DocumentCode :
3252089
Title :
“Visual ophthalmologist” an automated system for classification of retinal damage
Author :
Aleynikov, Sergey ; Micheli-Tzanakou, Evangelia
Author_Institution :
Dept. of Biomed. Eng., Rutgers Univ., Piscataway, NJ, USA
Volume :
4
fYear :
1997
fDate :
9-12 Jun 1997
Firstpage :
2485
Abstract :
The objective of this research is to provide an ophthalmologist with a helpful system, capable of classifying a degree of patients´ retinal haemorrhage. The system is composed of four modules: 1) data acquisition module, 2) image database module, 3) image processing module, and 4) image classification module. The system was trained with a modular neural network on a set of 25 images, and tested on a set of 160 images. A training performance of greater than 95% was achieved. The classifying part of the system showed 79% recognition accuracy. Since the testing images were taken from independent sources, we assume that the system should also provide an accurate classification of other image types
Keywords :
data acquisition; eye; feature extraction; image classification; medical image processing; neural nets; visual databases; data acquisition; image classification; image database module; image processing module; modular neural network; retinal damage classification; retinal haemorrhage; visual ophthalmologist; Diseases; Feature extraction; Hemorrhaging; Image classification; Image databases; Image processing; Neural networks; Retina; Spatial databases; System testing;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Networks,1997., International Conference on
Conference_Location :
Houston, TX
Print_ISBN :
0-7803-4122-8
Type :
conf
DOI :
10.1109/ICNN.1997.614675
Filename :
614675
Link To Document :
بازگشت