Mammography is the most widely used tool for the early detection of breast cancer. Computerbasedalgorithms can be developed to improve diagnostic information in mammograms and assist the radiologistto improve diagnostic accuracy. In this paper, we propose a novel computer aided technique to classifyabnormalities in mammograms using fusion of local and global features. The objective of this work is to test theeffectiveness of combined use of local and global features in detecting abnormalities in mammograms. Localfeatures used in the system are Chebyshev moments and Haralick’s gray level co-occurrence matrix basedtexture features. Global features used are Laws texture energy measures, Gabor based texture energy measuresand fractal dimension. All types of abnormalities namely clusters of microcalcifications, circumscribed masses,spiculated masses, architectural distortions and ill-defined masses are considered. A support vector machineclassifier is designed to classify the samples into abnormal and normal classes. It is observed that combined useof local and global features has improved classification accuracy from 88.75% to 93.17%.