Large hierarchical object recognition using libraries of parameterized model sub-parts

Using Projective Invariants for Constant Time Library Indexing in Model Based Vision

“…The method is given in [It]-We may also determine the projective transformation between a conic and a pair of lines, and their corresponding projection in a different frame. 4 Conclusions. This paper describes the initial phases in the development of a large model based vision system which uses projectively invariant descriptors.…”

Generic Model Abstraction from Examples

“…5 Each path in our product graph corresponds to a pair of possible cuts in two regions. Consequently, our goal is to find that path yielding the best matching subregions and relations.…”

On the Verification of Hypothesized Matches in Model-Based Recognition

“…As a first example, we consider the application of the interpretation tree method Lozano-P6rez, 1984, 1987;Ettinger, 1987Ettinger, , 1988Marray, 1987aMarray, , 1987bMurray and Cook, 1988] to recognizing sets of two dimensional parts. In this approach, a tree of possible matching model and image features is constructed.…”

“…Recognition systems generally search for a matching between elements of an object model and instances of those elements in the data, recovering a transformation that maps part of the model onto part of the image. There are a number of different approaches to this model-based recognition problem, including clustering in parameter space (e.g., Stockman [1987], Stockman et al [1982], Thompson and Mundy [1987]), searching a tree of corresponding model and image features (e.g., Grimson [1989aGrimson [ , 1989b Grimson and Lozano-P6rez [1984,1987], Ettinger [1987, 19881, Murray [1987a, 1987b, Murray and Cook [1988], Ayache and Faugeras [1986], Faugeras and Hebert [1986], Ikeuchi [1987]), and directly searching for possible transformations from a model to an image (e.g., Fischler and Bolles [1981], Ullman [1987, 1988]) (see also Chin and Dyer [1986] and Besl and Jain (1985] for more comprehensive reviews). These approaches all share the common property that a decision is ,:ade about the presence or absence of an object on the basis of geometric evidence acquired from the sensory input.…”