Abstract
It is of great importance to early detect abnormal brains, in order to save social resources. However, potential of wavelet decomposition is not fully explored and widely used. The wavelet-energy was a successful feature descriptor that achieved excellent performance in various applications; hence, we propose a wavelet-energy based new approach for automated classification of MR human brain images. The approach consisted of a three-stage system, including wavelet decomposition, energy extraction, and support vector machines. The results of proposed approach showed its performance was comparable with state-of-the-art algorithms. In addition, it provided a new means to detect features indicative of abnormal brains.