Ant-Snake model for Linear Feature Extraction from Satellite Image
Journal Title: INTERNATIONAL JOURNAL OF COMPUTERS & TECHNOLOGY - Year 2014, Vol 13, Issue 6
Abstract
This paper proposes an optimized mathematical model for linear feature extraction from satellite images. The model is based on a developed ant colony model combined with the snake model (called Ant-Snake model) to identify and extract the linear features like roads from satellite images. The process is started with the developed ant colony model to recognize and identify interest object and then with a snake model extract object. The developed ant model is able to establish a pheromone matrix that represents the object information at each pixel position of the image, according to the movements of a number of ants which are dispatch to move on the image. And the snake model is a parametric curve which is allowed to deform from some arbitrary initial locations from pheromone matrix toward the desired final location by minimizing an energy function. Experimental results are provided to demonstrate the superior performance of the proposed approach.
Authors and Affiliations
Jalal Amini, Leila Mohammadnia
Keywords
Related Articles
- EP ID EP650564
- DOI 10.24297/ijct.v13i6.2519
- Views 98
- Downloads 0
Coloured Image Segmentation Using K-Means Algorithm
Very large collections of images are growing ever more common. From stock photo collections to proprietary databases to the Web, these collections are diverse and often poorly indexed; unfortunately, image retrieval syst...
A Framework for e-Democracy implementation in the Developing Nations
Several e-Democracy implementations started as an offshoot of e-Government implementation where other models of e-Government such as Government to Government (G2G), Government to Business (G2B), Government to Employees (...
ACID GAS ABSORPTION STUDIES IN PACKED COLUMN
Carbon dioxide is a major greenhouse gas that results in climatic changes. Reducing CO2 emission for addressing the climatic change concerns is becoming increasingly important as the CO2 concentration in the atmosphere h...
Semi-Automated Ontology building through Natural Language Processing
Ontology is a backbone of semantic web which is used for domain knowledge representation. Ontology provides the platform for effective extraction of information. Usually, ontology is developed manually, but the manual on...
A review on the Detection of Missing Content Queries in FAQ Retrieval Systems
When developing an automated FAQ retrieval system, the information supplier constructs question candidates in advance using their own knowledge. Then they answer these question candidates to create question-answer pairs...