Accepted Papers

    Pierluigi Maponi, Riccardo Piergallini and Filippo Santarelli, University of Camerino, Italy

    We propose a gradient-based method to extract the orientation field of a fingerprint image, and an iterative algorithm to refine and regularise this field. The formulation of this iterative algorithm is based on two new integral operators, which are described together with their main properties. A preprocessing step is also proposed in order to enhance the performance of the whole procedure. The results of our tests on real fingerprint images are provided to show the performance of the proposed approach.

    Kong Xiangsi and Zhao Xian, Beijing University of Civil Engineering and Architecture, China

    In this paper, an image matching method based on modified RANSAC algorithm is proposed to improve the precision and speed. Firstly, the feature points of the images are extracted using the SIFT algorithm. Then, the image pair is matched roughly by generating SIFT feature descriptor. At last, the precision of image matching is optimized by the modified RANSAC algorithm,. The RANSAC algorithm is improved from three aspects: instead of the homography matrix, this paper uses the fundamental matrix generated by the 8 point algorithm as the model; the sample is selected by a random block selecting method, which ensures the uniform distribution and the accuracy; adds sequential probability ratio test(SPRT) on the basis of standard RANSAC, which cut down the overall running time of the algorithm. The experimental results show that this method can not only get higher matching accuracy, but also greatly reduce the computation and improve the matching speed.

  • A Novel Metric for Edge Centrality
    Xiaodi Huang1, Changqin Huang2, Weidong Huang3, 1School of Computing and Mathematics Charles Sturt University Albury, Australia, 2Education Technology Faulty South China Normal University Guangzhou, China, 3School of Engineering and ICT, University of Tasmania Tasmania, Australia

    As we are in the age of big data, graph data become bigger. A big graph normally has the overwhelming numbers of edges. Existing metrics of edge centrality are not suitable for dealing with such a large graph. A novel metric for measuring the importance of edges in a graph is presented. This metric not only captures the structural feature of a graph, but also has the good scalability. The extensive experiments have demonstrated the performance of the proposed metric by comparing it with several popular metrics against real-world graphs.

                                                                                                            Copyright SPPR 2017                                                                            Designed By NnN