Diabetic Retinopathy (DR) is one of the major causes of blindness in diabetic patients. Early detection is required to reduce the visual impairment causing damage to eye. Microaneurysms are the first clinical sign of diabetic retinopathy. Robust detection of microaneurysms in retinal fundus images is critical in developing automated system. In this paper we present a new technique for detection and localization of microaneurysms using Dual tree complex wavelet transform and log Gabor features. Retinal blood vessels are eliminated using minor and major axis properties and correlation is performed on images with the Gabor features to detect the microaneurysms. Feature vectors are extracted from candidate regions based on texture properties. Support vector machine classifier classifies the detected regions to determine the findings as microaneurysms or not. Accuracy of the algorithm is evaluated using the sensitivity and specificity parameters.
CITATION STYLE
Angadi, S., & Ravishankar, M. (2015). Detection and classification of microaneurysms using DTCWT and log gabor features in retinal images. In Advances in Intelligent Systems and Computing (Vol. 328, pp. 589–596). Springer Verlag. https://doi.org/10.1007/978-3-319-12012-6_65
Mendeley helps you to discover research relevant for your work.