Blood vessels segmentation based on three retinal images datasets
Retinal images are routinely acquired and retinal blood vessels are segmented to provide diagnostic evidence of diabetic retinopathy. Due to the acquisition process, usually these images are non-uniformly illuminated and demonstate local lu minosity and contrast variability. Based on four image pro...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English English |
| Published: |
Asian Research Publishing Network (ARPN)
2016
|
| Subjects: | |
| Online Access: | http://irep.iium.edu.my/46567/ http://irep.iium.edu.my/46567/ http://irep.iium.edu.my/46567/4/Blood_vessels.pdf http://irep.iium.edu.my/46567/7/46567_Blood%20vessels_scopus.pdf |
| Summary: | Retinal images are routinely acquired and retinal blood vessels are segmented to provide diagnostic evidence of diabetic retinopathy. Due to the acquisition process, usually these images are non-uniformly illuminated and demonstate local lu
minosity and contrast variability. Based on four image processing techniques, namely, Matched filter, Hough transform, Morphological operations and Watershed, the retinal blood vessels have been segmented. Then, their strengths and weaknesses are mathematically compared in terms of retinal images segmentation. Each algorithm performance was tested on DRIVE, DRIONS and High-Resolution Fundus images database. The results show that measuring the automatic segmentation algorithm performance is based mainly on how the retinal images are acquired as well as the image processing technique used for segmentation. Neural Network has been used to recognize the retinal images. The obtained results could help the eye specialists to visually examine the retinal images. |
|---|