International Journal of Computer Applications |
Foundation of Computer Science (FCS), NY, USA |
Volume 99 - Number 5 |
Year of Publication: 2014 |
Authors: Hanumanthappa M, S Regina Lourdhu Suganthi |
10.5120/17367-7891 |
Hanumanthappa M, S Regina Lourdhu Suganthi . Edge Detection in Color Images - A Comparative Study. International Journal of Computer Applications. 99, 5 ( August 2014), 5-7. DOI=10.5120/17367-7891
The ability to detect edges from an image plays a key role in solving many problems related to computer vision. Extracting appropriate features from an image is a great challenge in the context of content based image retrieval. Some important points in an image could be used to describe the features of an object. To recognize objects from an image, it is essential that the features extracted from an image are invariant due to noise and illumination. Such points lie in high contrast regions such as edges of an object. Generally, a color image is converted to gray scale image to detect the edges of objects. In this paper two color spaces namely RGB and HSV have been considered. These color spaces individually are combined with gray plane and the effect has been discussed. It is evident from the results that by either OR-ing the R, G, B planes with the grayscale plane or by OR-ing S, V planes with the grayscale plane more edges could be detected.