期刊名称：ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
印刷版ISSN：2194-9042
电子版ISSN：2194-9050
出版年度：2006
卷号：XXXVI-4/C42
出版社：Copernicus Publications
摘要：Second-order statistical texture image is regarded as one of useful images which can be produced from original data images, and wavelet scheme is also multi-resolution image analysis, as one of current issues in remote sensing image processing. Though texture image and wavelet decomposed image can be applied for remote sensing image, there are rare cases in quantitative interpretation with the combined images. In this study, we attempted the classification application of texture image in wavelet scheme; in other words, this was concerned classification of wavelet-based texture image. Our approach consists in several cases: conventional multi- spectral classification with original image sets, classification with texture images, and classification with wavelet-based texture image. In addition, we studied different types of texture parameters and wavelet basis functions, considering the affect of classification accuracy. In conclusion, it is thought that we can provide some criteria to choose appropriate wavelet basis function and texture parameter in classification
