A Maximum-Likelihood Strategy for Directing Attention during Visual Search
May 2001 (vol. 23 no. 5)
pp. 490-500
DOI Bookmark:
http://doi.ieeecomputersociety.org/10.1109/34.922707
Abstract—A precise analysis of an entire image is computationally wasteful if one is interested in finding a target object located in a subregion of the image. A useful “attention strategy” can reduce the overall computation by carrying out fast but approximate image measurements and using their results to suggest a promising subregion. This paper proposes a maximum-likelihood attention mechanism that does this. The attention mechanism recognizes that objects are made of parts and that parts have different features. It works by proposing object part and image feature pairings which have the highest likelihood of coming from the target. The exact calculation of the likelihood as well as approximations are provided. The attention mechanism is adaptive, that is, its behavior adapts to the statistics of the image features. Experimental results suggest that, on average, the attention mechanism evaluates less than 2 percent of all part-feature pairs before selecting the actual object, showing a significant reduction in the complexity of visual search. [1] N. Ayache and O. Faugeras, “HYPER: A New Approach for the Recognition and Positioning of Two-Dimensional Objects,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 8, no. 1, pp. 44-54, Jan. 1986.[2] J.J. Clark and N.J. Ferrier, “Modal Control of an Attentive Vision System,” Proc. Second Int'l Conf. Computer Vision, 1988.[3] S.M. Culhane and J.K. Tsotsos, “An Attentional Prototype for Early Vision,” Proc. Second European Conf. Computer Vision, pp. 512-562, 1992.[4] J. Duncan and G.W. Humphreys, “Visual Search and Stimulus Similarity,” Psychological Rev., vol. 96, pp. 433-458, 1989.[5] F. Ennesser and G. Medioni, “Finding Waldo, or Focus of Attention Using Local Color Information,” Proc. Computer Vision and Pattern Recognition, pp. 711-712, 1993.[6] W.E.L. Grimson and T. Lozano-Perez, “Localizing Overlapping Parts by Searching the Interpretation Tree,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 9, no. 4, pp. 469-482, Apr. 1987.[7] W.E.L. Grimson, Object Recognition by Computer. MIT Press, 1990.[8] F.A. Haight, Handbook of the Poisson Distribution. John Wiley&Sons, 1967.[9] A.H.C. van der Heijden, Selective Attention in Vision Routledge, 1992.[10] G.W. Humphreys and H.J. Müller, “SEarch via Recursive Rejection (SERR): A Connectionist Model of Visual Search,” Cognitive Psychology vol. 25, 1993.[11] L. Itti, C. Koch, and E. Niebur, “A Model for Saliency-Based Visual Attention for Rapid Scene Analysis,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 20, no. 11, pp. 1,254-1,259, Nov. 1998.[12] T. Lindeberg, “Detecting Salient Blob-Like Image Structures,” Int'l J. Computer Vision, vol. 11, no. 3, 1993.[13] G. Medioni and F. Ennesser, “Finding Waldo, or Focus of Attention Using Local Color Information,” Computer Vision and Pattern Recognition, 1993.[14] U. Neisser, “The Processes of Vision,” Scientific Am., vol. 219, no. 3, 1968.[15] K. Pahlavan and J. Eklundh, “A Head-Eye System—Analysis and Design,” CVGIP: Image Understanding, vol. 56, no. 1, July 1992.[16] R.D. Rimey and C. Brown, “Where to Look Next Using a Bayes Net,” Proc. European Conf. Computer Vision, 1992.[17] T.F. Syeda-Mahmood, “Data and Model-Driven Selection Using Closely-Spaced Parallel-Line Groups,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 881-885, 1994.[18] T.F. Syeda-Mahmood, “Data and Model-Driven Selection Using Color Regions,” Proc. European Conf. Computer Vision, pp. 321-327, 1992.[19] T.F. Syeda-Mahmood, “Model-Driven Selection Using Texture,” Proc. British Machine Vision Conf., pp. 65-74, 1993.[20] H.D. Tagare and J.G. Wang, “A Bayesian Strategy for Direction Attention During Object Recognition,” Technical Report 96-03, Yale Univ., 1996.[21] K. Toyama and G. Hager, “Incremental Focus of Attention for Robust Visual Tracking,” Proc. Computer Vision and Pattern Recognition, pp. 189-195, 1996.[22] A. Treisman, “Features and Objects in Visual Processing,” Scientific Am., Nov. 1986.[23] J.K. Tsotsos, “Analyzing Vision at the Complexity Level,” Behavioral and Brain Sciences, vol. 13, no. 3, pp. 423-469, 1990.[24] J.K. Tsotsos, S.M. Culhane, and W.Y.K. Wai, “Modeling Visual Attention in Selective Tuning,” Artificial Intelligence, to appear.[25] W.Y.K. Wai and J.K. Tsotsos, “Directing Attention to Onset and Offset of Image Events for Eye-Head Movement Control,” Proc. IEEE Workshop Visual Behavior, June 1994.[26] J.L. Turney, T.N. Mudge, and R.A. Volz, “Recognizing Partially Occluded Parts,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 7, no. 4, pp. 410-421, Apr. 1985[27] L.E. Wixson and D.H. Ballard, “Using Intermediate Objects to Improve the Efficiency of Visual Search,” Int'l J. Computer Vision, vol. 12, 1994.[28] J.M. Wolfe, K.R. Cave, and S.L. Franzel, “Guided Search: An Alternative to the Feature Integration Model for Visual Search,” J. Experiemental Psychology: Human Perception and Performance, vol. 15, 1989.
Index Terms:
Attention, object recognition, visual search.
Citation:
Hemant D. Tagare, Kentaro Toyama, Jonathan G. Wang, "A Maximum-Likelihood Strategy for Directing Attention during Visual Search," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 23, no. 5, pp. 490-500, May 2001, doi:10.1109/34.922707
Usage of this product signifies your acceptance of the
Terms of Use.
|
|||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb