Journal on Communications ›› 2022, Vol. 43 ›› Issue (11): 158-170.doi: 10.11959/j.issn.1000-436x.2022220

• Papers • Previous Articles     Next Articles

Multi-scale guided filtering integrated with superpixel and patch shift

Jianwu LONG, Jiangzhou ZHU   

  1. College of Computer Science and Engineering, Chongqing University of Technology, Chongqing 400054, China
  • Revised:2022-07-10 Online:2022-11-25 Published:2022-11-01
  • Supported by:
    Young Scientists Project of Science and Technology Research Program of Chongqing Education Commission of China(KJQN202201148);The National Natural Science Foundation of China for Young Scientists(61502065);Foundation and Frontier Research Key Program of Chongqing Science and Technology Commission(cstc2015jcyjBX0127);Humanities and Social Sciences Research Key Program of Chongqing Municipal Education Commission(17SKG136);Graduate Innovation Project of Chongqing University of Technology(clgycx20202096)

Abstract:

In order to avoid the phenomenon that edges were easily blurred during filtering, a multi-scale guided filtering integrated with superpixel and patch shift was proposed.Firstly, the bilateral filtering was applied to an input image to get more accurate superpixel regions.Then, the overlapping was used as the final filtering region, which was formed by the local window and the superpixel.The local window was selected by a metric function so that it did not contain edge information as much as possible.Finally, a small-scale window was used to preserve the edges, and then the window scale was increased for iterative guided filtering.The final filtering output was calculated by fusing the results of different window scales to smooth details while preserving the structural edges.Additionally, the evaluation index of filtering results quality was proposed and compared in different algorithms.The proposed algorithm has stronger edge preservation ability and can obtain better filtering effectiveness than other algorithms.

Key words: superpixel, patch shift, edge-aware, multi-scale, guided filtering

CLC Number: 

No Suggested Reading articles found!