A New Objective Test Criterion for Multispectral Dimension Reduction Evaluation

In this paper, we have proposed an objective test criterion to investigate the performance of dimension reduction capability of multispectral images. We evaluate four transform-based satellite image dimension reduction methods by using this criterion. This transform are principal omponent analysis, real wavelet transform, complex wavelet transform, and contourlet transform. The proposed objective test method is based on computing some image feature parameters and comparing their associated destruction rate. We have clarified the efficiency of this objective test criterion by implementing the four mentioned methods on various multispectral data sets. The experimental results show the efficiency of the proposed objective test criterion.

Keywords:

Dimension reduction , principal component analysis , real wavelet transform , complex wavelet transform , contourlet transform , and satellite images