Texture-Based Land Cover Classification Algorithm Using Hidden Markov Model for Multispectral Data

Texture-Based Land Cover Classification Algorithm Using Hidden Markov Model for Multispectral Data

Jenicka S (Anna University Chennai, India)
DOI: 10.4018/978-1-5225-2990-3.ch025
OnDemand PDF Download:
$30.00
List Price: $37.50

Abstract

In this chapter, the concept of stochastic optimal control is well explored using hidden Markov model (HMM) in classifying land covers of remotely sensed images. The features of land covers can be colour, shape, and texture. Texture is a useful feature in land cover classification. A texture-based land cover classification algorithm using HMM has been proposed. The local derivative pattern (LDP) texture descriptor for gray level images has been extended as multivariate local derivative pattern (MLDP) for remotely sensed images in this chapter. Experiments were conducted on IRS P6 LISS-IV data and the results were evaluated based on the classification accuracy and compared against the three existing methods such as wavelet, MLDP and colour gray level co-occurrence matrix (CGLCM). The results indicate that the proposed algorithm achieves a classification accuracy of 88.75%.
Chapter Preview
Top

Background

A texture model is a means of transforming a window of an image into a set of numbers called the feature vector. Literature reveals that texture measures can capture micro and macro patterns, as they can be captured by varying the size of the neighbourhood. Land cover classification has to incorporate uncertainty in order to improve classification accuracy. The problem of uncertainty is effectively handled in probabilistic modelling. So it was planned to propose a texture based land cover classification algorithm using hidden Markov model.

Complete Chapter List

Search this Book:
Reset