Applied Mechanics and Materials Vols. 380-384

Abstract: The application of classical gaussian mixture model to image segmentation has highly computer complexiton and have not taking into account spatial information except intensity values. A image segmentation based on Gaussian mixture model with sampling and spatially information is proposed in order to solve this problem. First, a spatial information function is defined as the neighbour information weighted class probabilities of very pixels; Secondly, the sampling theorem is given in this paper,and the size of the minimum sample has been derived according to the smallest cluster and cluster number; Finally, image pixels are sampled based on the size of the minimum sample to estimate the parameter of model , which are classifed to different clusters according to bayesian rules. The experimental results show the effectiveness of the algorithm.

Abstract: A new fuzzy enhancement method is put forward in the paper combining with Young-Helmholtz (Y-H) color space and fuzzy set theory. Color images with RGB tri-channels are transformed into Y-H color space by using Greaves transformation method. The colors image could be decomposed into chromaticity numbers matrix and intensity numbers matrix. The intensity numbers matrix is processed by using fuzzy enhancement arithmetic, while chromaticity numbers matrix keeps invariant. The primary chromaticity numbers matrix and enhanced intensity numbers matrix are processed by using Y-H inverse transformation. The method put forward in the paper have characteristics of efficiency, convenience and high speed. The method can achieve enhancement for color medical images without changing hue and saturation.

Abstract: With the development of modern signal processing technology, the method of Wavelet Transform (WT) has been greatly used in image and video processing. In this paper, a method to use Discrete Wavelet Transform (DWT) in intra-frame (I-frame) video compression is proposed for the purpose of better compression efficiency and quality on the basis of good visual effects. The method can be functioned as a preprocessing of I-frame coding. The experimental results show that the proposed method has an increase in both coding efficiency and quality.

Abstract: For it has so many features of SOA--loose coupling, findable, assemble, reuse, etc., it can bring great competitive strength to enterprise. Then we can integrate the communication service with the whole system. The article uses the concept of SOA and ESB and puts forward the life circle of the constructing of communication management system. First of all, we analyze the requirement of the CMS and achieve the goals need to be meet. Then the overall design are described. it focus on the design of the service model of communication core and communication gateway.

Abstract: In super-resolution reconstruction, there exists the defect that common template matching costs much memory and time. In this paper, the template matching algorithm is optimized. Firstly, a mathematical model of super-resolution is established. Then, the importance of image registration is discussed in super-resolution reconstruction of video image. Subsequently, the method of template matching for registration is put forward and the specific steps of algorithm are described. At the same time, the defects of template matching algorithm are analyzed. Finally, the algorithm of template matching has been improved to optimize the registration time. The experimental results show that the time used by this algorithm is half of the time used by the original template matching algorithm.

Abstract: When low-spline interpolation algorithm is adopted by super-resolution reconstruction for video images, there are some defects, such as saw tooth and blur edge, if the result image is magnified. In this paper, high-order spline interpolation algorithm is introduced and it is optimized. Firstly, the common low-spline interpolation algorithms are analyzed and their shortcomings are pointed out. Then cubic spline interpolation algorithm is discussed. If the image is rotated by cubic spline interpolation algorithm, the magnified image may be not correctly displayed and the image can not be registered in super-resolution reconstruction. Finally, the cubic spline algorithm has been improved. Experimental results show that the improved cubic spline interpolation algorithm can not only eliminate the edge blur and saw tooth, but also do registration in reconstruction when image is rotating.

Abstract: This paper presents an algorithm for estimating the parameters of multicomponent cubic phase signals. This algorithm combines the product generalized cubic phase function (PGCPF) and the product cubic phase function (PCPF) which are used to estimate the cubic phase coefficient and chirp rate of the cubic phase signal, respectively. This algorithm starts by estimating the parameters of the signal component with the strongest amplitude. Then removing the signal component whose parameters have been estimated, it proceeds to estimate the next signal component, and so on, until all of the signal components have been estimated. Numerical simulations are carried out to validate the performance of the proposed algorithm.

Abstract: The current sound data collecting system can`t meet the demand of the engineers on special occasions to master the process of the signal acquisition from remote timely. In order to solve this problem, this article designed a real-time monitoring system which can collect the signal by a sound card and implement the analysis of the sound signal`s power spectrum and phase spectrum, storage and playback. In addition, it can use the TCP/IP protocol to transmit the signal to remote engineers timely. Practice shows us that the system has the characters of simple structure, steady data transition, low cost and friendly interaction.

Abstract: Principal cmponent analysis is applied to face recognition problem to shorten image processing time in this paper. Based on the analysis of basic principal cmponent analysis algorithm, a new strategy which can improve algorithm efficiency by reducing the dimension of face images to be processed is introduced to face recognition problem, and the detailed computer implementation procedure is given. Numerical experiments have been performed to evaluate the efficiency of improved principal cmponent analysis algorithm for the problem of face recognition.

Abstract: Proposed a static gesture recognition method for identifying characteristics of the object in combination. With the feature vector composed of five features, such as the number of fingers, gesture outline convex defect characteristics, the length and area of contour and Hu matrix, we adopted the template-matching method to conduct the matching of featured parameters. Experiments show that the method successfully recognized static gestures under complex background and could reduce the impact of environmental change simultaneously.