Patent · US Active

Learning part-based models of objects

US9111173B2 · kind B2 · utility

4Cited by
2References
26Claims
0Family size

Assignee

Inventors

Key dates

Filing dateApr 23, 2012
Grant dateAug 18, 2015
Priority date
Expiry dateJul 9, 2033

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06V10/426
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

A system and method are provided for learning part-based object models during a learning phase from training images and applying the learned object models to an 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 to the shapes of the parts of an object. The appearance-based models provide additional appearance cues to the object models for object classification. The approach to learning part-based object models has the capability of learning object models without using viewpoint labels of the objects. The learning is also invariant to scale and in-plane rotation of the objects.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.