Laser & Optoelectronics Progress, Volume. 57, Issue 4, 041014(2020)

Mesh Segmentation Based on Optimizing Extreme Learning Machine with Ant Lion Optimization

Xiaowen Yang*, Honghong Yin, Xie Han, and Jiaming Liu
Author Affiliations
  • School of Data Science and Technology, North University of China, Taiyuan, Shanxi 030051, China
  • show less
    Figures & Tables(7)
    Overall flow chart of our method
    Convergence of Airplane model at different population sizes
    Convergence of Octopus model at different population sizes
    Segmentation results of six types of models
    Bar chart showing average segmentation accuracy obtained with the methods in references[6-8] and our method
    • Table 1. Comparison of average segmentation accuracy obtained with the methods in references [6-8] and our method

      View table

      Table 1. Comparison of average segmentation accuracy obtained with the methods in references [6-8] and our method

      DatasetAverage segmentation accuracy /%
      CGF[2014]ATG[2015]CEA[2017]Ours
      Airplane94.4997.7496.2097.00
      Ant95.9898.8497.5998.07
      Chair97.4198.5397.7398.05
      Octopus98.7398.87-99.49
      Teddy97.7498.5398.4498.79
      Fish95.6896.7496.3597.35
    • Table 2. Time consumption of our method during training the model with 200000-300000 patches

      View table

      Table 2. Time consumption of our method during training the model with 200000-300000 patches

      DatasetTotal number of patchesTraining time / s
      Airplane253954997.49
      Ant2991561112.56
      Fish239886901.69
    Tools

    Get Citation

    Copy Citation Text

    Xiaowen Yang, Honghong Yin, Xie Han, Jiaming Liu. Mesh Segmentation Based on Optimizing Extreme Learning Machine with Ant Lion Optimization[J]. Laser & Optoelectronics Progress, 2020, 57(4): 041014

    Download Citation

    EndNote(RIS)BibTexPlain Text
    Save article for my favorites
    Paper Information

    Category: Image Processing

    Received: Jul. 11, 2019

    Accepted: Aug. 12, 2019

    Published Online: Feb. 20, 2020

    The Author Email: Yang Xiaowen (Wenyang1314@nuc.edu.cn)

    DOI:10.3788/LOP57.041014

    Topics