Morphological operations with iterative rotation of structuring elements for segmentation of retinal vessel structures
- 203 Downloads
The development of computer aided diagnosis system has a great impact on early and accurate disease diagnosis. The segmentation of retinal blood vessels aids in identifying the alteration in vessel structure and hence helps to diagnose many diseases such as diabetic retinopathy, glaucoma, hypertension along with some cardiovascular diseases. In this research work, a method is presented for the segmentation of retinal vessel structure from retinal fundus images. 2D wavelet transform assisted morphological gradient operation based ‘Contrast Limited Adaptive Histogram Equalization’ technique has been introduced for the preprocessing of the low contrast fundus images. Morphological gray level hit-or-miss transform with multi-structuring element with varying orientation has been proposed for the separation of blood vessel from its background. Finally a hysteresis thresholding, guided by some morphological operations has been employed to obtain the binary image excluding other unwanted areas. The proposed methodology has been tested on DRIVE database and a maximum accuracy and an average accuracy of 95.65 and 94.31% respectively have been achieved.
KeywordsComputer aided diagnosis Diabetic retinopathy Hit-or-miss transform Segmentation Wavelet transform
This work is supported by the Department of Electronics and IT, Govt. of India through ‘Visvesvaraya PhD scheme’ awarded to Jadavpur University, India.
- Abràmoff, M. D., Garvin, M. K., & Sonka, M. (2010). Retinal imaging and image analysis. IEEE Transactions on Medical Imaging, 1(3), 169–208.Google Scholar
- Chatterjee, S., Dey, D., & Munshi, S. (2017b). Studies on a formidable dot and globule related feature extractiontechnique for detection of melanoma from dermoscopic images. In Proceedings of the computer, communication and electrical technology (pp. 337–341). (Taylor & Francis Group).Google Scholar
- DRIVE database for retinal fundus images. http://www.isi.uu.nl/Research/Databases/DRIVE.
- Gonzalez, R. C., & Woods, R. E. (2014). Digital image processing (3rd ed.). London: Pearson.Google Scholar
- Pal, S., & Chatterjee, S. (2017). Mathematical morphology aided optic disk segmentation from retinal images. In 2017 3rd IEEE international conference on condition assessment techniques in electrical systems (CATCON) (pp. 380–385).Google Scholar
- Saffarzadeh, V. M., Osareh, A., & Shadgar, B. (2014). Vessel segmentation in retinal images using multi-scale line operator and Kmeans clustering. Journal of Medical Signals and Sensors, 4(2), 122–129.Google Scholar
- Shapiro, L. G., & Stockman, G. C. (2001). Computer vision (pp. 137–150). Upper Saddle River: Prentice Hall.Google Scholar
- Soille, P. (2002). Advances in the analysis of topographic features on discrete images. In A. Braquelaire, J.-O. Lachaud & A. Vialard (Eds.), Proceedings of the DGCI’02—10th international conference on discrete geometry for computer imagery. Lecture notes in Computer Science (Vol. 2301, pp. 175–186). Bordeaux: Springer.Google Scholar