Patent · US Expired

Unsupervised learning of object categories from cluttered images

US7280697B2 · kind B2 · utility

17Cited by
5References
18Claims
0Family size

Assignee

Inventors

Key dates

Filing dateFeb 1, 2002
Grant dateOct 9, 2007
Priority date
Expiry dateMar 29, 2024

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06F18/24155
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Unsupervised learning of object category from images is carried out by using an automatic image recognition system. A plurality of training images are automatically analyzed using an interest operator which produces an indication of features. Those features are clustered using a vector guantizer. The model is learned from the features using expectation maximization to assess a joint probability of which features are most relevant.

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