A Coarse-to-Fine Strategy for
Multi-Class Shape Detection
Yali Amit, Donald Geman and Xiaodong Fan
Yali Amit is with the Department of Statistics and the Department of Computer Science, University of Chicago, Chicago, IL,
60637. Email: firstname.lastname@example.org. Supported in part by NSF ITR DMS-0219016.
Donald Geman is with the Department of Applied Mathematics and Statistics, and the Whitaker Biomedical Engineering
Institute, The Johns Hopkins University, Baltimore, MD 21218. Email:email@example.com. Supported in part by ONR under
contract N000120210053, ARO under grant DAAD19-02-1-0337, and NSF ITR DMS-0219016.
Xiaodong Fan is with the Department of Electrical and Computer Engineering, The Johns Hopkins University, Baltimore,
MD 21218. Supported in part by by ONR under contract N000120210053. Email:firstname.lastname@example.org.
September 2, 2004 DRAFT
Multi-class shape detection, in the sense of recognizing and localizing instances from multiple shape
classes, is formulated as a two-step process in which local indexing primes global interpretation. During
indexing a list of instantiations (shape identities and poses) is compiled constrained only by no missed
detections at the expense of false positives. Global information, such as expected relationships among
poses, is incorporated afterward to remove ambiguities. This division is motivated by computational
efficiency. In addition, indexing itself is organized as a coarse-to-fine search simultaneously in class