Abstract/Description
The appearance and structure of blood vessels in retinal images play an important role in diagnosis of eye diseases. This paper proposes a method for segmentation of blood vessels in color retinal images. We present a method that uses 2-D Gabor wavelet to enhance the vascular pattern. We locate and segment the blood vessels using adaptive thresholding. The technique is tested on publicly available DRIVE database of manually labeled images which has been established to facilitate comparative studies on segmentation of blood vessels in retinal images. The proposed method achieves an area under the receiver operating characteristic curve of 0.963 on DRIVE database.
Keywords
Retina, Blood vessels, Biomedical imaging, Image segmentation, Diseases, Diabetes, Face detection, Image databases, Retinopathy, Optical filters
Session Theme
Artificial Intelligence – II
Session Type
Other
Session Chair
Dr. Sharifullah Khan
Start Date
16-8-2009 12:00 PM
End Date
16-8-2009 12:20 PM
Recommended Citation
Akram, M. U., Tariq, A., & Khan, S. A. (2009). Artificial Intelligence – II: Retinal image blood vessel segmentation. International Conference on Information and Communication Technologies. Retrieved from https://ir.iba.edu.pk/icict/2009/2009/24
Artificial Intelligence – II: Retinal image blood vessel segmentation
The appearance and structure of blood vessels in retinal images play an important role in diagnosis of eye diseases. This paper proposes a method for segmentation of blood vessels in color retinal images. We present a method that uses 2-D Gabor wavelet to enhance the vascular pattern. We locate and segment the blood vessels using adaptive thresholding. The technique is tested on publicly available DRIVE database of manually labeled images which has been established to facilitate comparative studies on segmentation of blood vessels in retinal images. The proposed method achieves an area under the receiver operating characteristic curve of 0.963 on DRIVE database.