High Resolution peripheral Quantitative Computed Tomography (HR-pQCT) imaging for studying bone disease has become increasingly common. However, due to the bone inhomogeneity and the noise characteristics, segmentation of HR-pQCT data remains a challenging task. In this work we propose a novel segmentation technique of the cortical bone based on fuzzy energy active contours model. A novel approach as well as a new formulation of the fuzzy membership function are proposed to deal with the HR-pQCT inhomogeneity and separate the cortical bone from the trabecular one. Results show the efficiency and the high accuracy of the proposed approach compared to different existing techniques in terms of Dice similarity coefficient (DSC). Proposed method provides high result (DSC: 90.14±1.64%) compared to Burghardt (DSC: 85.86±3,16%) and FEBAC (DSC: 85.5±4.52%).