Search

Recently the method restoring an old picture using the local differential equation on the basis of the geometric measure is proposed. It is necessary to restore an old film and a medical image with noise as well as an old picture. So we extend the method applying for the two dimentional image such as a picture to the three dimensional image such as a time sequence image and a medical image. It is necessary to obtain an object boundary from the original image in order to generate a composite image of good quality, which is difficult to distinguish from the original image. If an object boundary can not be detected, it is difficult to remove the object. In this study, we propose a method for detecting an object boundary and removing it and inpainting its image in a manner that makes it difficult to distinguish from the original image. We extend the image partition method based on the level set method to the method applying for the movie and the medical image to detect an object boundary. We demonstrate its effectiveness by removing a terop from a movie and a tumor from a three dimensional medical image. [ABSTRACT FROM AUTHOR]

Cervical cancer is the second most common cancer among women worldwide. Early detection of cervical cancer is very important for successful treatment and increasing survival. We report a spectral imaging microscopic system for Papanicolaou smear analysis for early detection of cervical cancer. Different from traditional color imaging method, we use spectral imaging techniques for image acquisition, which can simultaneously record spectral and spatial information of a sample. In this paper, the imaging instrument construction and spectral image acquisition method is introduced. In the image segmentation process, an effective algorithm using spectral ratio method is applied for cell nuclei detection, which can easily detect the nuclei and diminish the influence of the cytoplasm overlap. Results showed that our segmentation is robust and precise. In addition to this, the segmentation speed is very high. Keywords: Cervical cell, spectral imaging, spectral image segmentation. [ABSTRACT FROM AUTHOR]

We present a new local obstacle avoidance approach for mobile robots in partially known environments on the basis of the curvature-velocity method (CVM), the lane-curvature method (LCM) and the beam-curvature method (BCM). Not only does this method inherit the advantages from both BCM and LCM, but also it combines the prediction model of collision with BCM perfectly so that the so-called prediction based BCM (PBCM) comes into being and can be used to avoid moving obstacles in dynamic environments. [ABSTRACT FROM AUTHOR]

In this paper we first give a new method of time series model to forecast GDP of China. The method proposed here aims to emphasis the importance of the impact of STEP-Affair on the GDP forecasting. The superiority of the method to ARMA model is illustrated in an example presented accordingly. Then in the system of whole economic when the GDP forecasted above is given, how can we allocate the limited resources to make the economical behavior relative efficient. We use data envelopment analysis to show how to determine input interval. Each input among the input interval as well as the given output constitute an efficient decision making unit (DMU). For decision makers the techniques are very important in decision making, especially in macroeconomic policies making in China. [ABSTRACT FROM AUTHOR]

The purpose of this paper is to investigate the use of hybrid intelligent control to aircraft automatic landing system. Current flight control law is adopted in the intelligent controller design. Tracking performance and adaptive capability are demonstrated through software simulations. Two control schemes that use neural network controller and neural controller with particle swarm optimization are used to improve the performance of conventional automatic landing system. Control gains are selected by particle swarm optimization. Hardware implementation of this intelligent controller is performed by DSP with VisSim platform. The proposed intelligent controllers can successfully expand the controllable environment in severe wind disturbances. [ABSTRACT FROM AUTHOR]

In this paper we introduce negation into Logical Markov Decision Processes, which is a model of Relational Reinforcement Learning. In the new model nLMDP the abstract state space can be constructed in a simple way, so that a good property of complementarity holds. Prototype action is also introduced into the model. A distinct feature of the model is that applicable abstract actions can be obtained automatically with valid substitutions. Given a complementary abstract state space and a set of prototype actions, a model-free Θ-learing method is implemented for evaluating the state-action-substitution value funcion. [ABSTRACT FROM AUTHOR]

Management software is required to be adaptive and scalable since the managed objects become more and more dynamic and complex. In this paper, we introduce cognitive concepts to deal with the complexity in developing management software, and an interactive intelligent agency framework, called iSMAcy (intelligent System Management Agency), is developed as an integrated solution to realize adaptive system management. The cognitive concepts are applied at two levels. At micro level, the intentional agent kernel of functional agent use mental states such as beliefs, goals and intentions to realize integration of goal-directed behavior with situated reactive action. At macro level, high-level cognitive semantics such as goals, requests and commitments are interchanged among agents. An example of applying iSMAcy system on a simulated network management environment is described, and the efficiency of the intentional agent kernel is analyzed to ensure the reactivity of iSMAcy system. [ABSTRACT FROM AUTHOR]

Stochastic Shortest Path problems (SSPs), a subclass of Markov Decision Problems (MDPs), can be efficiently dealt with VI, PI, RTDP, LAO* and so on. However, in many practical problems the estimation of the probabilities is far from accurate. In this paper, we present uncertain transition probabilities as close real intervals. Also, we describe a general algorithm, called gLAO*, that can solve uncertain MDPs efficiently. We demonstrate that Buffet and Aberdeen's approach, searching for the best policy under the worst model, is a special case of our approaches. Experiments show that gLAO* inherits excellent performance of LAO* for solving uncertain MDPs. [ABSTRACT FROM AUTHOR]

A new two-stage optimization model for mobile agent routing in the wireless sensor network is presented as a integer linear programming problem based on the virtual connection topology sub graph. In the model, the solution is presented by two subpaths instead of the closed path which is usually applied in many path search methods to keep balance between computation cost and accuracy. A hybrid technique of genetic algorithm (GA) integrated with discrete particle swarm optimization (PSO), GAPSO is designed to solve the problem. Simulation experiments with different sizes and distributions of nodes show the effectiveness of the new model and GAPSO algorithm. [ABSTRACT FROM AUTHOR]

We consider the generalized regularization problem of Shape-from- Shading. The traditional algorithms are to find the minimum point of the optimization problem where the regularization term is considered as the part of the objective function. However, the result of regularization may deviate from the true surface, due to the ill-posedness of the SFS problem. In this paper, we propose a novel method to solve this problem. The algorithm consists of two steps. In the first step, we recover the components of the surface in the range space of the transpose of the system matrix, from the observed image by using the Landweber iteration method, where the Pentland's linear SFS model is adopted without any regularization. In the second step, we represent the regularization condition as an energy spline in the Fourier domain, and find the minimum value of the energy function with respect to the components of the surface in the null space of the system matrix. Quantitative and visual comparisons, using simulated data of a fractal and smooth surface, show that the proposed method significantly outperforms the Horn, Zheng-Chellappa, Tsai-Shah and Pentland linear methods for surface reconstruction. [ABSTRACT FROM AUTHOR]

A low-cost infrared and Neuro-Fuzzy-based approach for identification and classification of road markings is presented in this paper. The main task of the designed prototype, implemented at the University of La Laguna, is to collect information by a set of infrared sensors and to process it in an intelligent mode. As an example, it should inform the driver about the different signs and elements it is driving on, complementing other well-known and widely used security devices. For the identification and classification stages, a Neuro-Fuzzy approach has been chosen; given it is a good option in order to get fuzzy rules and memberships functions in an automatic way. [ABSTRACT FROM AUTHOR]

Though there have been proposed many magnification works in literatures, magnification in this paper is approached as reconstructing the geometric structures of the original high-resolution image. The structure tensor is able to estimate the orientation of both the edges and flow-like textures, which hence is much appropriate to magnification. Firstly, an edge-enhancing PDE and a corner-growing PDE are respectively proposed based on the structure tensor. Then, the two PDE's are combined into a novel one, which not only enables to enhance the edges and flow-like textures, but also to preserve the corner structures. Finally, the novel PDE is applied to image magnification. The method is simple, fast and robust to both the noise and the blocking-artifact. Another novelty in the paper is the application of the novel PDE to super-resolution reconstruction, plus additional term for image fidelity. Experiment results demonstrate the effectiveness of our approach. [ABSTRACT FROM AUTHOR]

The high performance cryptographic chip is the core unit of the network information safety equipments. This paper proposes the design approach of the AES cryptographic system based on reconfigurable hardware, develops the method of key-sequence generation with the genetic algorithm that realizes different cipher key in every encryption round. The system has been implemented on Virtex-E FPGA. The result proves that the new design technology is feasible, and the security level of the AES is improved. [ABSTRACT FROM AUTHOR]

Compared with traditional Back Propagation (BP) neural network, the advantages of fuzzy neural network in fault diagnosis are analyzed. A new diagnosis method based on genetic algorithm (GA) and fuzzy Radial Basis Function (RBF) neural network is presented for complicated machinery system. Fuzzy membership functions are obtained by using RBF neural network, and then genetic algorithm is applied to train fuzzy RBF neural network. The trained fuzzy RBF neural network is used for fault diagnosis of ship main power system. Diagnostic results indicate that the method is of good generalization performance and expansibility. It can significantly improve the diagnostic precision. [ABSTRACT FROM AUTHOR]

This paper reports the implementation of an SoC (System on a Chip) IP(Intellectual Property) design for an Image Grabber that is capable of 2D scanning. The vast improvements in integrated circuit technology and semiconductor industry have allowed complicated hardware systems to be implemented into a single Chip. Previously, hardware designed by external buses was slow. However, the speed of the system has been improved by peripheral logics that are designed on a single chip. In addition, both hardware and software can be constructed together resulting in a significant decrease in research and development time. Four IPs were created in this study. I2C IP was developed for the Image Decoder. The NTSC analog signal from a CCD camera was converted to YUV422 using an image decoder and stored in a frame buffer by IMAGE IP. TFT-LCD IP was developed to display the data on an LCD. A robot IP was developed to control a perpendicular coordinate robot. Finally, system level software and PC software was developed to examine the SoC system. Keywords: SoC, IMAGE IP, Perpendicular Coordinate Robot IP, TFT-LCD IP. [ABSTRACT FROM AUTHOR]

In this paper the effect of steady and relaxation oscillation in optical fiber based on neural networks and hardware implementation is described. The inherent optical feedback by the backscattered Stokes wave in optical fiber leads to instabilities in the form of optical chaos. The controlling of chaos induced transient instability in Brillouin-active fiber based smart structures leads to neural networks with steady and relaxation oscillations. Controlled chaotic instabilities can be used for optical logic and computations and optical sensing. It is theoretically possible to apply the multi-stability regimes as an optical memory device for encoding and decoding and complex data transmission in optical systems. These memories can be estimated as an optical logic function used for all-optic in-line switching, channel selection, oscillation, optical logic elements in optical computation with neural network application. [ABSTRACT FROM AUTHOR]

This paper presents a miniature device, which is used for stimulating to and recording from the brain of an animal, based on system on chip (nRF24E1). Its performance is validated by in vivo experiments, in which rats are trained to run down a maze to respond to auditory instruction cues by turning right or left in order to get an electrical stimulation ‘virtual reward', and by comparing spikes recorded from the brain of rats between our device and a commercially available device (Spike2, Cambridge Electronic Design Ltd.). Results show that our device can work reliably and stably, and with notable characteristics of light weight (9g, without battery), simplicity and practicality. [ABSTRACT FROM AUTHOR]

To satisfy the requirement of embedded video encoder in various scenarios, an embedded universal video coding system based on embedded processors is proposed in this paper, which combines the advantages of multi processors in single architecture. According to different channels, two feasible solutions are given to avoid the overflow and underflow of buffer while transmitting the compressed data. Due to limited computational resources and real-time application requirement, each module of the MPEG-4 codec is reviewed and efficiently implemented based on the embedded hardware platform. Experimental results show that the embedded system can successfully be used for real-time application. [ABSTRACT FROM AUTHOR]

This paper presents a new technique for solving the unsupervised clustering problem using a pulse based RBF neural network that is optimized by a genetic algorithm. In this new approach, the neuron encodes the information using the firing times of pulses that are generated by the neurons. Due to hardware's speed advantage and its ability to parallelize along with reprogramability and reconfigurability, the field programmable gate array (FPGA) is used for implementing the proposed approach on-chip. The developed on-chip system is capable of solving various problems requiring large data set in real time. Experimental verification using a sample data set and Fisher's Iris data set has shown the feasibility of the developed system. [ABSTRACT FROM AUTHOR]

Semiconductor Technology and multimedia communication has been developed to interest in high quality video and multi channels audio. Especially, it is trend to important technology so that DVD market grows rapidly. Mpeg audio standard is available support for any bit rate. In this paper, the design of Field Programmable Gate Array(FPGA) is presented mpeg audio synthesis filter by Distributed Arithmetic Look Up Table(DALUT) method. In order to design for high speed filter that operated from 10MHz to 30MHz and DALUT is used instead of multiplier. In this paper, the output is designed by VHDL and is verification using C language. VHDL simulation used Model-sim SE 5.7f and synthesis is used Synplify Pro 7.2Ver. Target library is used XC4010E, XC4020EX, XC4052XL and P&R tool used XACT M1.4. [ABSTRACT FROM AUTHOR]

This paper proposes a low-power high-speed CMOS analog two- input/one-output neuro-fuzzy chip, the basic blocks of which are Gaussian membership function circuit, minimization circuit, and a centroid algorithm defuzzification circuit. This chip has been fabricated in 0.6-μm mixed-signal CMOS technology. Experiment and HSPICE simulation results show that because the compact structures and high-precision of the blocks the system not only consumes little power but also can be directly tuned by the weights calculated through the software such as Matlab. [ABSTRACT FROM AUTHOR]

This paper suggests a brokering process in which individual truckers participate in the process of matching trucks with freight. To maximize the total profit of trucks, a mathematical model is formulated for matching trucks with freight. It is shown that, by Lagrangean relaxation, the matching problem can be decomposed into a master problem and multiple sub-problems. This paper proposes a brokering process, based on the subgradient optimization technique, in which an optimality of individual truckers as well as the system optimality of truckers is satisfied. The effects of various practical considerations on the performance of the suggested brokering process are tested numerically and by using a simulation study. [ABSTRACT FROM AUTHOR]

This paper proposed a novel method of applying support vector machine for multi-class problem based on fuzzy integral. Firstly, the fuzzy measure of each binary classifier is constructed based on its classification accuracy during training and its agreement degrees to other support vector machines. Then the testing instances are classified by calculating the fuzzy integral between the fuzzy measures and the outputs of the binary support vector machines. The experiment results on iris and glass datasets from UCI machine learning repository and real plane dataset show that the new method is effective. And the experiment results ulteriorly indicate that the method with Choquet fuzzy integral has better performance than that with Sugeno integral. [ABSTRACT FROM AUTHOR]

Web forums and online communities are becoming increasingly important information sources. While there are significant research works on classification of Web pages, relatively less is known on classification of online discussions. By observing the special nature of user participation in web communities, we propose classification methods based on user participation and text content of online discussions. Support vector machines have been employed in this study to classify and analyze discussions based on content and participation. It is found that the accuracy of using participation as classification features can be very high in certain communities. The use of high-dimensional classifier can be effective in enhancing retrieval and classification of online discussion topics. Keywords: Online community, support vector machine, information retrieval, feature extraction, classification. [ABSTRACT FROM AUTHOR]

Based on multiwavelet transform and the clonal selection theory in the natural immune system, a novel pixel-level multifocus image fusion optimization algorithm is presented in this paper. Source images are first decomposed into low-frequency coarse information and high-frequency detail information via discrete multiwavelet transform. The high-frequency detail information adopts the absolute-values maximum selection. And then the immune clonal selection is introduced to optimize the weights of fusing the low-frequency four coarse subbands adaptively and separately. Image fusion performances of Daubechies-4 (Db4) scalar wavelet, Geronimo, Hardin and Massopust (GHM) multiwavelets and Chui and Lian (CL) multiwavelets are compared quantitatively, which have the same approximation order. Experimental results show that the proposed image fusion algorithm have clear edges, abundance details and few artificial artifacts. [ABSTRACT FROM AUTHOR]

Two-dimensional computations of the propagation of the explosion wave in a mixture of hydrogen and oxygen are performed using WENO finite difference scheme with fifth order accuracy and two-step chemical reaction model. Numerical results show that obstacles setting repeatedly along the path of the flame propagation process obviously can accelerate the flame. The mechanism of the accelerating effect is attributed to the positive feedback of the turbulence region induced by obstacles for combustion process. [ABSTRACT FROM AUTHOR]

Many researches on path planning and obstacle avoidance for the fundamentals of mobile robot have been done. Although many solutions help finding a optimal path, those can be applied to real world only under constrained condition, which means that it is difficult to find a universal algorithm. Moreover, a complicated computation to obtain an optimal path induces the time delay so that a robot can not avoid moving obstacles. In this paper, we propose the algorithm of path planning and obstacle avoidance using Random Access Sequence(RAS) methodology. In the proposed scheme, the cell decomposition is make first and cell neighbors are assigned as sequence code, then the path with minimum length is selected. [ABSTRACT FROM AUTHOR]

A series of high order Mandelbrot and Julia fractal images of complex map $f:z\leftarrow{\mathcal{}z}^n+c(n>2,n\in{N}) $ are constructed by using escape time algorithm. Topology invariance and the relation between period bud distribution and mapping orders are found through lots of computer mathematic experiments. The escape time algorithm is improved on basis of the rotation symmetric property of Manderlbrot and Julia sets, and then a rotation escape time algorithm is established. The high-order Mandelbrot and Julia sets fractal images are generated by using Web oriented Java Applet. Therefore the complexity of computer simulation under complex conditions is greatly reduced. The application of Java technology provides an Internet-based distribution platform for chaos-fractal theory study. [ABSTRACT FROM AUTHOR]

Most texture-based image retrieval system just consider an original image of coarseness, contrast and roughness, actually there are many texture information in the edge image. In this paper, a method combining both edge information and gray level co-occurrence matrix properties is proposed to improve the retrieval performance. The proposed method gives encouraging results when comparing its retrieval performance to that of the Yao's method, in the same image database. [ABSTRACT FROM AUTHOR]

It proposes a chaotic secure communication scheme by introducing a concept of key function (KF) and key initial conditions (KICs). By using KF, secret signal is combined with complex chaotic signal in order to enhance the security of transmitted signal. KICs are used to enlarge minor mismatch of drive signal so as to increase initial conditions sensitivity of the auxiliary driver system. Experiment results show that proposed cryptosystems are very sensitive to KICs' and KFs' mismatch. [ABSTRACT FROM AUTHOR]

The physical flame characteristics in the burning process are analyzed in detail. Combined with static and dynamic flame features, a flame detection algorithm based on multi-feature fusion is designed to quickly recognize fire flame using the theory of the degree of belief. The experiments show that the processing rate of the algorithm is as high as 25 frames/s without any manual adjustments. In complex situations, the algorithm remains with stronger anti-jamming ability and higher accuracy, for example, the suspected probability of street lamps and automotive lamps is lower than 10%. From comparing results, the video-based detection algorithm has the good capabilities. [ABSTRACT FROM AUTHOR]

When converting image sequence to 3D, several entries of the matrix have not been observed by occlusions and other entries have been perturbed by the influence of noise. In this paper, we propose a method for fitting geometrically missing data in noisy observation matrix with iterative SVD factorization. The main idea of the proposed algorithm is that the orientation and distance of noisy vector ca be handled directly by geometrical properties between 2D image plane and 3D error space under noise distribution. To confirm the recoverability of missing data, we carry out the experiments for synthetic and real sequences. The results in practical situations demonstrated with synthetic and real video sequences verify the efficiency and flexibility of the proposed method. [ABSTRACT FROM AUTHOR]

In this paper, we present a new method of SAR imagery compression based on multiscale autoregressive moving average (MARMA) models. We use the multiscale representation as the cornerstone of the modeling process, and construct the MARMA models of SAR image. We then predict the initialized image data using these multiscale models. Next we compress image data through coding the residual image. Extension simulations have proven that the proposed method achieves high compression radios with impressive image quality. [ABSTRACT FROM AUTHOR]

A new Fourier-wavelet volume rendering algorithm (FWVR) in frequency domain is presented and corresponding preprocessing is given in this paper. After the wavelet transforming and obtaining slice plane, FWVR finish the volume rendering image with a wavelet-based X-ray rending method in the frequency domain. FWVR comprises and unifies the advantages of recently introduced Fourier domain volume rendering techniques and wavelet based volume rendering. For the algorithm is based on the CT imaging and wavelet transformation, the time complexity of this method is O(N2logN) which is reduced apparently. Experiment of medicine volume data shows that this method is efficient. Finally, the potential application of FWVR is introduced in network rendering for saving transmission time. [ABSTRACT FROM AUTHOR]

As an effective method of background subtraction, codebook model suffers from unacceptable false negative detection rate in many situations due to its quantization criterion. In this paper, we propose an improved codebook model to solve this problem. Instead of using the original quantization criterion, we quantize the temporal series of the observations at a given pixel into codewords based on the Gaussian distribution assumption. We have performed this approach in our surveillance system for outdoor scenes and achieved excellent detection results. [ABSTRACT FROM AUTHOR]

Stack filters are often employed for suppressing the pulse noise. In general, the larger sizes the stack filters are, the better results are. Unfortunately, available algorithms for designing stack filters can only be suit for small window sizes due to their huge computational complexities. This paper presents a new fast adaptive algorithm for designing a stack filter with large windows. The idea of the new algorithm is to divide a lager window into many sub-windows. The procedures of dividing a large window are given. An Immune Memory Clonal Selection Algorithm is employed to design the stack filters with small window sizes. Because of its highly parallel structure, it can be very fast implemented. As an experiment, the algorithm was used to restore images corrupted by uncorrelated additive noise with the level from 10% to 50 %. The results show that the algorithm is effective and feasible. [ABSTRACT FROM AUTHOR]

The Ant Colony Optimization has gained great success in applications to combinatorial optimization problems, but few of them are proposed in the continuous domain. This paper proposes an ant algorithm, called Direct Ant Colony Optimization (DACO), for the function optimization problem in continuous domain. In DACO, artificial ants generate solutions according to a set of normal distribution, of which the characteristics are represented by pheromone modified by ants according to the previous search experience. Experimental results show the advantage of DACO over other ACO based algorithms for the function optimization problems of different characteristics. Keywords: Ant Colony Optimization, Function Optimization Problem, Continuous Domain. [ABSTRACT FROM AUTHOR]

A new method of the Road extraction in synthetic aperture radar (SAR) image is proposed in this paper. Roads in a high resolution SAR image can be modeled as a homogeneous dark area bounded by two parallel lines. The fundamental is based on linear extraction and improved Hough transform. Combining Hough transform and the partition of the line, the problem of location of line segments was solved. The improved Hough transform is tested on synthetic images and noisy images. The experimental results show the method's validity. Keywords: road extraction, Hough Transform, SAR image. [ABSTRACT FROM AUTHOR]

This paper proposes a novel filtering method for removing such speckle noise from Synthetic Aperture Radar image that combines the Stationary Tree-structured Wavelet Transform (STWT) with a Bayesian wavelet estimator. Experimental results on several test images by using the proposed method show that, the proposed method yields significantly superior image quality and better Peak Signal to Noise Ratio (PSNR). [ABSTRACT FROM AUTHOR]

In this paper, we introduce a new multiobjective optimization (MO) algorithm to solve ZDT test problems using the immune clonal principle. This algorithm is termed Immune Clonal MO Algorithm (ICMOA). In ICMOA, the antibody population is split into nondominated antibodies and dominated antibodies. Meanwhile, the nondominated antibodies are allowed to survive and to clone and the nonuniform mutation is adopted. Two metrics proposed by K. Deb et al. are adopted to measure the extent of convergence to a known set of Pareto-optimal solutions and the extent of spread achieved among the obtained solutions. Our algorithm is compared with another algorithm that is representative of the state-of-the-art in evolutionary multiobjective optimization-NSGA-II. Simulation results on ZDT test problems show that ICMOA, in most problems, is able to find much better spread of solutions and better convergence near the true Pareto-optimal front compared to NSGA-II. [ABSTRACT FROM AUTHOR]

This paper proposes a novel grid intrusion detection model based on immune agent (GIDIA), and gives the concepts and formal definitions of self, nonself, antibody, antigen, agent and match algorithm in the grid security domain. Then, the mathematical models of mature MoA (mature monitoring agent), and dynamic memory MoA (memory monitoring agent) survival are established. Besides, effects of the important parameter T in the model of mature MoA on system performance are showed. Our theoretical analysis and experimental results show that the model that has higher detection efficiency and steadier detection performance than the current models is a good solution to grid intrusion detection. [ABSTRACT FROM AUTHOR]

A novel image registration scheme is proposed. In the proposed scheme, two-dimensional principal component analysis (2DPCA) combined with principal component analysis (PCA) is used to extract features from the image sets and these features are fed into feedforward neural networks to provide translation, rotation and scaling parameters. Comparison experiments between 2DPCA combined with PCA based method and the other two former methods: discrete cosine transform (DCT) and Zernike moment, are performed. The results indicate that the proposed scheme is both accurate and remarkably robust to noise. [ABSTRACT FROM AUTHOR]

In this paper, a novel image discriminant analysis method, coined two-dimensional discriminant transform based on scatter difference criterion (2DSDD), is developed for image representation. The proposed 2DSDD scheme adopts the difference of both between-class scatter and within-class scatter as discriminant criterion. In this way, the small sample size problem usually occurred in the traditional Fisher discriminant analysis (LDA) is essentially avoided. In addition, the developed method directly depends on image matrices. That is to say, it is not necessary to convert the image matrix into high-dimensional image vector like those conventional linear discriminant methods prior to feature extraction so that much computational time would be saved. Finally, the experimental results on the ORL face database indicate that the proposed method outperforms Fisherfaces, the standard scatter difference discriminant analysis, not only in the computation efficiency, but also in its recognition performance. [ABSTRACT FROM AUTHOR]

Human motion analysis is an important research subject in human-robot interaction (HRI). However, before analyzing the human motion, silhouette of human body should be extracted from sequential images obtained by CCD camera. The intelligent robot system requires more robust silhouette extraction method because it has internal vibration and low resolution. In this paper, we discuss the hybrid silhouette extraction method for detecting and tracking the human motion. The proposed method is to combine and optimize the temporal and spatial gradient information. Also, we propose some compensation methods so as not to miss silhouette information due to poor images. Finally, we have shown the effectiveness and feasibility of the proposed method through some experiments. [ABSTRACT FROM AUTHOR]

In this paper, we present a realistic avatar called e-Shadow. This avatar is a virtual shadow of a user and facial animations are injected into the head position as response to the user's gestures. We adopt background subtraction method to separate the user's shape from the background scene and combine several image processing methods in order to reduce noise. A heuristic algorithm for tracking positions of head and hands is proposed to detect predefined user's gestures. Because e-Shadow assumes everyday indoor lighting, casual camera, and small desktop, it can be directly incorporated with video chatting programs as a realistic avatar and the presented detection method might be applied to the applications of real-time interactive media art. [ABSTRACT FROM AUTHOR]

Speech signal detection is very important in many areas of speech signal process technology. In real environments, speech signal is usually corrupted by background noise, which greatly affects the performance of speech signal detection system. Correlation analysis is a waveform analysis method which is commonly used in time domain, and the similarity of two signals can be measured by using of the correlation function. This paper presents a new approach based on waveform track from cross correlation coefficients to detect speech signal in adverse acoustic environments. This approach firstly removes irrelevant signal so as to decrease the interference from noise by making use of computing cross correlation coefficients, and then decides whether contains speech signal or not according to the waveform track. Moreover, the performance of the algorithm is compared to the approach based on short-term energy and the approach based on spectrum-entropy in various noise conditions, and algorithm is quantified by using the probability of correct classification. The experiments show that the waveform from cross correlation coefficients is powerful in anti-interference, especially being robust to colored noise such as babble. [ABSTRACT FROM AUTHOR]

Contour information is always valuable for object analysis in image processing. In this paper, a new method of constructing contours of skin regions is proposed. To exploit skin formation in images, a nonlinear skin color classifier is first introduced. Then, a region splitting scheme is adopted to generate adaptive grids over skin regions. Based on the grids, initial contours are constructed. Finally, the contours are refined according to the minimum energy principle. Experimental results show that the proposed method has a good performance in contour construction of skin regions. Keywords: Skin detection, region splitting, contour construction. [ABSTRACT FROM AUTHOR]

Feature sensitive hole filling is important for many computer graphics and geometric modeling applications. In this paper, we address the problem of reconstructing the salient features when filling holes in mesh. It respects fine shape features and works well on various types of shapes, including natural mesh and mechanical parts. For representing salient surface features, we adopt crest lines. The connectivity of the hole including the lost crest lines are decided by triangulation and region growing. The geometric position of the vertices and crest points in the hole are resolved by using a least-squares problem. [ABSTRACT FROM AUTHOR]

This paper considers the specific issues relating to finite word length (FWL) coefficient constraints for the case of infinite impulse response (IIR) digital filters. Due to the feedback nature of recursive filters, stability issues are an important factor in their design and are discussed in some detail. Some previously reported work on the optimization of FWL coefficients for IIR filters is also discussed. Extensive range of filter types and structures of IIR filters and their optimization using genetic algorithms is investigated and reported. Finally, comparative tests were conducted using the simple hill climber optimization techniques for a selection of filters. [ABSTRACT FROM AUTHOR]

The key frame technology is one of the most important technologies in the computer animation. All the researchers in the key frame algorithm are mainly focusing on the Euclidean object, without considering the fractal object. Fractal geometry can describe many irregularly shaped objects or spatially nonuniform phenomena in nature that cannot be accommodated by Euclidean geometry. In addition, the fractal objects in nature are almost colorful. Therefore, a computer aided inbetweening algorithm for color fractal graphics is presented in this paper. Our study shows that the fractal idea can be effectively applied in the key frame animation. The main feature of our algorithm is that it can deal with a fractal object while the conventional algorithm cannot. The theoretical and experimental results presented in this paper show that our algorithm has many practical values that can improve the efficiency of animation production and simultaneously greatly reduce the cost. [ABSTRACT FROM AUTHOR]