人工知能学会誌（1986～2013, Print ISSN:0912-8085）
重なりあった二次元形状の認識
1988 年 3 巻 4 号 p. 461-473
詳細
1988 年 3 巻 4 号 p. 461-473
This paper describes a new method for the recognition of partially occluded 2-D objects. This method considers an object as a set of straight lines combined each other locally as typical features of an object. Possible candidate models are estimated from these features, and detailed structural matching is performed between these models and the features obtained from a picture. 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 objects are obtained. Lines are matched with a model minutely when model candidates are limited to one or a few.
