Spatial Gaussian Mixture Model for gender recognition

Patch-based approaches have become popular in many computer vision applications over recent years. An intrinsic flaw of this framework, missing of the spatial information, however, restricts its usage in face related applications where the spatial configuration is relatively settled. In this paper, we introduce a new patch feature representation, namely spatial Gaussian mixture models (SGMM), which enhances the traditional GMM approach by taking the spatial information into consideration at both local and global scales. In the meantime, SGMM inherits all the merits of GMM, such as precise appearance description and robustness to image misalignment. The experiments on gender recognition demonstrate that the SGMM representation achieves more than 40% relative error reduction compared with either GMM or SVM-based approaches.