GENERIC OBJECT RECOGNITION - BUILDING AND MATCHING COARSE DESCRIPTIONS FROM LINE DRAWINGS

This paper introduces primal access recognition of visual objects (PARVO), which is a computer vision system that addresses the problem of fast and generic recognition of unexpected 3-D objects from single 2-1) 20 yr, the field of computer vision has still not produced any clear understanding of how this complex high-level visual ability is even possible. On the other hand, the human visual system is an existence proof that such a competence is attainable. This is demonstrated informally by everyone's daily experience and more formally by the results of various psychological studies. Recently, RBC, which is a new human image understanding theory, has been proposed on the basis of some of these psychological results. However, no systematic computational evaluation of its many aspects has yet been reported. essential if the theory is ever to play a role in the progress of the computer vision field. The PARVO system discussed in this paper is a first step towards this goal since its design respects and makes explicit the main assumptions of the proposed theory. It analyses single-view 2-D line drawings of 3-D objects typical of the ones used in human image understanding studies. It is designed to handle partially occluded objects of different shape and dimension in various spatial orientations and locations in the image plane. The system is shown to successfully compute generic descriptions and then recognize man: common man-made objects.