A novel study of feature extraction technique for hyperspectral images of remote sensing is proposed. The approach is based on the greedy modular eigenspace (GME) scheme, which was designed to extract the simplest and most efficient feature modules for high-dimensional datasets. It presents a framework for hyperspectral images, which consists of two algorithms, referred to as the complete modular eigenspace (CME) and the feature scale uniformity transformation (FSUT). The CME scheme is introduced to improve the performance of GME feature extraction optimally by modifying the correlation coefficient operations. It is designed to extract features by a new defined multi-dimensional correlation matrix to optimize the modular eigenspace, while FSUT is performed to fuse most correlated features from different spectrums associated with different data sources. The performance of the proposed method is evaluated by applying to hyperspectral images of MODIS/ASTER (MASTER) airborne simulator during the Pacrim II campaign. The experiments demonstrate the proposed CME/FSUT approach is an effective scheme not only for the feature extraction but also for the band selection of high-dimensional datasets. It can improve the precision of hyperspectral image classification compared to conventional multispectral classification schemes.