Results 1 
4 of
4
ViewBased Object Recognition Using Saliency Maps
, 1998
"... We introduce a novel viewbased object representation, called the saliency map graph (SMG), which captures the salient regions of an object view at multiple scales using a wavelet transform. This compact representation is highly invariant to translation, rotation (image and depth), and scaling, and ..."
Abstract

Cited by 48 (8 self)
 Add to MetaCart
We introduce a novel viewbased object representation, called the saliency map graph (SMG), which captures the salient regions of an object view at multiple scales using a wavelet transform. This compact representation is highly invariant to translation, rotation (image and depth), and scaling, and offers the locality of representation required for occluded object recognition. To compare two saliency map graphs, we introduce two graph similarity algorithms. The first computes the topological similarity between two SMG's, providing a coarselevel matching of two graphs. The second computes the geometrical similarity between two SMG's, providing a finelevel matching of two graphs. We test and compare these two algorithms on a large database of model object views.
The Representation and Matching of Categorical Shape
, 2005
"... We present a framework for categorical shape recognition. The coarse shape of an object is captured by a multiscale blob decomposition, representing the compact and elongated parts of an object at appropriate scales. These parts, in turn, map to nodes in a directed acyclic graph, in which edges enco ..."
Abstract

Cited by 9 (3 self)
 Add to MetaCart
We present a framework for categorical shape recognition. The coarse shape of an object is captured by a multiscale blob decomposition, representing the compact and elongated parts of an object at appropriate scales. These parts, in turn, map to nodes in a directed acyclic graph, in which edges encode both semantic relations (parent/child or sibling) as well as geometric relations. Given two image descriptions, each represented as a directed acyclic graph, we draw on spectral graph theory to derive a new algorithm for computing node correspondence in the presence of noise and occlusion. In computing correspondence, the similarity of two nodes is a function of their topological (graph) contexts, their geometric (relational) contexts, and their node contents. We demonstrate the approach on the domain of viewbased 3D object recognition.
GraphTheoretical Methods in Computer Vision
 IN: THEORETICAL ASPECTS OF COMPUTER SCIENCE: ADVANCED LECTURES, 2002
"... The management of large database sof hierarchical (e.g., multiscale or multilevel) imagefageB1' is a common problem in object recognition. Such structures are often represented as trees or directed acyclic graphs (DAGs), where nodes represent imagefageB4 abstractions and arcs represent spatial rel ..."
Abstract

Cited by 2 (0 self)
 Add to MetaCart
The management of large database sof hierarchical (e.g., multiscale or multilevel) imagefageB1' is a common problem in object recognition. Such structures are often represented as trees or directed acyclic graphs (DAGs), where nodes represent imagefageB4 abstractions and arcs represent spatial relations, mappings across resolution levels, component parts, etc. Object recognition consistsof two processes: indexing andverifi ation. In the indexing process, a collectionof one or more extracted imagefageB15 belonging to an object is used to select, fle a large databaseof object models, a small setof candidates likely to contain the object. Given this relatively small setof candidates, a verification, or matching procedure is used to select the most promising candidate. Such matching problems can bef44 ulated as largest isomorphic subgraph or largest isomorphic subtree problems,fo which a wealth of literature exists in the graph algorithms community. However, the natureof the vision instantiationof this problemofbl precludes the direct applicationof these methods. Due to occlusion and noise, no significant isomorphisms may exists between two graphs or trees. In this paper, we review our applicationof spectral encodingof a graphfa indexing to large databaseof imagefageB15 represented as DAGs. We will also review a more general classof matching methods, called bipartite matching, to two problems in object recognition.