Applied Mechanics and Materials Vols. 462-463

Abstract: Background subtraction is often used to detect the moving objects from static cameras. The difficult of defect detecting of printing matter is how to detect the unknown flaws in complicate background effectively. Inspired by the background modeling approach for moving objects detection, a background modeling method in defect detection of printed image is suggested in this paper. Those pixels without defects are regarded as background, while the flaw pixels are defined as foreground. Firstly, we select LBP histogram as texture feature and HSV histogram as color feature to model the background respectively. Then, lots of printed images in which there are no defects are used to update these two models. Finally, we utilize the models to detect defects of printing images. Experimental results show that this background model works well in our defect detection.

Abstract: The dynamic response of different micro-beams after laser excitation experiments have been investigated in this paper. The impact force that induces the vibration of micro-beams is the interaction of focused pulse laser and tested beams. The impact response of micro-beams after being excited is measured by Laser Doppler Vibrometer. Different beams such as cantilever beam, L-shaped beam are employed in our experiments. Comparisons of the vibration velocity and its frequencies of different beams have also been performed. Experimental results show that the mechanical effects of laser shock do really exist and can be utilized.

Abstract: Global and local image retrieval of ancient Chinese characters is a helpful means for character research work. Because of the characteristics of ancient Chinese characters such as complex structures and variant shapes, there exist many theoretical and technical problems in feature extraction, clustering and retrieval of these images. A retrieval method was established with the strategy of “clustering before matching” for the ancient Chinese character images by integrating the structural features of them. Firstly, preprocessed character image area was divided into elastic meshes and the directional elements were extracted to form the feature vectors. Then, K-means algorithm was employed to cluster the character images within global and local areas. Finally, the similar images within selected areas were searched in corresponding cluster and the obtained images were provided to users. The experimental results show that this method is helpful for the improvement of the efficiency of ancient Chinese character study.

Abstract: Neural network with quadratic junction was described. Structure, properties and unsupervised learning rules of the neural network were discussed. An ART-based hierarchical clustering algorithm using this kind of neural networks was suggested. The algorithm can determine the number of clusters and clustering data. A 2-D artificial data set is used to illustrate and compare the effectiveness of the proposed algorithm and K-means algorithm.

Abstract: A new multi spectral and panchromatic image fusion, which is based on Nonsubsampled Contourlet Transform (NSCT) and HIS transform, is proposed in this paper. First, I component was obtained from multispectral image through HIS transform. Second, coefficients were gained by fusion algorithm, which performed on I component and Panchromatic image by NSCT transform. Finally, the fusion images were received by inverse HIS transform on H and S component of multispectral image and . The experiment results show that the proposed algorithm not only preserves spectral information of original images well, but also enhances detail texture information in image fusion.

Abstract: A nonlinear system described by Mkdv equation is studied. Based on software Mathematica, the solutions of such complex nonlinear system are visualized. The characteristics of such solutions and the relationship between their velocity and shape are exhibited. Especially, the simulations of the collisions of two solitary waves are shown and analyzed.

Abstract: Li et al. [Pattern Recognition 41 (2008) 3287 -- 329 proposed the constrained maximum variance mapping method. The CMVM is globally maximizing the distances between different manifolds. We find out that globally minimizing the distances between the same manifolds can have better recognition than CMVM method on the Yale face database, ORL face database and UMIST face database. Hence we propose to use an inverse constrained maximum variance mapping method (ICMVM) which can be seen as the inverse Laplacian Fisher discriminate criteria. Experiment results suggest that this new approach performs well.

Abstract: This paper proposes an algorithm called DDSCDA, which is based on the concepts of the node degree difference and the node similarity. In the algorithm, we iteratively extract the node from the network with larger degree and certified the node as a kernel node, then take the kernel node as the founder or initiator of a community to attract its neighbors to join in that community; by doing so, we obtain a partition corresponding to a coarse-grained community structure of the network. Finally taken the coarse-grained community as a starting point, we use the strategy of LPA to propagate labels through the network further. At the end of the algorithm, we obtain the final community structure. We compared the performance with classical community detection algorithms such as LPA, LPAm, FastQ, etc., the experimental results have manifested that our proposal is a feasible algorithm, can extract higher quality communities from the network, and outperforms the previous algorithms significantly.

Abstract: It is difficult to reconstruct the unknown information only by some sparse known data in the reconstruction of porous media. Multiple-point geostatistics (MPS) has been proved to be a powerful tool to capture curvilinear structures or complex features in training images. One solution to capture large-scale structures while considering a data template with a reasonably small number of grid nodes is provided by the multiple-grid method. This method consists in scanning a training image using increasingly finer multiple-grid data templates instead of a big and dense data template. The experimental results demonstrate that multiple-grid data templates and MPS are practical in porous media reconstruction.

Abstract: Knowledge reduction is one of the main problems in the study of rough set theory. This paper deals with knowledge reduction of set-valued decision information systems based on tolerance relation. The concepts of distribution reduct based on set-valued decision information systems is introduced. The judgement theorems and discernibility matrices associated with the tolerance relation were examined, from which we can obtain the specific operation methods to inconsistent set-valued decision information systems.