Patent · US Active

Hierarchical interlinked multi-scale convolutional network for image parsing

US9530071B2 · kind B2 · utility

10Cited by
1References
21Claims
0Family size

Assignee

Inventors

Key dates

Filing dateOct 10, 2014
Grant dateDec 27, 2016
Priority date
Expiry dateFeb 4, 2035

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06V40/165
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

A disclosed facial recognition system (and method) includes face parsing. In one approach, the face parsing is based on hierarchical interlinked multiscale convolutional neural network (HIM) to identify locations and/or footprints of components of a face image. The HIM generates multiple levels of image patches from different resolution images of the face image, where image patches for different levels have different resolutions. Moreover, the HIM integrates the image patches for different levels to generate interlinked image patches for different levels, where interlinked image patches for different levels have different resolutions. Furthermore, the HIM combines the interlinked image patches to identify refined locations and/or footprints of components.

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