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
  • [21] Segmentation of Exudates Based on High Pass Filtering in Retinal Fundus Images
    Nugroho, Hanung Adi
    Oktoeberza, K. Z. Widhia
    Adji, Teguh Bharata
    Sasongko, Muhammad Bayu
    2015 7TH INTERNATIONAL CONFERENCE ON INFORMATION TECHNOLOGY AND ELECTRICAL ENGINEERING (ICITEE), 2015, : 436 - 441
  • [22] An Improved Method for Automated Identification of Hard Exudates in Diabetic Retinopathy Disease
    Datta, Niladri Sekhar
    Dutta, Himadri Sekhar
    Majumder, Koushik
    Chatterjee, Sumana
    Wasim, Najir Abdul
    IETE JOURNAL OF RESEARCH, 2019, 68 (01) : 611 - 621
  • [23] Texture Based Method for Automated Detection, Localization and Evaluation of the Exudates in Retinal Images
    Popescu, Dan
    Ichim, Loretta
    Caramihale, Traian
    NEURAL INFORMATION PROCESSING, ICONIP 2015, PT IV, 2015, 9492 : 463 - 472
  • [24] Automatic detection of exudates in retinal images based on threshold moving average models
    Wisaeng K.
    Hiransakolwong N.
    Pothiruk E.
    Biophysics, 2015, 60 (2) : 288 - 297
  • [25] Multifocal electroretinography amplitudes increase after photocoagulation in areas with increased retinal thickness and hard exudates
    Lovestam-Adrian, Monica
    Holm, Kristina
    ACTA OPHTHALMOLOGICA, 2010, 88 (02) : 188 - 192
  • [26] A novel automatic image processing algorithm for detection of hard exudates based on retinal image analysis
    Sanchez, Clara I.
    Hornero, Roberto
    Lopez, Maria I.
    Aboy, Mateo
    Poza, Jesus
    Abasolo, Daniel
    MEDICAL ENGINEERING & PHYSICS, 2008, 30 (03) : 350 - 357
  • [27] Automated Segmentation of Hard Exudates Based on Matched Filtering
    Nugroho, Hanung Adi
    Oktoeberza, Widhia K. Z.
    Ardiyanto, Igi
    Buana, Ratna Lestari Budiani
    Sasongko, Muhammad Bayu
    2016 INTERNATIONAL SEMINAR ON SENSORS, INSTRUMENTATION, MEASUREMENT AND METROLOGY (ISSIMM), 2016, : 84 - 87
  • [28] A Survey on Automatic Detection of Hard Exudates in Diabetic Retinopathy
    Kumar, B. Vinoth
    Janani, K.
    Priya, N. Mythili
    PROCEEDINGS OF THE 2017 INTERNATIONAL CONFERENCE ON INVENTIVE SYSTEMS AND CONTROL (ICISC 2017), 2017, : 642 - 652
  • [29] A novel method for detection of hard exudates from fundus images based on SVM and improved FCM
    高玮玮
    SHEN Jian-xin
    WANG Ming-hong
    ZUO Jing
    Journal of Chongqing University(English Edition), 2018, 17 (03) : 77 - 86
  • [30] Optic Disc Identification Methods for Retinal Images
    Rotaru, Florin
    Bejinariu, Silviu Joan
    Nita, Cristina Diana
    Luca, Ramona
    Lazar, Camelia
    COMPUTER SCIENCE JOURNAL OF MOLDOVA, 2014, 22 (02) : 186 - 210