Contour Grouping and Abstraction using Simple Part Models

Grouping and Abstraction Using Simple Part Models Pablo Sala and Sven Dickinson Department of Computer Science, University of Toronto, Toronto ON, Canada We address the problem of contour-based perceptual grouping using a user-defined vocabulary of simple part models. We train a family of classifiers on the vocabulary, and apply them to a region oversegmentation of the input image to detect closed contours that are consistent with some shape in the vocabulary. ch a set of consistent cycles, they are both abstracted and categorized through a novel application of an active shape model also trained on the vocabulary. From an image of a real object, our framework recovers the projections of the abstract surfaces that comprise an idealized model of the object. We evaluate our framework on a newly constructed dataset annotated with a set of ground stract surfaces.

• Type: Conference
• Year: 2010
• Where: ECCV
• Keywords: Computer Vision, Contour-based Perceptual Grouping, ECCV 2010, Models Pablo Sala, User-defined Vocabulary