Laser & Optoelectronics Progress, Volume. 57, Issue 22, 221007(2020)

Multi-focus Image Fusion Algorithm Based on Extended Phase Stretch Transform

Yafeng Zhang1、*, Zexun Geng1,2, and Junmin Wang1
Author Affiliations
  • 1College of Information Engineering, Pingdingshan University, Pingdingshan, Henan 467000, China
  • 2Institute of Surveying and Mapping, Information Engineering University, Zhengzhou, Henan 450001, China
  • show less
    Figures & Tables(11)
    Results comparison. (a) Operation results by PST; (b) Operation results by Eq. (13)
    Error curve of the calculation result in Fig.1
    Grayscale variance and angle map variance maps of the source images. (a)(d) Blurred and clear source images;(b)(e) grayscale variance of Fig. (a) and (d); (c)(f) angle map variance of Fig. (a) and (d)
    Original image and high-frequency information extraction results. (a)(b) Original images; (c)(d) high-frequency information extracted by kernel function in Ref. [9] and proposed kernel function
    Flow chart of proposed multi-focus image fusion algorithm
    Fusion results of Lytro-07. (a) Fusion result by DWT; (b) fusion result by Laplace operator; (c) fusion result by SR; (d) fusion result by guided filter; (e) fusion result by JCAN; (f) fusion result using the kernel function in Ref. [9]; (g) fusion result using the proposed kernel function
    Difference maps of fusion results. (a)-(g) Corresponding to the difference maps in Fig. 6 (a)--(g)
    Local enlarged drawing. (a)(b) Corresponding to the local enlarged drawing in Fig. 7 (f) and (g)
    Source images and fusion results of proposed algorithm. (a)(b) Source images; (c) fusion results
    • Table 1. Grayscale variance and angle map variance of the blurred and clear images

      View table

      Table 1. Grayscale variance and angle map variance of the blurred and clear images

      Source imageVariance ofblurred imagesVariance ofclear imagesVariance of anglemap of blurred imagesVariance of anglemap of clear images
      1409.11584.31972.721031.26
      2907.29967.251210.741318.45
    • Table 2. Objective evaluation indexes of fusion results

      View table

      Table 2. Objective evaluation indexes of fusion results

      SourceimageMethodMutualinformationAveragegradientInformationentropySpatialFrequencyStructuralsimilarityCorrelationcoefficient
      Lytro-07DWT1.25962.0817.7257.97210.85050.9846
      Laplace1.28142.0857.72657.81910.85180.9844
      SR1.31252.0977.72998.01130.85580.9847
      Guided filter1.32612.0907.72797.98900.86270.9842
      JCAN1.32742.1127.73228.13430.88410.9871
      Kernel function of Ref. [9]1.32752.1107.73568.08910.88080.9849
      Proposed algorithm1.32682.1167.73578.09580.89580.9852
      Lytro-01DWT1.2222.3207.8666.87990.84190.9558
      Laplace1.2212.4407.9956.78780.84210.957
      SR1.41032.5297.94316.90710.87110.9515
      Guided filter1.41512.5027.9236.90790.89020.9561
      JCAN1.42602.6608.08427.16540.89920.9625
      Kernel function of Ref. [9]1.2512.6107.9857.16440.85240.9578
      Proposed algorithm1.4222.6308.11257.16760.87310.959
      Lytro-03DWT1.2151.9507.62146.58130.8790.9864
      Laplace1.2161.9807.59316.5170.88020.9862
      SR1.21292.0137.61976.50450.88120.9869
      Guided filter1.22242.0107.62586.60140.88650.9865
      JCAN1.24872.0707.62726.55540.88730.9875
      Kernel function of Ref. [9]1.2192.0307.63176.52390.88170.9882
      Proposed algorithm1.2232.0407.63286.55930.89530.9885
      Lytro-12DWT1.4363.2417.460811.65370.87150.9865
      Laplace1.4413.2477.433511.50880.88010.9869
      SR1.43293.2657.466711.66110.91140.9876
      Guided filter1.43433.2707.461411.67230.90250.9873
      JCAN1.4683.2807.473311.69420.91700.9889
      Kernel function of Ref. [9]1.4433.2837.472111.67620.87670.9893
      Proposed algorithm1.4463.2867.472611.69730.91350.9892
      Lytro-14DWT1.3372.8107.57529.81570.88710.9692
      Laplace1.3392.8207.55989.80790.88740.9698
      SR1.34232.8307.56019.85470.88830.9694
      Guided Filter1.3412.8307.55769.85280.8890.9692
      JCAN1.3472.8407.57049.85520.88970.9771
      Kernel function of Ref. [9]1.3442.8607.56099.80470.89040.9700
      Proposed algorithm1.3432.8707.56069.87170.89100.9703
    Tools

    Get Citation

    Copy Citation Text

    Yafeng Zhang, Zexun Geng, Junmin Wang. Multi-focus Image Fusion Algorithm Based on Extended Phase Stretch Transform[J]. Laser & Optoelectronics Progress, 2020, 57(22): 221007

    Download Citation

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

    Category: Image Processing

    Received: Feb. 10, 2020

    Accepted: Apr. 10, 2020

    Published Online: Oct. 27, 2020

    The Author Email: Yafeng Zhang (zhangyafeng@pdsu.edu.cn)

    DOI:10.3788/LOP57.221007

    Topics