(with Michael Tarr)
Recently, the assumed goal of computer vision, to reconstruct a representation of the scene, has been criticized as unproductive and impractical. Critics have suggested that the reconstructive approach should be supplanted by a new purposive approach that emphasizes functionality and task driven perception at the cost of general vision. In response to these arguments, we claim that the recovery paradigm central to the reconstructive approach is viable, and moreover, provides a promising framework for understanding and modeling general purpose vision in humans and machines. An examination of the goals of vision from an evolutionary perspective and a case study involving the recovery of optic flow support this hypothesis. In particular, while we acknowledge that there are instances where the purposive approach may be appropriate, these are insufficient for implementing the wide range of visual tasks exhibited by humans (the kind of flexible vision system presumed to be an end-goal of artificial intelligence). Furthermore, there are instances, such as recent work on the estimation of optic flow, where the recovery paradigm may yield useful and robust results. Thus, contrary to certain claims, the purposive approach does not obviate the need for recovery and the reconstruction of flexible representations of the world.
Tarr, M. J. and Black, M. J., A computational and evolutionary perspective on the role of representation in computer vision, CVGIP: Image Understanding, Vol. 60, No. 1, pages 65-73, July 1994. (pdf)
Tarr, M. J. and Black, M. J., Reconstruction and purpose, CVGIP: Image Understanding, Vol. 60, No. 1, pages 113-118, July 1994. (pdf).
Black, M. J. (Chair), Aloimonos, Y., Brown, C. M., Horswill, I., Malik, J., G. Sandini, and Tarr, M. J., Action, representation, and purpose: Re-evaluating the foundations of computational vision, International Joint Conference on Artificial Intelligence, IJCAI-93, Chambery, France, 1993, pp. 1661-1666. (postscript)