Journals Articles Conferences News About CLP
Submit a paper Email Alert
Search
Search
Articles
Journals
News
Advanced Search
Top Searches
2D MaterialsTransformation opticsQuantum PhotonicsSmall lasersSemiconductor UV PhotonicsSupersymmetric microring laser arrays

Laser & Optoelectronics Progress, Volume. 57, Issue 14, 141022(2020)

Image Matching Algorithm Based on Gradient Information Descriptor

Shun Yang**, Kexin Kang*, and Fei Ma***
Author Affiliations
  • School of Electronics and Information Engineering, Liaoning Technical University, Huludao, Liaoning 125105, China
    • show less
    AbstractGet PDF(in Chinese)
    Figures&Tables (9)
    Equations (0)
    References (16)
    Cited By (2)
    Tools
    Paper Information
    Topics
    Figures & Tables(9)
    Diagram of GM and GO

    Fig. 1. Diagram of GM and GO

    Download full size
    Same orientation histograms constructed based on GM for four different subregions

    Fig. 2. Same orientation histograms constructed based on GM for four different subregions

    Download full size
    Same orientation histograms constructed based on GO for four different subregions

    Fig. 3. Same orientation histograms constructed based on GO for four different subregions

    Download full size
    Sample images of dataset. (a)(h) Fussy transformation; (b) zooming; (c) rotation; (d)(g) viewing transformation; (e) light; (f) JPEG compression

    Fig. 4. Sample images of dataset. (a)(h) Fussy transformation; (b) zooming; (c) rotation; (d)(g) viewing transformation; (e) light; (f) JPEG compression

    Download full size
    Matching accuracy of dataset image pairs. (a) Bark; (b) Boat; (c) Graffti; (d) Wall; (e) Bikes; (f) Trees; (g) Leuven; (h) Ubc

    Fig. 5. Matching accuracy of dataset image pairs. (a) Bark; (b) Boat; (c) Graffti; (d) Wall; (e) Bikes; (f) Trees; (g) Leuven; (h) Ubc

    Download full size
    Runtime of dataset image pairs

    Fig. 6. Runtime of dataset image pairs

    Download full size

    • Table 1. Three-level normalization

      View table

      Table 1. Three-level normalization

      GM normalized rangeNormalized value
      (0,33%](33%,67%](67%,100%)0.330.671.00

    • Table 2. Eight-level normalization

      View table

      Table 2. Eight-level normalization

      GM normalized rangeNormalized value
      (0,12.5%]0.125
      (12.5%,25%]0.250
      (25%,37.5%]0.325
      (37.5%,50%]0.500
      (50%,65.5%]0.625
      (65.5%,75%]0.750
      (75%,87.5%]0.875
      (87.5%,100%)1.000

    • Table 3. Test results of SND inhibition threshold

      View table

      Table 3. Test results of SND inhibition threshold

      Threshold value1/41/81/161/32
      Accuracy0.52390.84500.97710.9653
    Tools

    Get Citation

    Copy Citation Text

    Shun Yang, Kexin Kang, Fei Ma. Image Matching Algorithm Based on Gradient Information Descriptor[J]. Laser & Optoelectronics Progress, 2020, 57(14): 141022

    Download Citation

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

    Category: Image Processing

    Received: Nov. 13, 2019

    Accepted: Dec. 17, 2019

    Published Online: Jul. 28, 2020

    The Author Email: Shun Yang (596258832@qq.com), Kexin Kang (1254651840@qq.com), Fei Ma (7245486@qq.com)

    DOI:10.3788/LOP57.141022

    Topics

    laser devices and laser physics
    Lasers and Laser Optics
    Laser physics
    laser manufacturing
    Instrumentation, Measurement and Metrology