Diabetic Retinopathy is a major cause of blindness. It is mainly due to the development of abnormal new blood vessels in the retina. In this approach, we proposed an efficient method to detect the abnormal new blood vessels. The retinal images are pre-processed using Adaptive Histogram Equalization (AHE) and the blood vessels are enhanced by applying Top-hat and Bottom-hat transforms. The enhanced image is segmented using Fuzzy C Means Clustering (FCM) technique. Features based on shape, brightness, position and contrast are extracted from the segmented image and classified as normal or abnormal using K Nearest Neighbour (KNN) Classifier. The performance was evaluated on DRIVE and MESSIDOR database and an accuracy of 96.5% was obtained.

Diabetic Retinopathy (DR) is the primary cause of visual loss in case of diabetic patients. It is mainly caused by the changes in the blood vessels of the retina even though manual screening is available but they are very much time consuming and inefficient. Therefore for automatic detection of these changes and prevention of vision loss, color retinal image is an important tool used by the ophthalmologist. This paper discusses on seven different preprocessing available in literature and found the optimum technique for enhancing the retinal images. The performance of all the techniques has been tested on more than 1000 images obtained from several publicly available DRIVE and STARE and MESSIDOR dataset.

Advances in the eye care telemedicine system aid the diabetic patients in remote areas to stop the unwanted visit to ophthalmologist, reduces overall cost, time and money. Diabetic retinopathy, which is the primary cause of sight loss, has the most common symptoms like microaneurysms, haemorrhages, cotton‐wool spots, exudates and drusen. In this work, an efficient approach for the automatic detection of haemorrhages in colour retinal images is proposed and validated. The colour retinal images captured from the diabetic patients are enhanced by an effective pre‐processor. A bag of features based on intensity, colour and texture are extracted. Finally, the features are classified with the help of partial least square classifier. The classifier performance is validated on two publicly available databanks. The developed method obtains an area under receiver operating characteristic curve of 0.98 with an average execution time of 6 s. This application outperforms the existing approaches with high robustness and efficiency.

Reliable detection of abnormal vessels in color fundus image is still a great issue in medical image processing. An Efficient and robust approach for automatic detection of abnormal blood vessels in digital color fundus images is presented in this paper. First, the fundus images are preprocessed by applying a 3x3 median filter. Then, the images are segmented using a novel morphological operation. To classify these segmented image into normal and abnormal, seven features based on shape, contrast, position and density are extracted. Finally, these features are classified using a non-linear Support Vector Machine (SVM) Classifier. The average computation time for blood vessel detection was less than 2.4sec with a success rate of 99%. The performance of our proposed method is measured on publically available DRIVE and STARE database.

Glaucoma and Diabetic Retinopathy are the leading common cause of vision loss. Optic Disc and macula are the important landmark for the detection of these retinal pathology. Even though, the manual screening of Optic Disc and macula are available, they consume more time and have more human error. Therefore, there is a need of an automated application for the reliable and efficient localization of OD and macula. This paper presents a novel and fast stand-alone MATLAB application for the segmentation of these anatomical structures. This application uses colour K-means segmentation for locating macula and for detecting Optic Disc, bilateral filtering followed by Morphological operation is used. The application were evaluated on 135 glaucomatous images collected from local eye hospital and 200 diabetic retinopathy images from DIARETDB1 and DRIVE database. This stand-alone application consumes an average computation time of 13s for macula localization and 32s for OD segmentation with a success rate of 98%. Overall, the proposed application obtain an efficient result in the segmentation of both OD and macula, which in turn helps to detect glaucoma and Diabetic Retinopathy.