Publication detail

Exudates Detection in Digital Fundus Image Using Edge Based Method & Strategic Thresholding

DUTTA, M. SRIVASTAVA, K. GANGULY, S. GANGULY, S. PARTHASARATHI, M. BURGET, R. PŘINOSIL, J.

Original Title

Exudates Detection in Digital Fundus Image Using Edge Based Method & Strategic Thresholding

English Title

Exudates Detection in Digital Fundus Image Using Edge Based Method & Strategic Thresholding

Type

conference paper

Language

en

Original Abstract

The paper proposes an image processing algorithm to accurately detect the presence of exudates in Fundus images. For Diabetic Retinopathy, presence of exudates in the fundus image marks the beginning of vision loss and hence detecting the exudates accurately and efficiently is of prime concern. The proposed algorithm is a strategic method which removes false detection because of noise generated for different reasons. Using a strategic combination of two independent approaches based on threshold and edge detection helps in eliminating all possible types of noises leading to false exudates that may have crept in. Hence, this method of detecting the exudates has an advantage of increased accuracy. Experimental results indicate that this method has a clear advantage of accuracy in terms of exudates detection in the digital Fundus image without compromising the computational time.

English abstract

The paper proposes an image processing algorithm to accurately detect the presence of exudates in Fundus images. For Diabetic Retinopathy, presence of exudates in the fundus image marks the beginning of vision loss and hence detecting the exudates accurately and efficiently is of prime concern. The proposed algorithm is a strategic method which removes false detection because of noise generated for different reasons. Using a strategic combination of two independent approaches based on threshold and edge detection helps in eliminating all possible types of noises leading to false exudates that may have crept in. Hence, this method of detecting the exudates has an advantage of increased accuracy. Experimental results indicate that this method has a clear advantage of accuracy in terms of exudates detection in the digital Fundus image without compromising the computational time.

Keywords

Diabetic Retinopathy, Exudates, Thresholding based detection, Edge detection, Fundus image processing

RIV year

2014

Released

09.07.2015

Location

Berlin, Germany

ISBN

978-80-214-4983-1

Book

2014 37th International Conference on Telecommunications and Signal Processing (TSP)

Pages from

748

Pages to

752

Pages count

5

URL

Documents

BibTex


@inproceedings{BUT110230,
  author="Malay Kishore {Dutta} and Kshitij {Srivastava} and Shaunak {Ganguly} and Shaumik {Ganguly} and M. {Parthasarathi} and Radim {Burget} and Jiří {Přinosil}",
  title="Exudates Detection in Digital Fundus Image Using Edge Based Method & Strategic Thresholding",
  annote="The paper proposes an image processing algorithm to accurately detect the presence of exudates in Fundus images. For Diabetic Retinopathy, presence of exudates in the fundus image marks the beginning of vision loss and hence detecting the exudates accurately and efficiently is of prime concern. The proposed algorithm is a strategic method which removes false detection because of noise generated for different reasons. Using a strategic combination of two independent approaches based on threshold and edge detection helps in eliminating all possible types of noises leading to false exudates that may have crept in. Hence, this method of detecting the exudates has an advantage of increased accuracy. Experimental results indicate that this method has a clear advantage of accuracy in terms of exudates detection in the digital Fundus image without compromising the computational time.",
  booktitle="2014 37th International Conference on Telecommunications and Signal Processing (TSP)",
  chapter="110230",
  doi="10.1109/TSP.2015.7296364",
  howpublished="electronic, physical medium",
  year="2015",
  month="july",
  pages="748--752",
  type="conference paper"
}