Digital Image Processing

R. Priya ¹, Vasantha Kalyani David ²

Affiliations
1 Department of Computer Science, Sree Narayana Guru College, Coimbatore, IN
2 Department of Computer Science, Avinashilingam Deemed University, Coimbatore, IN

Abstract

Recently the usage of multimedia contents like images and videos has increased. This usage has created the problem of locating from a very large database. This paper presents Content Based Image Retrieval (CBIR) system that uses multiple feature fusion to retrieve images. The features like color, shape and texture are used. The color histogram is used to extract color feature and active contour model is used for shape extraction. K-means and SOM algorithms are used for clustering and dimensional reduction. The experimental results show that the proposed CBIR system is better in terms of precision, recall and speed of image retrieval.

Keywords

Content Based Image Retrieval, Color Histogram, Contour Model, K-Means, Self Organizing Map.

Full Text

     

R. Priya ¹, P. Aruna ¹

Affiliations
1 Department of Computer science and Engineering, Annamalai University, IN
2 Department of Computer Science and Engineering, Annamalai University, IN

Abstract

This paper proposes an automated system for the detection of important anatomical structures such as the Blood Vessels, Optic Disc (OD), Macula and also Exudates in digital fundus retinal images. Blood vessel Detection (BVD) was done using canny edge detection. Optic disc localization was done using pyramidal decomposition and Hausdorff-based template matching. Macula was located using pyramidal decomposition. Exudates are found using machine learning algorithm which uses k-nearest neighbor classifier and a linear discriminant classifier. The procedure has been tested on a database of about 100 color fundus images acquired from a digital non-mydriatic fundus camera and the experimental results show the accuracy of the system.

Keywords

Blood Vessels, Exudates, Macula, Optic Disc.

Full Text