Title

Image Processing – I: Automated system for macula detection in digital retinal images Publisher: IEEE Cite This PDF

Abstract/Description

In the field of medicines, medical image processing plays a vital role to detect the abnormalities of eye or eye diseases like glaucoma and diabetic retinopathy. Macular degeneration is one of the medical conditions that affect the vision of elder people. If not detected in early stages it causes loss of eye sight. This paper presents an automated system for the localization and detection of macula in digital retinal images. In this paper, macula is first localized by making use of localized optic disc centre and enhanced blood vessels. Finally macula is detected by taking the distance from center of optic disk and thresholding, then combining it with enhanced blood vessels image to locate the darkest pixel in this region, making clusters of these pixels. The largest pixel is located as macula. This methodology is tested on publically available DRIVE and STARE database of retinal images which enable us to check the results of macula localization and detection. Our algorithm performs well in localizing and detecting macula on these databases.

Location

Room C4

Session Theme

Image Processing – I

Session Type

Other

Session Chair

Dr. Sharifullah Khan

Start Date

24-7-2011 12:20 PM

End Date

24-7-2011 12:40 PM

Share

COinS
 
Jul 24th, 12:20 PM Jul 24th, 12:40 PM

Image Processing – I: Automated system for macula detection in digital retinal images Publisher: IEEE Cite This PDF

Room C4

In the field of medicines, medical image processing plays a vital role to detect the abnormalities of eye or eye diseases like glaucoma and diabetic retinopathy. Macular degeneration is one of the medical conditions that affect the vision of elder people. If not detected in early stages it causes loss of eye sight. This paper presents an automated system for the localization and detection of macula in digital retinal images. In this paper, macula is first localized by making use of localized optic disc centre and enhanced blood vessels. Finally macula is detected by taking the distance from center of optic disk and thresholding, then combining it with enhanced blood vessels image to locate the darkest pixel in this region, making clusters of these pixels. The largest pixel is located as macula. This methodology is tested on publically available DRIVE and STARE database of retinal images which enable us to check the results of macula localization and detection. Our algorithm performs well in localizing and detecting macula on these databases.