Advanced Materials Research Vols. 121-122

Abstract: Human action recognition has been widely researched and applied in intelligent visual surveillance fields nowadays. Most work on action recognition has been visible-spectrum oriented over the past decade, while the persistence of visual surveillance system increases the demand for night-time action recognition. This paper deals with the problem of night action recognition using thermal infrared imagery. A novel algorithm based on the human action silhouettes energy histograms is proposed. The algorithm first makes use of the statistical background model and background subtraction method to extract the human action silhouettes, while calculating the silhouette energy images for the action sequences. Then, the histograms of oriented gradients are computed from the silhouette energy images. Finally, the human action is represented by the energy histograms features, and recognized by using the Euclidean distance and nearest neighbor classifier. An infrared human action database was built to provide a foundation for night action recognition. Experimental results using the infrared thermal action data show the effective of this method.

Abstract: According to the different frequency areas decomposed by shearlet transform, the selection principles of the lowpass subbands and highpass subbands were discussed respectively. The lowpass subband coefficients of the fused image can be obtained by means of the fusion rule based on the region variation, the highpass subband coefficients can be selected by means of the fusion rule based on the region energy. Experimental results show that comparing with traditional image fusion algorithms, the proposed approach can provide more satisfactory fusion outcome.

Abstract: The interior design is used to create functional, reasonable, comfortable and beautiful environment to meet the material and spiritual needs of people, which is based on the building nature of environment and the corresponding standards for usness of material and technical means and principles of architectural aesthetics. Meanwhile, good interior design is an important symbol which stands for an interior designer standards and levels. By analyzing the research status, content and factor analysis of interior design, this article used the membership change to analysis the interior design, and then we can get an evaluation method to evaluate the interior design. Though evaluating the results, we can easily modify the interior design and interior design development.

Abstract: The art design is the perfect combination between the human society and the spirit of certain material features, is also the inevitable product of the development process of the modern society. Art comes from life, in turn, which also affects on life. Art design is used to create functional and reasonable, comfortable and beautiful environment based on the building's useness nature, environment and the corresponding standard in order to meet the material and spiritual needs of people. By analyzing the art design research status, content and factor analysis, this article used AHP to evaluate the art design teaching. Though evaluating the results, We can easily transform the teaching profession of the art design teaching, which is a good way to promote the development of art design education.

Abstract: In this paper, we propose a new face recognition approach for image feature extraction named two-dimensional locality discriminant preserving projections (2DLDPP). Two-dimensional locality preserving projections (2DLPP) can direct on 2D image matrixes. So, it can make better recognition rate than locality preserving projection. We investigate its more. The 2DLDPP is to use modified maximizing margin criterion (MMMC) in 2DLPP and set the parameter optimized to maximize the between-class distance while minimize the within-class distance. Extensive experiments are performed on ORL face database and FERET face database. The 2DLDPP method achieves better face recognition performance than PCA, 2DPCA, LPP and 2DLPP.

Abstract: We enunciate the need for watermarking database relations to deter data piracy, identify the characteristics of relational data that pose unique challenges for watermarking. This paper creatively proposes a novel method for watermarking relational database, which uses speech signal as watermark embed into database according to the weight of attributes. Experimental results show that the proposed scheme is robust against various forms of attacks. Our approach is more intuitive, and it support easy watermark identification.

Abstract: THIS PAPER HAS BEEN REMOVED due to Plagiarism by Gao Guohong et al.The original paper was published by IEEEDesign and Implementation of an Embedded System for Neural-ControlledArtificial Legs》, published in International Conference of 《2010 IEEEWorkshop on Health Care Management》in February, 2010 by Lin An, ZhangXiaorong, Huang He and Yang Qing.http://www.ele.uri.edu/linc/htm/WHCM_Paper27Regular.pdf

Abstract: From the perspective of research progress and relevant results, this article carries out a relatively detailed combing and introduction of the progress and status quo of digitization of ancient books in China. On the basis of the introduction, this article points out the breakthrough progress of study on digitization of ancient books in technology and theory as well as problems to be solved urgently in the process of digitization construction, such as lack of overall planning and unified standard, retrieval technology and function of supporting research of digitized ancient books are to be perfected and improved, then put forward relevant suggestion, hoping to provide reference for further research.

Abstract: Vehicle classification and tracking is considered as one of the most challenging problems in the field of pattern recognition. In this paper, Particle Swarm Optimization (PSO) based method is exploited to recognize vehicle classes. Vehicle features, such as vehicle size, shape information, contour information are extracted. Each vehicle class is encoded as a centroid with multidimensional feature and PSO is employed to search the optimal position for each class centroid based on fitness function. After vehicle classification, an improved meanshift algorithm is presented for vehicle tracking. The algorithm’s evaluations on video image series, moving vehicle detection, vehicle classification and tracking are respectively conducted. The results show that PSO ensures a promising and stable performances in recognizing these vehicle classes, and the improved meanshift algorithm can achieve accuracy and real-time for tracking moving vehicles.

Abstract: This paper proposes an attack algorithm for digital image watermarking based on independent component analysis (ICA). The paper gives a briefly introduction about ICA algorithm, and expatiates on the attack algorithm which we proposed. The algorithm uses an auxiliary image to remove the watermark signal from the host image based on blind signal separation technology. The paper also does some experiment to attack the watermark algorithm proposed by I J. Cox. The results show that this attack algorithm not only removes most of the digital watermark information, but also has little effect on the image’s peak signal to noise ratio. The paper also discusses the attack algorithm for different watermark signals and different auxiliary images; the effect of this attack algorithm is feasible.