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 20, 201504(2020)

RetinexNet Low Illumination Image Enhancement Algorithm in HSV Space

Hongying Zhang* and Jindong Zhao
Author Affiliations
  • College of Electronic Information and Automation, Civil Aviation University of China, Tianjin 300300, China
    • show less
    AbstractGet PDF(in Chinese)
    Figures&Tables (7)
    Equations (0)
    References (18)
    Cited By (2)
    Tools
    Paper Information
    Topics
    Figures & Tables(7)
    Structure of RetinexNet algorithm

    Fig. 1. Structure of RetinexNet algorithm

    Download full size
    Enhancement effect of the RetinexNet algorithm. (a) Low-light image; (b) enhanced image

    Fig. 2. Enhancement effect of the RetinexNet algorithm. (a) Low-light image; (b) enhanced image

    Download full size
    Flow chart of our algorithm

    Fig. 3. Flow chart of our algorithm

    Download full size
    Decomposition of V component image. (a) Image of low illumination; (b) image of V component; (c) incident light image of V component; (d) reflectivity image of V component

    Fig. 4. Decomposition of V component image. (a) Image of low illumination; (b) image of V component; (c) incident light image of V component; (d) reflectivity image of V component

    Download full size
    Enhancement effect of different algorithms. (a) Original image; (b) HE algorithm; (c) LIME algorithm; (d) MSRCR algorithm; (e) RetinexNet algorithm; (f) our algorithm

    Fig. 5. Enhancement effect of different algorithms. (a) Original image; (b) HE algorithm; (c) LIME algorithm; (d) MSRCR algorithm; (e) RetinexNet algorithm; (f) our algorithm

    Download full size
    Enlarged view of partial pairs of different algorithms. (a) Original image; (b) HE algorithm; (c) LIME algorithm; (d) MSRCR algorithm; (e) RetinexNet algorithm; (f) our algorithm

    Fig. 6. Enlarged view of partial pairs of different algorithms. (a) Original image; (b) HE algorithm; (c) LIME algorithm; (d) MSRCR algorithm; (e) RetinexNet algorithm; (f) our algorithm

    Download full size

    • Table 1. Objective evaluation results of different algorithms

      View table

      Table 1. Objective evaluation results of different algorithms

      Test imageEvaluation indexAlgorithm
      HELIMEMSRCRRetinexNetOurs
      ALSD72.53565.07442.70141.05588.301
      1stAG12.1048.91610.33418.97420.795
      Entropy7.5327.2357.2547.5168.104
      GM145.965127.080117.957121.294128.981
      ALSD63.95256.73229.18735.55874.090
      2edAG14.38510.4527.96311.38016.674
      Entropy5.2325.0976.6016.8977.482
      GM134.70251.015114.187107.925127.520
      ALSD70.86565.13032.34936.46271.641
      3rdAG16.14019.65810.41316.57521.717
      Entropy5.9457.1726.9237.3687.778
      GM134.082100.814124.491112.021126.477
    Tools

    Get Citation

    Copy Citation Text

    Hongying Zhang, Jindong Zhao. RetinexNet Low Illumination Image Enhancement Algorithm in HSV Space[J]. Laser & Optoelectronics Progress, 2020, 57(20): 201504

    Download Citation

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

    Category: Machine Vision

    Received: Dec. 10, 2019

    Accepted: Feb. 25, 2020

    Published Online: Oct. 17, 2020

    The Author Email: Hongying Zhang (carole_zhang0716@163.com)

    DOI:10.3788/LOP57.201504

    Topics

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