Simulation Tools and Techniques. 11th International Conference, SIMUtools 2019, Chengdu, China, July 8–10, 2019, Proceedings

Research Article

Image Mosaic Based on Improved Logarithmic Polar Coordinate Transformation and Ransac Algorithm

Download
77 downloads
  • @INPROCEEDINGS{10.1007/978-3-030-32216-8_59,
        author={Dan Li and Lei Chen and Jun Tian and Dai-hong Jiang and Jin-ping Sun and Bin Ding},
        title={Image Mosaic Based on Improved Logarithmic Polar Coordinate Transformation and Ransac Algorithm},
        proceedings={Simulation Tools and Techniques. 11th International Conference, SIMUtools 2019, Chengdu, China, July 8--10, 2019, Proceedings},
        proceedings_a={SIMUTOOLS},
        year={2019},
        month={10},
        keywords={Image registration Logarithmic polar coordinates Mosaic Ransac algorithm NSCT transform},
        doi={10.1007/978-3-030-32216-8_59}
    }
    
  • Dan Li
    Lei Chen
    Jun Tian
    Dai-hong Jiang
    Jin-ping Sun
    Bin Ding
    Year: 2019
    Image Mosaic Based on Improved Logarithmic Polar Coordinate Transformation and Ransac Algorithm
    SIMUTOOLS
    Springer
    DOI: 10.1007/978-3-030-32216-8_59
Dan Li1,*, Lei Chen1,*, Jun Tian1, Dai-hong Jiang1, Jin-ping Sun1, Bin Ding1
  • 1: Xuzhou University of Technology
*Contact email: lidanonline@163.com, chenlei@xzit.edu.cn

Abstract

Complex factors with the electronic noise, X-ray scattering and uneven illumination often disturb the image registration. A new algorithm was proposed in this paper. The improved phase correlation algorithm based on log polar transformation was used to calculate parameters, such as rotation, scaling and translation. Then, the Harris corner matching points were extracted in overlapping positions and purified by the improved Ransac algorithm. Finally, images were processed by NSCT transform algorithm to make the image joint seemed smooth and natural. Experiments confirmed that, the new algorithm is accurate and efficient, and has high robustness to complex environment.