Recognition of overlapping 2-D objects by local feature construction method

Abstract

A method is described for the recognition of partially occluded 2-D objects. This method considers a set of corners, parallel lines, and so on as typical features of an object. Possible candidate models are estimated from these features, and structural matching is performed between these models and features obtained from a picture by checking the combinations of various features. Even if the whole structure is not obtained due to a partial occlusion, the system can infer an object if some unique features of the object are obtained. Partial shapes and extracted lines are matched in detail with model candidates when they are limited to one or a few.<>