Dynamic Resolving of Image Edge Detection Techniques
Loading...
Files
Date
2016-07-22T08:58:40Z
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
Image processing is the analysis and manipulation of a digitized image, especially in order to
improve its quality. Edge detection is an image processing technique for finding the boundaries
and edges of objects within images. The main purpose of edge detection is to simplify the image
data in order to minimize the amount of data to be processed. Edge detection can be used to
enhance the image by filtering the noise in X-ray images, satellite images etc. Canny, LoG, and
Sobel are the three most widely used techniques for edge detection. These techniques are not
suitable for all images because all these techniques have its advantages and disadvantages and
varying levels of noise. An adaptive edge-detection algorithm is necessary to provide a robust
solution that is adaptable to the varying noise levels. We propose an adaptive edge-detection
algorithm that chooses among the Canny algorithm, Sobel algorithm, and the LoG algorithm at
dynamic time based on the PSNR value, the one with more PSNR value is selected and given as
output. Thus, we provide a robust solution that is adaptable to the varying noise levels. The
output is an image with the edges detected from the input image. Eclipse, a java based open
source platform is used to develop the system. The system is implemented using native Java
API’s which is a programming framework that enables to run java code. Eclipse uses
WindowBuilder as a plug-in to build the interface.
Description
Keywords
Dynamic Resolving of Image Edge Detection Techniques, Amrita S Menon, Ashwini A, Bhavyashree B T, C Neshwa Salih