|International Journal of Applied Information Systems|
|Foundation of Computer Science (FCS), NY, USA|
|Volume 6 - Number 5|
|Year of Publication: 2013|
|Authors: Manjiri B. Patwari, Ramesh R. Manza, Yogesh M. Rajput, Manoj Saswade, Neha Deshpande|
Manjiri B. Patwari, Ramesh R. Manza, Yogesh M. Rajput, Manoj Saswade, Neha Deshpande . Detection and Counting the Microaneurysms using Image Processing Techniques. International Journal of Applied Information Systems. 6, 5 ( November 2013), 11-17. DOI=10.5120/ijais13-451056
In this paper, we present an algorithm for the detection and counting of the Diabetic retinopathy lesion 'Microaneurysms' by using image processing techniques. Processed fundus Image is able to display the lesions which otherwise are visible only after angiography. This algorithm processes through following steps 1) Preprocessing operations on high resolution fundus images 2) For detecting the Microaneurysms , Morphological operation on high resolution fundus images along with some enhancement techniques like histogram equalization and intensity transformation function. 3) Segmentation for finding boundaries of the extracted Microaneurysms. Performance of this algorithm is tested using the fundus image database( 245 images) taken from Dr. Manoj Saswade, Dr. Neha Deshpande This algorithm achieves accuracy of 96% with 0. 92 sensitivity and 0 specificity for Saswade database, and also used statistical techniques.