% in artery from 20 cases, that indicates the effectiveness of our proposed segmentation method.     

Thermodynamics-inspired inverse halftoning viamultiple halftone images

Based on an analogy between thermodynamics and Bayesian inference,inverse halftoning was formulated using multiple halftone images based on Bayesian inference using the maximizer of the posterior marginal(MPM) estimate.Applying Monte Carlo simulation to a set of snapshots of the Q-Ising model,it was demonstrated that optimal performance is achieved around the Bayes-optimal condition within statistical uncertainty and that the performance of the Bayes-optimal solution is superior to that of the maximum-a-posteriori(MAP) estimation which is a deterministic limit of the MPM estimate.These properties were qualitatively confirmed by the mean-field theory using an infinite-range model established in statistical mechanics.Additionally,a practical and useful method was constructed using the statistical mechanical iterative method via the Bethe approximation.Numerical simulations for a 256-grayscale standard image show that Bethe approximation works as good as the MPM estimation if the parameters are set appropriately.     

Evaluating the performance of a EuroDivisia index using artificial intelligence techniques

This paper compares two methods to predict inflation rates in Europe. One method uses a standard back propagation neural network and the other uses an evolutionary approach, where the network weights and the network architecture are evolved. Results indicate that back propagation produces superior results. However, the evolving network still produces reasonable results with the advantage that the experimental set-up is minimal. Also of interest is the fact that the Divisia measure of money is superior as a predictive tool over simple sum.     

Clustering mechanism for electric tomography imaging

Electrical tomography(ET) imaging,developed in the 1980s,has attracted much industrial and research attentions owing to its low cost,quick response,lack of radiation exposure,and non-intrusiveness compared to other tomography modalities.However,to date applications thereof have been limited owing to its low imaging resolution.The issue with space resolution in existing ET imaging reconstruction methods is that they employ a mathematical approach based on an ill-posed equation with inconsistent solutions.In this paper,we propose a novel ET imaging method based on a data-driven approach.By recovering the cluster structures hidden in the ET imaging process followed by the application of a fuzzy clustering algorithm to identify the cluster structures,there is no need to study the ill-posed mathematical formulation.The proposed method has been tested by means of three experiments,including image reconstructions of a human lung image and plastic rode shape,as well as two simulations executed on the Comsol platform.The results show that the proposed method can reconstruct ET images with much higher space resolution more quickly than the existing algorithms.     

Online face recognition system based on multi-view algorithm and Kernel PCA

An online face recognition system is presented in the paper. To online face recognition system, we should consider the recognition rate, the image compression and image size. In the paper we researched the innovation technologies for face recognition system, including Kernel Principal Component Analysis （Kernel PCA）, Delta low-pass wavelet filter, and face recognition algorithm using multiple images. Kernel PCA is derived to classify the characteristics of training images in the database. Delta low-pass wavelet filter is used to reduce the image size. A face recognition algorithm using multiple images is presented to improve the recognition rate. Simulation experiment shows that in the case of packet loss recognition rate is improved highly.     

Unified probabilistic models for face recognition from a single example image per person

This paper presents a new technique of unified probabilistic models for face recognition from only one single example image per person. The unified models, trained on an obtained training set with multiple samples per person, are used to recognize facial images from another disjoint database with a single sample per person. Variations between facial images are modeled as two unified probabilistic models: within-class variations and between-class variations. Gaussian Mixture Models are used to approximate the distributions of the two variations and exploit a classifier combination method to improve the performance. Extensive experimental results on the ORL face database and the authors‘ database (the ICT-JDL database) including totally 1,750 facial images of 350 individuals demonstrate that the proposed technique, compared with traditional eigenface method and some well-known traditional algorithms, is a significantly more effective and robust approach for face recognition.     

An FPGA-based face recognition using combined 5/3 DWT with PCA methods

This paper describes a new scheme for feature extraction from facial images on FPGA. The proposed method is comprised of two stages. The first stage uses the 5/3 DWT to decompose the original face image into LL, LH, HL, and HH wavelet coefficient to reduce the size of the image. In the second stage, PCA is employed to extract the face features from the wavelet coefficients. Here we use the power iteration algorithm to find the eigenvector of the covariance matrix. We present an efficient hardware architecture using combination of parallel processing module and serial processing module. This method can take the benefits of parallel usage advantage of FPGAs and can save hardware resources. Complete hardware implemented on a Stratix II FPGA. The experimental results show that the system works with high processing rate and only 21% of the logic resources an FPGA are consumed by face recognition logic Thus it is very suitable for the low cost implementation of the face recognition system.     

The Supervised Learning Gaussian Mixture Model

The traditional Gaussian Mixture Model(GMM)for pattern recognition is an unsupervised learning method.The parameters in the model are derived only by the training samples in one class without taking into account the effect of sample distributions of other classes,hence,its recognition accuracy is not ideal sometimes.This paper introduces an approach for estimating the parameters in GMM in a supervising way.The Supervised Learning Gaussian Mixture Model(SLGMM)improves the recognition accuracy of the GMM.An experimental example has shown its effectiveness.The experimental results have shown that the recognition accuracy derived by the approach is higher than those obtained by the Vector Quantization(VQ)approach,the Radial Basis Function (RBF) network model,the Learning Vector Quantization (LVQ) approach and the GMM.In addition,the training time of the approach is less than that of Multilayer Perceptrom(MLP).     

A new maximum-likelihood phase estimation method for X-ray pulsar signals

X-ray pulsar navigation （XPNAV） is an attractive method for autonomous navigation of deep space in the future. Currently, techniques for estimating the phase of X-ray pulsar radiation involve the maximization of the general non-convex object functions based on the average profile fxom the epoch folding method. This results in the suppression of useful information and highly complex computation. In this paper, a new maximum likelihood （ML） phase estimation method that directly utilizes the measured time of arrivals （TOAs） is presented. The X-ray pulsar radiation will be treated as a cyclo-stationary process and the TOAs of the photons in a period will be redefined as a new process, whose probability distribution function is the normalized standard profile of the pulsar. We demonstrate that the new process is equivalent to the generally used Poisson model. Then, the phase estimation problem is recast as a cyclic shift parameter estimation under the ML estimation, and we also put forward a parallel ML estimation method to improve the ML solution. Numerical simulation results show that the estimator described here presents a higher precision and reduces the computational complexity compared with currently used estimators.     

Automatic façade recovery from single nighttime image

Nighttime images are difficult to process due to insufficient brightness,lots of noise,and lack of details.Therefore,they are always removed from time-lapsed image analysis.It is interesting that nighttime images have a unique and wonderful building features that have robust and salient lighting cues from human activities.Lighting variation depicts both the statistical and individual habitation,and it has an inherent man-made repetitive structure from architectural theory.Inspired by this,we propose an automatic nighttime fa?ade recovery method that exploits the lattice structures of window lighting.First,a simple but efficient classification method is employed to determine the salient bright regions,which may be lit windows.Then we groupwindows into multiple lattice proposals with respect to fa?ades by patch matching,followed by greedily removing overlapping lattices.Using the horizon constraint,we solve the ambiguous proposals problem and obtain the correct orientation.Finally,we complete the generated fa?ades by filling in the missing windows.This method is well suited for use in urban environments,and the results can be used as a good single-view compensation method for daytime images.The method also acts as a semantic input to other learning-based 3D image reconstruction techniques.The experiment demonstrates that our method works well in nighttime image datasets,and we obtain a high lattice detection rate of 82.1%of 82 challenging images with a low mean orientation error of 12.1±4.5 degrees.     

Precise recognition of warhead and decoy based on components of micro-Doppler frequency curves

From the view of electromagnetic scattering,it is indicated that the micro-Doppler (m-D) character-istics of an extended target undergoing micro-motions are actually induced by the change of incident directions of radar pulses.Different micro-motions may lead to similar change of incident directions,consequently inducing similar m-D characteristics.To tackle this problem,rather than distinguish warhead and decoy directly from m-D characteristics,the frequency components of m-D frequency curves are used as a new characteristic for recognition in this paper.To get high precision of frequency components estimation,model-based parameter estimation (MBPE) is utilized to extract the m-D frequency curves from TFR.To obtain high accurate simu-lation results,the backscattered signal simulation is conducted by full-wave numerical method.The simulation results validate the theoretical analysis and the high performance of the proposed method.     

Extraction of spatial-temporal features for vision-based gesture recognition

One of the key problems in a vision-based gesture recognition system is the extraction of spatial-temporal features of gesturing.In this paper an approach of motion-based segmentation is proposed to realize this task.The direct method cooperated with the robust M-estimator to estimate the affine parameters of gesturing motion is used.and based on the dominant motion model the gesturing region is extracted,i.e.,the dominant object.So the spatial-temporal features of gestrues can be extracted.Finally,the dynamic time warping(DTW) method is directly used to perform matching of 12 control gestures(6 for “translation“ orders,6 for “rotation“orders).A small demonstration system has been set up to verify the method,in which a panorama image viewer can be controlled(set by mosaicing a sequence of standard“Garden“ images)with recognized gestures instead of the 3-D mouse tool.     

Gene selection in class space for molecular classification of cancer

Gene selection (feature selection) is generally pertormed in gene space(feature space), where a very serious curse of dimensionality problem always existsbecause the number of genes is much larger than the number of samples in gene space(G-space). This results in difficulty in modeling the data set in this space and the lowconfidence of the result of gene selection. How to find a gene subset in this case is achallenging subject. In this paper, the above G-space is transformed into its dual space,referred to as class space (C-space) such that the number of dimensions is the verynumber of classes of the samples in G-space and the number of samples in C-space isthe number of genes in G-space. it is obvious that the curse of dimensionality in C-spacedoes not exist. A new gene selection method which is based on the principle of separatingdifferent classes as far as possible is presented with the help of Principal ComponentAnalysis (PCA). The experimental results on gene selection for real data set areevaluat     

Level Set method for license plate localization technology

Localization of license plate is an important factor in license plate recognition system. Currently although there are some methods for the localization, some limits such as low accuracy exist. So a better method should be found to solve this problem. Level Set, which has been proved efficient currently, gives new prospect to license plate localization. In this paper, based on the original thought of Level Set method, the Mumford-Shah model with Level Set method is obtained, further the finite difference and a third order TVD （Total Variation Diminishing） Runge-Kutta time discretization scheme is analyzed, and applied in license plate image localization. Computation results show that better edge detection results from level set method are obtained compared to other edge detection methods such as Roberts, Sobel and Canny. Level Set method drops much edge of non-target area which has a lot of value to target edge detection and target position tracking.