Learning and Detection of Object Landmarks in Canonical Object Space

This work contributes to part-based object detection and recognition by introducing an enhanced method for local part detection. The method is based on complex-valued multiresolution Gabor features and their ranking using multiple hypothesis testing. In the present work, our main contribution is the introduction of a canonical object space, where objects are represented in their ``expected pose and visual appearance´´. The canonical space circumvents the problem of geometric image normalisation prior to feature extraction. In addition, we define a compact set of Gabor filter parameters, from where the optimal values can be easily devised. These enhancements make our method an attractive landmark detector for part-based object detection and recognition methods.