{"type":"ScholarlyArticle","title":"Efficient Interpretation Policies","authors":[{"name":"Ramana Isukapalli","slug":"ramana-isukapalli","given":"Ramana","family":"Isukapalli","affiliation":"Crawfords Corner Road Lucent Technologies Holmdel , NJ 07733 USA"},{"name":"Russell Greiner","slug":"russell-greiner","given":"Russell","family":"Greiner","affiliation":"Department of Computing Science University of Alberta Edmonton , AB T6G 2E8 Canada"}],"abstract":"Many imaging systems seek a good interpretation of the scene presented — i.e., a plausible (perhaps optimal) mapping from aspects of the scene to real-world objects. This paper addresses the issue of finding such likely mappings efficiently. In general, an “(interpretation) policy” specifies when to apply which “imaging operators”, which can range from low-level edge-detectors and region-growers through highlevel token-combination–rules and expectation-driven objectdetectors. Given the costs of these operators and the distribution of possible images, we can determine both the expected cost and expected accuracy of any such policy. Our task is to find a maximally effective policy — typically one with sufficient accuracy, whose cost is minimal. We explore this framework in several contexts, including the eigenface approach to face recognition. Our results show, in particular, that policies which select the operators that maximize information gain per unit cost work more effectively than other policies, including ones that, at each stage, simply try to establish the putative most-likely interpretation.","doi":null,"url":"https://ijcai.org/proceedings/2001/182","pdf":"https://ijcai.org/proceedings/2001/0182.pdf","markdown":"https://ijcai.org/proceedings/2001/182.md","bibtex":"https://ijcai.org/proceedings/2001/bibtex/182","volume":{"slug":"2001","title":"Proceedings of the Seventeenth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2001","url":"https://ijcai.org/proceedings/2001/","year":2001,"location":"Seattle, Washington, USA","dates":"","editors":"","isbn":"","publisher":"International Joint Conferences on Artificial Intelligence","doi_prefix":""},"section":null,"track":"","number":182,"pages":{"first":1381,"last":1389},"keywords":[],"videos":[],"references":[{"position":1,"raw":"T Binford, T Levitt, and W Mann. Bayesian inference in model based machine vision. In UAI, 1989.","title":"Bayesian inference in model based machine vision","authors":"Binford, Levitt, Mann","year":"1989","venue":"UAI","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"S Chien, F Fisher, H Mortensen, and E Lo. Using ai planning techniques to automatically reconfigure software mod- ules. In Lecture Notes in CS, 1998.","title":"Using ai planning techniques to automatically reconfigure software modules","authors":"F Chien, H Fisher, Mortensen, Lo","year":"1998","venue":"Lecture Notes in CS","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"R. Duda and P. Hart. Pattern Classification and Scene Analysis. Wiley, New York, 1973.","title":"Pattern Classification and Scene Analysis","authors":"R Duda, P Hart","year":"1973","venue":null,"doi":null,"url":null,"internal_url":null},{"position":4,"raw":"B. Draper. Learning control strategies for object recogni- tion. In Ikeuchi and Veloso, editors, Symbolic Visual Learning. Oxford University Press, 1996.","title":"Learning control strategies for object recognition","authors":"B Draper","year":"1996","venue":"Symbolic Visual Learning","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"K Etemad and R Chellappa. Discriminant analysis for recognition of human faces. J. Optical Society of America, 1997.","title":"Discriminant analysis for recognition of human faces","authors":"K Etemad, R Chellappa","year":"1997","venue":"J. Optical Society of America","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"P Fua. Image Understanding for Intelligence Imagery, chapter Model-Based Optimization: An Approach to Fast, Ac- curate, and Consistent Site Modeling from Imagery. Morgan Kaufmann, 1997.","title":"Image Understanding for Intelligence Imagery, chapter Model-Based Optimization: An Approach to Fast, Accurate, and Consistent Site Modeling from Imagery","authors":"Fua","year":"1997","venue":null,"doi":null,"url":null,"internal_url":null},{"position":7,"raw":"R. Greiner and C. Elkan. Measuring and improving the effectiveness of representations. In IJCAI91, pages 518-524, August 1991.","title":"Measuring and improving the effectiveness of representations","authors":"R Greiner, C Elkan","year":"1991","venue":"IJCAI91","doi":null,"url":null,"internal_url":"/proceedings/1991/78"},{"position":8,"raw":"G Geman and B Jedynak. An active testing model for tracking roads in satellite images. IEEE PAMI, 1996.","title":"An active testing model for tracking roads in satellite images","authors":"G Geman, Jedynak","year":"1996","venue":"IEEE PAMI","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"R Haralick. Overview: Computer vision performance characterization. In ARPA IU, 1994.","title":"Overview: Computer vision performance characterization","authors":"Haralick","year":"1994","venue":"ARPA IU","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"R Huang and S Russell. Object identification: A bayesian analysis with application to traffic surveillance. Artificial Intel- ligence, 1996.","title":"Object identification: A bayesian analysis with application to traffic surveillance","authors":"R Huang, S Russell","year":"1996","venue":"Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"R. Isukapalli and R. Greiner. Efficient car recognition poli- cies. In ICRA, 2001.","title":"Efficient car recognition policies","authors":"R Isukapalli, R Greiner","year":"2001","venue":"ICRA","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"T S Levitt, J M Agosta, and T O Binford. Model-based influence diagrams for machine vision. In UAI, 1990.","title":"Model-based influence diagrams for machine vision","authors":"J M T S Levitt, T O Agosta, Binford","year":"1990","venue":"UAI","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"T. Levitt, M. Hedgecock, J. Dye, S. Johnston, V. Sha- dle, and D. Vosky. Bayesian inference for model-based segmen- tation of computed radiographs of the hand. Artificial Intelli- gence in Medicine, 1993.","title":"Bayesian inference for model-based segmentation of computed radiographs of the hand","authors":"T Levitt, M Hedgecock, J Dye, S Johnston, V Shadle, D Vosky","year":"1993","venue":"Artificial Intelligence in Medicine","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"T. Matsuyama. Expert systems for image process- ing: knowledge-based composition of image analysis processes. Computer Vision, Graphics, and Image Processing, 48(1):22- 49, 1989.","title":"Expert systems for image processing: knowledge-based composition of image analysis processes","authors":"T Matsuyama","year":"1989","venue":"Computer Vision, Graphics, and Image Processing","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"T. Mitchell. Machine Learning. McGraw-Hill, 1997.","title":"Machine Learning","authors":"T Mitchell","year":"1997","venue":null,"doi":null,"url":null,"internal_url":null},{"position":16,"raw":"A. Pope and D. Lowe. Vista: A software environment for computer vision research. In IEEE CVPR, 1994.","title":"Vista: A software environment for computer vision research","authors":"A Pope, D Lowe","year":"1994","venue":"IEEE CVPR","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"A. Pope and D. Lowe. Learning object recognition models from images. In Early Visual Learning, 1995.","title":"Learning object recognition models from images","authors":"A Pope, D Lowe","year":"1995","venue":"Early Visual Learning","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"A Pentland, B Moghaddam, and T Starner. View-based and modular eigenspaces for face recognition. In IEEE CVPR, 1994.","title":"View-based and modular eigenspaces for face recognition","authors":"Pentland, Moghaddam, Starner","year":"1994","venue":"IEEE CVPR","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"P Phillips, H Wechsler, J Huang, and P Rauss. The feret database and evaluation procedure for face recognition al- gorithms. Image and Vision Computing, 1998.","title":"The feret database and evaluation procedure for face recognition algorithms","authors":"H Phillips, J Wechsler, Huang, Rauss","year":"1998","venue":"Image and Vision Computing","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"V Ramesh and R M Haralick. Performance characteriza- tion of edge operators. In Machine Vision and Robotics Confer- ence, 1992.","title":"Performance characterization of edge operators","authors":"V Ramesh, R M Haralick","year":"1992","venue":"Machine Vision and Robotics Conference","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"S. Russell, D. Subramanian, and R. Parr. Provably bounded optimal agents. In IJCAI93, August 1993.","title":"Provably bounded optimal agents","authors":"S Russell, D Subramanian, R Parr","year":"1993","venue":"IJCAI93","doi":null,"url":null,"internal_url":"/proceedings/1993/48"},{"position":22,"raw":"K Sengupta and K Boyer. Information theoretic clustering of large structural modelbases. In IEEE CVPR, 1993.","title":"Information theoretic clustering of large structural modelbases","authors":"K Sengupta, K Boyer","year":"1993","venue":"IEEE CVPR","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"Richard S. Sutton and Andrew G. Barto. Reinforcement Learning: An Introduction. MIT Press, 1998.","title":"Reinforcement Learning: An Introduction","authors":"Richard S Sutton, Andrew G Barto","year":"1998","venue":null,"doi":null,"url":null,"internal_url":null},{"position":24,"raw":"S Srinivas. A polynomial algorithm for computing the optimal repair strategy in a system with independent component failures. In UAI, 1995.","title":"A polynomial algorithm for computing the optimal repair strategy in a system with independent component failures","authors":"Srinivas","year":"1995","venue":"UAI","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"M Turk and A Pentland. Eigenfaces for recognition. Jour- nal of Cognitive Neuroscience, 1991.","title":"Eigenfaces for recognition","authors":"M Turk, Pentland","year":"1991","venue":"Journal of Cognitive Neuroscience","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}