An Efficient Preprocessing Step for Retinal Vessel Segmentation via Optic Nerve Head Exclusion
Retinal vessel segmentation plays a significant role for accurate diagnostics of ophthalmic diseases. In this paper, a novel preprocessing step for retinal vessel segmentation via optic nerve head exclusion is proposed. The idea relies in the fact that the exclusion of brighter optic nerve head prior to contrast enhancement process can better enhance the blood vessels for accurate segmentation. A histogram based intensity thresholding scheme is introduced in order to extract the optic nerve head which is then replaced by its surrounding background pixels. The efficacy of the proposed preprocessing step is established by segmenting the retinal vessels from the optic nerve head excluded image enhanced using CLAHE algorithm. Experimental works are carried out with fundus images from DRIVE database. It shows that 1%–3% of improvement in terms of TPR measure is achieved.
KeywordsFundus image enhancement Retinal vessel segmentation Optic nerve head Preprocessing
The authors would like to acknowledge the University Grants Commission (UGC), New Delhi, India for the financial support extended under Maulana Azad National Fellowship (MANF) scheme.
- 1.Kumar, I., Bhadauria, H., Virmani, J., Rawat, J.: Reduction of speckle noise from medical images using principal component analysis image fusion. In: 2014 9th International Conference on Industrial and Information Systems (ICIIS) (2014)Google Scholar
- 2.Gonzalez, R., Woods, R.: Digital Image Processing. Pearson, London (2006)Google Scholar
- 10.Mapayi, T., Viriri, S., Tapamo, J.: Comparative study of retinal vessel segmentation based on global thresholding techniques. Comput. Math. Methods Med. 2015, 1–15 (2015)Google Scholar
- 11.Zuiderveld, K.: Contrast Limited Adaptive Histogram Equalization in Graphics Gems IV. AP Professional, Boston (1994)Google Scholar
- 12.Lu, C., et al.: Vessel enhancement of low quality fundus image using mathematical morphology and combination of Gabor and matched filter. In: 2016 International Conference on Wavelet Analysis and Pattern Recognition (ICWAPR) (2016)Google Scholar
- 18.Yadav, S., Kumar, S., Kumar, B., Gupta, R.: Comparative analysis of fundus image enhancement in detection of diabetic retinopathy. In: 2016 IEEE Region 10 Humanitarian Technology Conference (R10-HTC) (2016)Google Scholar