Feature Extraction in Medical Image using Ant Colony Optimization : A Study
Journal Title: International Journal on Computer Science and Engineering - Year 2011, Vol 3, Issue 2
Abstract
The front end of most vision systems consists of an edge detection as preprocessing. The vision of objects is easy for the human because of the natural intelligence of segmenting, pattern matching and recognizing very complex objects. But for the machine, everything needs to be artificially induced and it is not so easy to recognize and identify objects. Towards Computer vision, the Machine needs pattern recognition; extracting the important features so as to recognize the objects, where the boundary detection or the edge detection is very crucial. Edge detection is finding the points where there are sudden changes in the intensity values and linking them suitably. This paper aims at presenting a comparison of the Gradient based existing edge detectors, with a swarm intelligence Ant Colony. Though, these detectors are applied on to the same image, they may not see the same edge pixels. Some detectors seems to be good only for simple transparent images which are less noise prone, and marks pseudo and congested edges in case of denser images. Hence it would be appreciated, to have an edge detector, which is sensitive in detecting edges in majority of the common types of edges. With this in mind, the authors propose a new edge detector based on swarm intelligence, which fairly detects the edges of all types of images with improved quality, and with a low failing probability in detecting edges.
Authors and Affiliations
A. Amali Asha , S. P. Victor , A. Lourdusamy
End to End delay analytical estimation of NoC with VBR traffic
Network On Chip (NoC) integrate real time application that require strength performance guaranties, usually enforced by a tight upper bound on the maximum end-to-end delay. The complex and unpredictable nature of data tr...
Generalisation of RSA Scheme using fundamental groups and ZKIP
We address the problem of computation involved in RSA algorithm namely exponentiation under modulo arithmetic and various mathematical and timing attacks in RSA. The computation is made easy and quick by assigning elemen...
Dynamic Broadcast Scheduling in DDBMS
This system will address the problem of online scheduling sequential data objects with the principle of periodicity in the context of dynamic information dissemination. Many modern information applications spread dynamic...
Considerable Issues to detect Topical-Relevance Upon Free Texts
Topical Relevance has always been an equivocal concept in IR evaluations upon text documents. Text Miners have been well engaged in unfolding various strategies in finding, how well the core content is expressed in a doc...
An Implementation Approach for Intrusion Detection System in Wireless sensor Network
The Intrusion Detection System (IDS) has become a critical component of wireless sensor networks security strategy. In this paper we have made an effort to document related issues and challenges of intrusion detection sy...