Abstract
Abstract. With the number of channels in the hundreds instead of in the tens Hyper spectral imagery possesses much richer spectral information than multispectral imagery. The increased dimensionality of such Hyper spectral data provides a challenge to the current technique for analyzing data. Conventional classification methods may not be useful without dimension reduction pre-processing. So dimension reduction has become a significant part of Hyper spectral image processing. This paper presents a comparative analysis of the efficacy of Haar and Daubechies wavelets for dimensionality reduction in achieving image classification. Spectral data reduction using Wavelet Decomposition could be useful because it preserves the distinction among spectral signatures. Daubechies wavelets optimally capture the polynomial trends while Haar wavelet is discontinuous and resembles a step function. The performance of these wavelets are compared in terms of classification accuracy and time complexity. This paper shows that wavelet reduction has more separate classes and yields better or comparable classification accuracy. In the context of the dimensionality reduction algorithm, it is found that the performance of classification of Daubechies wavelets is better as compared to Haar wavelet while Daubechies takes more time compare to Haar wavelet. The experimental results demonstrate the classification system consistently provides over 84% classification accuracy.
Highlights
Remote sensing research focusing of image classification has long attracted the attention of the remote sensing community because classification results are the basis for many environmental and socio economic applications such as land cover classification, agriculture and urban land use(Gallego,2004)
The results show that Daubechies wavelet-based dimension reduction method provides a good computational efficiency as well as a better classification
We have qualitatively and quantitatively assessed the classification results by visual inspection and accuracy assessment respectively. By visual inspection it is clear from the classified images that the results from the Daubechies are better than the results from the Haar wavelet
Summary
Remote sensing research focusing of image classification has long attracted the attention of the remote sensing community because classification results are the basis for many environmental and socio economic applications such as land cover classification, agriculture and urban land use(Gallego,2004). Hyper spectral remote sensing involves image acquisition and analysis of spectral cubes which are composed of tens and hundreds of narrow spectral bands. This process is used for extracting, identifying and classifying materials. The main assumption is that there are relations between the chemical, biological and physical properties of those materials and phenomena and the characteristics of their reflected radiation distribution. Those relations are the basis of remote sensing analysis(Sellers et al, 1995). The Hyper spectral sensors commonly oversample the spectral signal to ensure that narrow band features are adequately represented
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
