专利内容由知识产权出版社提供
专利名称：LEARNING PART-BASED MODELS OF
OBJECTS
发明人：Ananth Ranganathan,Roozbeh Mottaghi申请号：US13453571申请日：20120423
公开号：US20130279800A1公开日：20131024
专利附图：
摘要：A system and method are disclosed for learning part-based object modelsduring a learning phase from training images and applying the learned object models toan input image during runtime. The learned part-based object models are augmented by
appearance-based models of the objects. The part-based object models correspond tothe shapes of the parts of an object. The appearance-based models provide additionalappearance cues to the object models for object classification. The approach to learningpart-based object models has the capability of learning object models without usingviewpoint labels of the objects. The learning is also invariant to scale and in-planerotation of the objects.
申请人：Ananth Ranganathan,Roozbeh Mottaghi
地址：Mountain View CA US,Los Angeles CA US
国籍：US,US
更多信息请下载全文后查看
