Study of retinal biometric systems with respect to feature classification for recognition and diabetic retinopathy

Srikanth Prabhu, Chandan Chakraborty, R. N. Banerjee, A. K. Ray

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

A biometric system is a heterogeneous entity characterized by identification and classification of data depending on a metric along with characteristics such as disease recognition and classification. This work is mainly concentrated on biometric pattern matching of a retinal image based on its macro and micro features. During data collection, several instances of abnormalities were detected on the retina, specially diabetes. In this work 350 images (fundus data which are training data) were analyzed using Decision trees and K Nearest Neighbour clustering technique. Four groups were identified from the data: normal retinopathy, mild non-proliferative diabetic retinopathy, moderate non-proliferative diabetic retinopathy and severe non-proliferative diabetic retinopathy. The important features that were collected for the data were distances, micro-aneurysms, exudates and haemorrhages. These features were extracted depending on the shapes of the vessels and the shapes of the diabetic features. In this paper a constructive method has been designed for classifying a person based on retinal biometric.The percentage accuracy by using decision tree has been 91.3% and by using K Nearest Neighbour has been 62%.The size of the training data set has been 350 and the size of the testing data set is 150.

Original languageEnglish
Pages (from-to)97-106
Number of pages10
JournalJournal of Medical Imaging and Health Informatics
Volume1
Issue number2
DOIs
Publication statusPublished - 01-06-2011

Fingerprint

Diabetic Retinopathy
Decision Trees
Exudates and Transudates
Aneurysm
Cluster Analysis
Retina
Hemorrhage
Datasets

All Science Journal Classification (ASJC) codes

  • Radiology Nuclear Medicine and imaging
  • Health Informatics

Cite this

Prabhu, Srikanth ; Chakraborty, Chandan ; Banerjee, R. N. ; Ray, A. K. / Study of retinal biometric systems with respect to feature classification for recognition and diabetic retinopathy. In: Journal of Medical Imaging and Health Informatics. 2011 ; Vol. 1, No. 2. pp. 97-106.
@article{641f37bd740349e296740314036bd10f,
title = "Study of retinal biometric systems with respect to feature classification for recognition and diabetic retinopathy",
abstract = "A biometric system is a heterogeneous entity characterized by identification and classification of data depending on a metric along with characteristics such as disease recognition and classification. This work is mainly concentrated on biometric pattern matching of a retinal image based on its macro and micro features. During data collection, several instances of abnormalities were detected on the retina, specially diabetes. In this work 350 images (fundus data which are training data) were analyzed using Decision trees and K Nearest Neighbour clustering technique. Four groups were identified from the data: normal retinopathy, mild non-proliferative diabetic retinopathy, moderate non-proliferative diabetic retinopathy and severe non-proliferative diabetic retinopathy. The important features that were collected for the data were distances, micro-aneurysms, exudates and haemorrhages. These features were extracted depending on the shapes of the vessels and the shapes of the diabetic features. In this paper a constructive method has been designed for classifying a person based on retinal biometric.The percentage accuracy by using decision tree has been 91.3{\%} and by using K Nearest Neighbour has been 62{\%}.The size of the training data set has been 350 and the size of the testing data set is 150.",
author = "Srikanth Prabhu and Chandan Chakraborty and Banerjee, {R. N.} and Ray, {A. K.}",
year = "2011",
month = "6",
day = "1",
doi = "10.1166/jmihi.2011.1015",
language = "English",
volume = "1",
pages = "97--106",
journal = "Journal of Medical Imaging and Health Informatics",
issn = "2156-7018",
publisher = "American Scientific Publishers",
number = "2",

}

Study of retinal biometric systems with respect to feature classification for recognition and diabetic retinopathy. / Prabhu, Srikanth; Chakraborty, Chandan; Banerjee, R. N.; Ray, A. K.

In: Journal of Medical Imaging and Health Informatics, Vol. 1, No. 2, 01.06.2011, p. 97-106.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Study of retinal biometric systems with respect to feature classification for recognition and diabetic retinopathy

AU - Prabhu, Srikanth

AU - Chakraborty, Chandan

AU - Banerjee, R. N.

AU - Ray, A. K.

PY - 2011/6/1

Y1 - 2011/6/1

N2 - A biometric system is a heterogeneous entity characterized by identification and classification of data depending on a metric along with characteristics such as disease recognition and classification. This work is mainly concentrated on biometric pattern matching of a retinal image based on its macro and micro features. During data collection, several instances of abnormalities were detected on the retina, specially diabetes. In this work 350 images (fundus data which are training data) were analyzed using Decision trees and K Nearest Neighbour clustering technique. Four groups were identified from the data: normal retinopathy, mild non-proliferative diabetic retinopathy, moderate non-proliferative diabetic retinopathy and severe non-proliferative diabetic retinopathy. The important features that were collected for the data were distances, micro-aneurysms, exudates and haemorrhages. These features were extracted depending on the shapes of the vessels and the shapes of the diabetic features. In this paper a constructive method has been designed for classifying a person based on retinal biometric.The percentage accuracy by using decision tree has been 91.3% and by using K Nearest Neighbour has been 62%.The size of the training data set has been 350 and the size of the testing data set is 150.

AB - A biometric system is a heterogeneous entity characterized by identification and classification of data depending on a metric along with characteristics such as disease recognition and classification. This work is mainly concentrated on biometric pattern matching of a retinal image based on its macro and micro features. During data collection, several instances of abnormalities were detected on the retina, specially diabetes. In this work 350 images (fundus data which are training data) were analyzed using Decision trees and K Nearest Neighbour clustering technique. Four groups were identified from the data: normal retinopathy, mild non-proliferative diabetic retinopathy, moderate non-proliferative diabetic retinopathy and severe non-proliferative diabetic retinopathy. The important features that were collected for the data were distances, micro-aneurysms, exudates and haemorrhages. These features were extracted depending on the shapes of the vessels and the shapes of the diabetic features. In this paper a constructive method has been designed for classifying a person based on retinal biometric.The percentage accuracy by using decision tree has been 91.3% and by using K Nearest Neighbour has been 62%.The size of the training data set has been 350 and the size of the testing data set is 150.

UR - http://www.scopus.com/inward/record.url?scp=84881125907&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84881125907&partnerID=8YFLogxK

U2 - 10.1166/jmihi.2011.1015

DO - 10.1166/jmihi.2011.1015

M3 - Article

AN - SCOPUS:84881125907

VL - 1

SP - 97

EP - 106

JO - Journal of Medical Imaging and Health Informatics

JF - Journal of Medical Imaging and Health Informatics

SN - 2156-7018

IS - 2

ER -