by Kemal AKYOL, Şafak BAYIR, Baha ŞEN and Hasan B. ÇAKMAK
Original Research
Diabetic retinopathy is one of the main complications of diabetes mellitus and it is a progressive ocular disease, the most significant factor contributing to blindness in the later stages of the disease. It has been a subject of many studies in the medical image processing field for a long time. Hard exudates are one of the primary signs of early stage diabetic retinopathy diagnosis. Immediately identifying hard exudates is of great importance for the blindness and coexistent retinal edema. There are various ways of achieving meaningful information from an image and one of them is key point extraction method. In this study, we presented a technique based on the acquisition of important information by utilizing the description information about the image within the framework of the learning approach in order to identify hard exudates. This technique includes the learning and testing processes of the system in order to make the right decisions in the analysis of new retinal fundus images. We performed experimental validation on DIARETDB1 dataset. The obtained results showed us the positive effects of machine learning technique suggested by us for the detection of hard exudates.
Journal of Computer Sciences and Applications. 2016, 4(3), 59-66. DOI: 10.12691/jcsa-4-3-2
Pub. Date: November 29, 2016
20825 Views4564 Downloads
by V. Lokeswara Reddy
Original Research
As the multimedia system technologies have become more popular, users do not satisfied with the standard retrieval techniques, thus today the content based image retrieval is becoming source of exact and for quick retrieval. The last decade has witnessed great interest in research on content based image retrieval. In this paper a graph based ranking model has been proposed and successfully applied to content-based image retrieval, due to its outstanding ability to find underlying geometrical structure of the given image database. The Admin have control to add, delete and modify the image database and therefore the user will search the image that need to be accessed and later the graph is generated based on user search. Experimental results show that the proposed technique has high accuracy than other conventional methods for generating the graph.
Journal of Computer Sciences and Applications. 2016, 4(3), 52-58. DOI: 10.12691/jcsa-4-3-1
Pub. Date: September 27, 2016
17495 Views3228 Downloads