Skeletal Shape Abstraction from Examples

• Published in: IEEE transactions on pattern analysis and machine intelligence Vol. 31; no. 5; pp. 944 - 952
• Main Authors: Demirci, M.F., Shokoufandeh, A., Dickinson, S.J.
• Format: Journal Article
• Language: English
• Published: Los Alamitos, CA IEEE 01.05.2009; IEEE Computer Society; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Applied sciences; Artificial Intelligence; Computer science; control theory; systems; Exact sciences and technology; Heart; Humans; Image Enhancement - methods; Image Interpretation, Computer-Assisted - methods; Imaging, Three-Dimensional - methods; Indexing; Information retrieval. Graph; many-to-many graph matching; medial axis graphs; Motorcycles; Noise shaping; Object recognition; Pattern Recognition, Automated - methods; Power system modeling; Product development; prototype learning; Prototypes; Reproducibility of Results; Sensitivity and Specificity; Shape; Shape abstraction; Theoretical computing; Topology; Medial Axis Graphs; Shape Abstraction; Many-to-Many Graph Matching; Prototype Learning; Branching; Shape abstraction; medial axis graphs; Computer vision; prototype learning; Silhouette; Abstraction; many- to-many graph matching; Pattern analysis; Categorization; Artificial intelligence; Graph matching
• ISSN: 0162-8828; 1939-3539
• DOI: 10.1109/TPAMI.2008.267

Learning a class prototype from a set of exemplars is an important challenge facing researchers in object categorization. Although the problem is receiving growing interest, most approaches assume a one-to-one correspondence among local features, restricting their ability to learn true abstractions of a shape. In this paper, we present a new technique for learning an abstract shape prototype from a set of exemplars whose features are in many-to-many correspondence. Focusing on the domain of 2D shape, we represent a silhouette as a medial axis graph whose nodes correspond to "partsrdquo defined by medial branches and whose edges connect adjacent parts. Given a pair of medial axis graphs, we establish a many-to-many correspondence between their nodes to find correspondences among articulating parts. Based on these correspondences, we recover the abstracted medial axis graph along with the positional and radial attributes associated with its nodes. We evaluate the abstracted prototypes in the context of a recognition task.