Constrained Energy Minimization for Matching-Based Image Recognition

We propose to use energy minimization in MRFs for matching-based image recognition tasks. To this end, the Tree-Reweighted Message Passing algorithm is modified by geometric constraints and efficiently used by exploiting the guaranteed monotonicity of the lower bound within a nearest-neighbor based classification framework. The constraints allow for a speedup linear to the dimensionality of the reference image, and the lower bound allows to optimally prune the nearestneighbor search without loosing accuracy, effectively allowing to increase the number of optimization iterations without an effect on runtime. We evaluate our approach on well-known OCR and face recognition tasks and on the latter outperform current state-of-the-art.

• Type: Conference
• Year: 2010
• Where: ICPR
• Authors: Tobias Gass, Philippe Dreuw, Hermann Ney
• Keywords: Computer Vision, ICPR 2010, Image Recognition Tasks, Lower Bound, Recognition Tasks