Showing papers by "Wilhelm Burger published in 1996"

Recognition and learning with polymorphic structural components

Abstract: We address the problem of describing, recognizing, and learning generic, free-form objects in real-world scenes. An appearance-based system using weak-structure and evidence accumulation where object models are implicitly encoded in a learned decision tree and objects are represented in graph form as in the method developed by Bischof and Caelli (1994). The decision tree is used to classify sequences of image components, or part paths, extracted from the object to be recognized. The part paths are in turn used to accumulate evidence for the classification of the entire object. We introduce an improved method for generating part paths based upon the part compatibility graph, a replacement for Bischof and Caelli's implicit use of the part adjacency graph. A new formalism for extending the representation and recognition scheme to utilize multiple (polymorphic) types of primitive parts is presented and the approach is demonstrated on a selection of imagery.

Qualitative spatial relations using arrangements for complex images

Abstract: A new spatial relation called arrangements has been previously proposed to describe how embedded parts in an image are surrounded by their neighbors. Arrangements can be derived directly from the sequence of Voronoi cells bordering an embedded part of an image. It has been shown that it is possible to compare any two arrangements, caused by the embedding of the same parts, by use of the Diagonal Exchange Operator and the Voronoi Flower diagram. However, the algorithms previously proposed is practical only for very small sets of embedded parts because of both the expensive operation of computing the prerequisite area Voronoi tessellation and the exponential search complexity (in terms of the number of edges in the Voronoi tessellation) required to compute the distance metric. We present a new algorithm for computing arrangements efficiently for complex images containing a large number of embedded parts. Motivated by the new algorithm, we propose the use of arrangements for the indexing and retrieval of complex technical diagrams which may contain many similar parts.© (1996) COPYRIGHT SPIE--The International Society for Optical Engineering. Downloading of the abstract is permitted for personal use only.

Learning to recognize generic visual categories using a hybrid structural approach

Abstract: We address the problem of describing, recognizing, and learning generic, free-form objects in real-world scenes. For this purpose, we have developed a hybrid appearance-based approach where objects are encoded as loose collections of parts and relations between neighboring parts. The key features of this approach are: part decomposition based on local structure segmentation derived from multi-scale wavelet filters, flexible and efficient recognition by combining weak structural constraints, and learning and generalization of generic object categories (with possibly large intra-class variability) from real examples.