Patent · US Active

Digital image analysis utilizing multiple human labels

US8379994B2 · kind B2 · utility

10Cited by
2References
9Claims
0Family size

Assignee

Inventors

Key dates

Filing dateOct 13, 2010
Grant dateFeb 19, 2013
Priority date
Expiry dateNov 8, 2031

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06F18/217
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Systems and methods for implementing a multi-label image recognition framework for classifying digital images are provided. The provided multi-label image recognition framework utilizes an iterative, multiple analysis path approach to model training and image classification tasks. A first iteration of the multi-label image recognition framework generates confidence maps for each label, which are shared by the multiple analysis paths to update the confidence maps in subsequent iterations. The provided multi-label image recognition framework permits model training and image classification tasks to be performed more accurately than conventional single-label image recognition frameworks.

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