Identification of hard exudates in retinal images.

被引:0
作者
Dhiravidachelvi, E. [1 ]
Rajamani, V [2 ]
Janakiraman, P. A. [3 ]
机构
[1] Sathyabama Univ, Dept Elect & Commun Engn, Madras, Tamil Nadu, India
[2] Veltech Multi Tech Engn Coll, Dept Elect & Commun Engn, Madras, Tamil Nadu, India
[3] IIT, Madras, Tamil Nadu, India
来源
BIOMEDICAL RESEARCH-INDIA | 2017年 / 28卷
关键词
Hard exudates; Soft exudates; Optic disc; Hue; Parameterization; Retinal image;
D O I
暂无
中图分类号
R318 [生物医学工程];
学科分类号
0831 ;
摘要
A new procedure for identification of the hard exudates is described in this Paper. Images are sorted into as many as 15 types using the maximum value of the hue in an image. Hue (h) at a point is defined as the ratio of green (g) to red (r) intensities. Given an image, the type-number is assigned to it. The exudates are also identified by using the hue, h. The varying intensities have been taken care of by the linear fit obeyed by the plot: h = m*g+c. A modified hue variable `Bh' is used to eliminate the soft exudates which have a blue component, by fitting lines like Bh=w1*h+w2. Very low intensity yellow coloured patches which do not qualify as hard exudates are removed by a discriminating threshold `de'. The parameters like (m, c), ( w1, w2), de are listed for the 15 types, in a Look up Table derived from experiments. The table entries vary in a structured manner. The tables can further be simplified as expressions if desired.
引用
收藏
页码:S336 / S343
页数:8
相关论文
共 50 条
  • [42] Utility of Hard Exudates for the Screening of Macular Edema
    Litvin, Taras V.
    Ozawa, Glen Y.
    Bresnick, George H.
    Cuadros, Jorge A.
    Muller, Matthew S.
    Elsner, Ann E.
    Gast, Thomas J.
    [J]. OPTOMETRY AND VISION SCIENCE, 2014, 91 (04) : 370 - 375
  • [43] Intelligent Feature Selection for Regions of Interest Identification in Retinal Images
    Ichim, Loretta
    Caramihale, Traian
    Popescu, Dan
    [J]. 2016 IEEE 11TH INTERNATIONAL SYMPOSIUM ON APPLIED COMPUTATIONAL INTELLIGENCE AND INFORMATICS (SACI), 2016, : 311 - 315
  • [44] Hard exudates segmentation based on learned initial seeds and iterative graph cut
    Kusakunniran, Worapan
    Wu, Qiang
    Ritthipravat, Panrasee
    Zhang, Jian
    [J]. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE, 2018, 158 : 173 - 183
  • [45] Detection of Hard Exudates in Colour Fundus Images Using Fuzzy Support Vector Machine-Based Expert System
    T. Jaya
    J. Dheeba
    N. Albert Singh
    [J]. Journal of Digital Imaging, 2015, 28 : 761 - 768
  • [46] Detection of Hard Exudates in Colour Fundus Images Using Fuzzy Support Vector Machine-Based Expert System
    Jaya, T.
    Dheeba, J.
    Singh, N. Albert
    [J]. JOURNAL OF DIGITAL IMAGING, 2015, 28 (06) : 761 - 768
  • [47] IMPROVING HARD EXUDATE DETECTION IN RETINAL IMAGES THROUGH A COMBINATION OF LOCAL AND CONTEXTUAL INFORMATION
    Sanchez, C. I.
    Niemeijer, M.
    Schulten, M. S. A. Suttorp
    Abramoff, M.
    van Ginneken, B.
    [J]. 2010 7TH IEEE INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING: FROM NANO TO MACRO, 2010, : 5 - 8
  • [48] Detection of exudates from retinal images for non-proliferative diabetic retinopathy detection using deep learning model
    Saranya, P.
    Umamaheswari, K. M.
    [J]. MULTIMEDIA TOOLS AND APPLICATIONS, 2023, 83 (17) : 52253 - 52273
  • [49] Automatic detection of diabetic retinopathy exudates from non-dilated retinal images using mathematical morphology methods
    Sopharak, Akara
    Uyyanonvara, Bunyarit
    Barman, Sarah
    Williamson, Thomas H.
    [J]. COMPUTERIZED MEDICAL IMAGING AND GRAPHICS, 2008, 32 (08) : 720 - 727
  • [50] Robust intensity variation and inverse surface adaptive thresholding techniques for detection of optic disc and exudates in retinal fundus images
    Karkuzhali, S.
    Manimegalai, D.
    [J]. BIOCYBERNETICS AND BIOMEDICAL ENGINEERING, 2019, 39 (03) : 753 - 764