%0 Conference Proceedings %F scene_text %A Zhang, Dong-Qing %A Chang, Shih-Fu %T Learning to Detect Scene Text Using a Higher-order MRF with Belief Propagation %B IEEE Workshop on Learning in Computer Vision and Pattern Recognition, in conjunction with CVPR (LCVPR) %C Washington DC %X Detecting text in natural 3D scenes is a challenging problem due to background clutter and photometric/gemetric variations of scene text. Most prior systems adopt approaches based on deterministic rules, lacking a systematic and scalable framework. In this paper, we present a partsbased approach for 3D scene text detection using a higherorder MRF model. The higher-order structure is used to capture the spatial-feature relations among multiple parts in scene text. The use of higher-order structure and the feature-dependent potential function represents significant departure from the conventional pairwise MRF, which has been successfully applied in several low-level applications. We further develop a variational approximation method, in the form of belief propagation, for inference in the higherorder model. Our experiments using the ICDAR?3 benchmark showed promising results in detecting scene text with significant geometric variations, background clutter on planar surfaces or non-planar surfaces with limited angles %U http://www.ee.columbia.edu/dvmm/publications/04/dqzhang_lcvpr2004.pdf %8 June %D 2004