In this work, classification of normal and abnormal human femur bone images are carried out using Support Vector Machines (SVM) and AdaBoost classifiers. The trabecular (soft bone) regions of human femur bone images (N=44) recorded under standard conditions are used for the study. The acquired images are subjected to auto threshold binarization algorithm to recognize the presence of mineralization and trabecular structures in the digitized images. The mechanical strength regions such as primary compressive and tensile are delineated by semi-automated image processing methods from the digitized femur bone images. The first and higher order statistical parameters are calculated from the intensity values of the delineated regions of interest and their gray level cooccurrence matrices respectively. The significant parameters are found using principal component analysis. The first two most significant parameters are used as input to the classifiers. Statistical classification tools such as SVM and AdaBoost are employed for the classification. Results show that the AdaBoost classifier performs better in terms of sensitivity and specificity for the chosen parameters for primary compressive and tensile regions compared to SVM. Copyright © 2011 by ASME.