Model-driven grouping and recognition of generic object parts from single images

Grouping is often intended as a general-purpose early vision stage which gathers together image features of perceptual salience, usually having a well-deenable structure. This work addresses the problem of generic part-based grouping and recognition from single two-dimensional edge images following a strategy that employs generic part models at all stages: the key underlying idea is to perform a purposive grouping of simple parts and these parts can be conveniently represented by generic part models. This paper outlines the proposed computational method, which is extensively treated in 18].