Magnetic resonance image analysis for detection of some neurodegenerative diseases are investigated and reported in this work. It is based on discrete wavelet transform in combination with different fractal analysis. The proposed action consists of two stages. In the first stage consists of image preprocessing which includes image enhancement, the region of extraction and skull stripping. In the second stage, the preprocessed image is converted to wavelet domain, and the following study is performed for feature extraction using fractal analysis. Finally proposed work has experimented with a publically available dataset of images having the mild cognitive impairment, Alzheimer's and healthy patient. The support vector machine based classifier has achieved the classification accuracy of 89.7 +- 0.6. This work will pave to develop a system for computer-aided diagnosis of some neurological diseases.