An Effective Supervised Framework for Retinal Blood Vessel Segmentation Using Local Standardisation and Bagging
In this paper, we present a supervised framework for extracting blood vessels from retinal images. The local standardisation of the green channel of the retinal image and the Gabor filter responses at four different scales are used as features for pixel classification. The Bayesian classifier is used with a bagging framework to classify each image pixel as vessel or background. A post processing method is also proposed to correct central reflex artifacts and improve the segmentation accuracy. On the public DRIVE database, our method achieves an accuracy of 0.9491 which is higher than any existing methods. More importantly, visual inspection on the segmentation results shows that our method gives two important improvements on the segmentation quality: vessels are well separated and central reflex are effectively removed. These are important factors that affect to the accuracy of all subsequent vascular analysis.
KeywordsRetinal images blood vessel segmentation central reflex Gabor filter Bayeisan classifier bagging
Unable to display preview. Download preview PDF.
- 10.Marín, D., Aquino, A., Gegúndez, M., Bravo, J.: A new supervised method for blood vessel segmentation in retinal images by using gray-level and moment invariants-based features. IEEE Transactions on Medical Imaging (2010)Google Scholar
- 11.Movellan, J.R.: Tutorial on gabor filters. Open Source Document (2002)Google Scholar
- 13.Niemeijer, M., Staal, J., van Ginneken, B., Loog, M., Abramoff, M.D.: Comparative study of retinal vessel segmentation methods on a new publicly available database. In: Proceedings of SPIE, vol. 5370, p. 648 (2004)Google Scholar