A Caltech Library Service

Recognition by probabilistic hypothesis construction

Moreels, Pierre and Maire, Michael and Perona, Pietro (2004) Recognition by probabilistic hypothesis construction. In: Computer Vision – ECCV 2004. Lecture Notes in Computer Science. Vol.1. No.3021. Springer , Berlin, pp. 55-68. ISBN 978-3-540-21984-2.

PDF - Accepted Version
See Usage Policy.


Use this Persistent URL to link to this item:


We present a probabilistic framework for recognizing objects in images of cluttered scenes. Hundreds of objects may be considered and searched in parallel. Each object is learned from a single training image and modeled by the visual appearance of a set of features, and their position with respect to a common reference frame. The recognition process computes identity and position of objects in the scene by finding the best interpretation of the scene in terms of learned objects. Features detected in an input image are either paired with database features, or marked as clutters. Each hypothesis is scored using a generative model of the image which is defined using the learned objects and a model for clutter. While the space of possible hypotheses is enormously large, one may find the best hypothesis efficiently-we explore some heuristics to do so. Our algorithm compares favorably with state-of-the-art recognition systems.

Item Type:Book Section
Related URLs:
URLURL TypeDescription ReadCube access
Perona, Pietro0000-0002-7583-5809
Additional Information:© 2004 Springer. The authors thank Prof. D.Lowe for kindly providing the code of his feature detector and for useful advice. They also acknowledge funding from the NSF Engineering Research Center on Neuromorphic Systems Engineering at Caltech.
Funding AgencyGrant Number
Center for Neuromorphic Systems Engineering, CaltechUNSPECIFIED
Subject Keywords:Image Processing and Computer Vision, Pattern Recognition, Computer Graphics, Artificial Intelligence (incl. Robotics), Image Processing and Computer Vision, Pattern Recognition Computer Graphics Artificial Intelligence (incl. Robotics)
Series Name:Lecture Notes in Computer Science
Issue or Number:3021
Record Number:CaltechAUTHORS:20140730-101718814
Persistent URL:
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:47610
Deposited By: Caroline Murphy
Deposited On:19 Aug 2014 22:24
Last Modified:10 Nov 2021 17:48

Repository Staff Only: item control page