DocumentCode :
2657407
Title :
Retinal images: Noise segmentation
Author :
Akram, Muhammad Usman ; Tariq, Anam ; Nasir, Sarwat
Author_Institution :
Dept. of Comput. Eng., Coll. of EME, Rawalpindi
fYear :
2008
fDate :
23-24 Dec. 2008
Firstpage :
116
Lastpage :
119
Abstract :
In automated diagnosis of diabetic retinopathy, retinal images are used. The retinal images of poor quality need to be enhanced before the extraction of features and abnormalities. Segmentation of retinal images is essential for this purpose. The segmentation is employed to smooth and strengthen images by separating the noisy area from the overall image thus resulting in retinal image enhancement and less processing time. In this paper, we present a novel automated approach for segmentation of colored retinal images, which involves two steps. In the first step, we create binary noise segmentation mask to segment the retinal image. Second step creates final segmentation mask by applying morphological techniques. We used standard retinal image databases Diaretdb0 and Diaretdb1 to test the validation of our segmentation technique. Experimental results indicate our approach is effective and can get higher segmentation accuracy.
Keywords :
diseases; eye; feature extraction; image colour analysis; image enhancement; image segmentation; medical image processing; Diaretdb0; Diaretdb1; binary noise segmentation mask; colored retinal image segmentation; diabetic retinopathy diagnosis; feature extraction; morphological techniques; retinal image databases; retinal image enhancement; Colored noise; Diabetes; Feature extraction; Filters; Image databases; Image segmentation; Lighting; Noise reduction; Retina; Retinopathy; Diabetic retinopathy; Morphological operations; Noise segmentation; Retinal images; component;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Multitopic Conference, 2008. INMIC 2008. IEEE International
Conference_Location :
Karachi
Print_ISBN :
978-1-4244-2823-6
Electronic_ISBN :
978-1-4244-2824-3
Type :
conf
DOI :
10.1109/INMIC.2008.4777719
Filename :
4777719
Link To Document :
بازگشت