Digital Image Processing

S. Vasanthi ¹, C. Sujatha ²

Affiliations
1 VLSI Design, Sethu Institute of Technology, Kariapatti, IN
2 ECE Dept, Sethu Institute of Technology, Kariapatti, IN

Abstract

This paper proposes a technique for FPGA implementation of road detection on satellite images. Many Geographic Information System (GIS) activities such as GIS updating, geo-referencing and geospatial integration requires detection of road from satellite images. Hence extraction of roads from satellite image has grown in importance. A technique for road detection using edge detection and morphological operation and its FPGA implementation using Xilinx System Generator (XSG) has been proposed. Initially the image is preprocessed to remove unwanted noises. Then edges of the image are detected using sobel edge detector and the Euclidean distance between neighbor pixels in the edge map is computed. Then skeletonization is done on the edge map based on the distance function. To detect the road segments a double thersholding operation is performed. Finally the image is subject to post processing to obtain the binary road map.

Keywords

Xilinx System Generator, FPGA, Edge Detection, Morphological Operation, Road Detection.

Full Text

     

Richu Paul ¹, S. Vasanthi ²

Affiliations
1 Department of Information Technology, Christ College of Engineering and Technology, Puducherry-605005, IN
2 Department of Electronics and Communication Engineering, Anna University of Technology, Coimbatore, IN

Abstract

Diabetic retinopathy is a major cause of preventable blindness in the world. Regular screening is essential in order detect the early stages of diabetic retinopathy for timely treatment to prevent or delay further deterioration. This project detects the presence of abnormalities in the retina such as the exudates in retinopathy images using computational intelligence techniques. The color retinal images are segmented using fuzzy c-means clustering following color normalization and contrast enhancement. For classification of these segmented regions into exudates and nonexudates, a set of initial features such as color, size, edge strength, and texture are extracted. A genetic based algorithm is used to rank the features and identify the subset that gives the best classification results. Using a multilayer neural network classifier, the selected feature vectors are then classified.

Keywords

Fuzzy C-Means (FCMs), Kmeans Algorithm, Gabor Filters, Neural Networks (NNs), Retinal Exudates.

Full Text