Patent · US Active

Multi-label multi-instance learning for image classification

US8249366B2 · kind B2 · utility

5Cited by
4References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateJun 16, 2008
Grant dateAug 21, 2012
Priority date
Expiry dateJun 22, 2031

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06V10/457
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Described is a technology by which an image is classified (e.g., grouped and/or labeled), based on multi-label multi-instance data learning-based classification according to semantic labels and regions. An image is processed in an integrated framework into multi-label multi-instance data, including region and image labels. The framework determines local association data based on each region of an image. Other multi-label multi-instance data is based on relationships between region labels of the image, relationships between image labels of the image, and relationships between the region and image labels. These data are combined to classify the image. Training is also described.

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