AN EFFICIENT APPROACH FOR EXTRACTION OF LINEAR FEATURES FROM HIGH RESOLUTION INDIAN SATELLITE IMAGERIES
Journal Title: International Journal on Computer Science and Engineering - Year 2010, Vol 2, Issue 4
Abstract
This paper presents an Object oriented feature extraction pproach in order to classify the linear features like drainage, roads etc. from high resolution Indian satellite imageries. It starts with the multiresolution segmentations of image objects for optimal separation and representation of mage regions or objects. Fuzzy membership functions were efined for a elected set of image object parameters such as mean, ratio, shape index, area etc. for representation of equired image objects. Experiment was carried out for both anchromatic (CARTOSAT-I) and multispectral (IRSP6 LISS IV) Indian satellite imageries. Experimental results show that the xtraction of linear features can be achieved in a satisfactory level through proper segmentation and appropriate definition & epresentation of key parameters of image objects.
Authors and Affiliations
D Chutia , DK Bhattacharyya
Keywords
Related Articles
- EP ID EP139722
- DOI -
- Views 110
- Downloads 0
WEB-BASED-SECURE ONLINE NONCHOICE –BASED EXAMINATION SYSTEM (WONES) using Cryptography
Web based Online Non-choice-based Examination System (WONES) is an effective solution for mass education evaluation. WONES ensures transactions between the examination server and the candidates by employing special authe...
An Improved Hop-Count Metric for Infrastructural Wireless Mesh Network
Wireless mesh networks (WMNs) consist of mesh routers and mesh clients, where mesh routers have minimal mobility and form the backbone of WMNs. They provide network access for both mesh and conventional clients. In a WMN...
A Modified Robust Queue Management with Feedback Compensation Technique to Manage the Congestion Control in Wireless Communication Networks
At present there has been a tremendous growth in the computer networks and wireless networks. Due to the enormous growth of voice, audio, video and data applications over the wireless networks, the requirement of congest...
Collaborative Clustering: An Algorithm for Semi-Supervised Learning
Supervised learning is the process of disposition of a set of consanguine data items which have known labels. The apportion of an unlabeled dataset into a conglomeration of analogous items(clusters) by the optimization o...
Neuro Language Generator
‘Neuro Language Generator using Finite State Machine’ is based on neural network and finite state machine. The undamental properties of neural network along with the power of Turing machine prove how it can be implement...