A retinal image sharpness metric based on histogram of edge width

被引：3
|
作者：
Lin J.-W. [1 ,2 ]
Weng Q. [2 ]
Xue L.-Y. [1 ]
Cao X.-R. [1 ]
Yu L. [1 ]
机构：
[1] College of Physics and Information Engineering, Fuzhou University, Fuzhou
[2] College of Mathematics and Computer Science, Fuzhou University, Fuzhou
来源：
Lin, Jia-Wen (ljw@fzu.edu.cn) | 1600年 / SAGE Publications Inc.卷 / 11期
基金：
中国国家自然科学基金;
关键词：
Diabetic retinopathy screening; Fundus image sharpness; Histogram; Weighted edge width;
D O I：
10.1177/1748301817713184
中图分类号：
学科分类号：
摘要：
Retinal image sharpness assessment is one of the critical requirements of automatic quality evaluation in telemedicine screening for diabetic retinopathy. In this paper, a new sharpness metric measuring the spread of edges is presented to quantify fundus image clarity. After edge detection on the region of interest of retinal image, the width of each edge is calculated and the histogram of region of interest generated. Based on the histogram, a distance-based factor is introduced to gain the weighted edge width, which is defined as the sharpness metric for the fundus image. The method was tested on Messidor dataset and a proprietary dataset. The results show that the proposed metric performs well over different image distortion levels and resolutions and is of low computational complexity. The weighted edge width value of gradable retinal image, which is irrelevant to resolution, is always within the range of 3–7 pixels. © The Author(s) 2017.
引用
收藏
页码：292 / 300
页数：8
相关论文
共 50 条
  • [1] Sharpness metric based on histogram of strong edge width
    Feng, H.-J. (fenghj@zju.edu.cn), 1600, Zhejiang University (48):
  • [2] Blind image sharpness metric based on edge and texture features
    Maheshwary, Priti
    Shirvaikar, Mukul
    Grecos, Christos
    REAL-TIME IMAGE AND VIDEO PROCESSING 2018, 2018, 10670
  • [3] A Perceptual Image Sharpness Metric Based on Local Edge Gradient Analysis
    Feichtenhofer, Christoph
    Fassold, Hannes
    Schallauer, Peter
    IEEE SIGNAL PROCESSING LETTERS, 2013, 20 (04) : 379 - 382
  • [4] A blur metric method based on edge width for the blurred image
    Luo, X. (lxh10801@163.com), 1600, Binary Information Press (11):
  • [5] Image Sharpness Metric Based on Algebraic MultiGrid Method
    Ying, Qian
    Xue-Mei, Ren
    Ying, Huang
    Li, Meng
    INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS, 2014, 5 (04) : 175 - 179
  • [6] IMAGE SHARPNESS METRIC BASED ON MAXPOL CONVOLUTION KERNELS
    Hosseini, Mahdi S.
    Plataniotis, Konstantinos N.
    2018 25TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2018, : 296 - 300
  • [7] No-reference sharpness metric based on local edge kurtosis
    Caviedes, J
    Gurbuz, S
    2002 INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, VOL III, PROCEEDINGS, 2002, : 53 - 56
  • [8] No-reference retinal image sharpness metric using daubechies wavelet transform
    Vonghirandecha P.
    Bhurayanontachai P.
    Kansomkeat S.
    Intajag S.
    International Journal of Circuits, Systems and Signal Processing, 2021, 15 : 1064 - 1071
  • [9] No-reference Image Sharpness Metric Based on Directional Derivatives
    Qian, Jiye
    Zhao, Hengjun
    Fu, Jin
    He, Guojun
    Hou, Xingzhe
    Fang, Bin
    Qian, Jide
    2017 INTERNATIONAL CONFERENCE ON SECURITY, PATTERN ANALYSIS, AND CYBERNETICS (SPAC), 2017, : 340 - 344
  • [10] Efficient implementation of kurtosis based no reference image sharpness metric
    Ferzli, Rony
    Girjia, Lakshmi
    Ali, Walid S. Ibrahim
    IMAGE PROCESSING: ALGORITHMS AND SYSTEMS VIII, 2010, 7532
12345