Title:
METHOD AND SYSTEM FOR PERSON RECOGNITION
Document Type and Number:
WIPO Patent Application WO/2017/173605
Kind Code:
A1
Abstract:
A method and systems for person recognition, wherein the method comprises: providing a Convolutional Neural Network (CNN) having a feature extracting layer (1200), a region of interest (ROI) proposal layer (1300) coupled to the feature extracting layer (1200), and a person identifying layer (1400) coupled to the ROI proposal layer (1300), the ROI proposal layer (1300) and the person identifying layer (1400) being trained synchronously; extracting, via the feature extracting layer (1200), a feature map from the image; cropping, via the ROI proposal layer (1300), a ROI containing a candidate person, from the extracted feature map; and identifying, via the person identifying layer (1400), the candidate person contained in the cropped ROI, according to a preset target person image.
Inventors:
WANG XIAOGANG (CN)
XIAO TONG (CN)
LI SHUANG (CN)
XIAO TONG (CN)
LI SHUANG (CN)
Application Number:
PCT/CN2016/078549
Publication Date:
October 12, 2017
Filing Date:
April 06, 2016
Export Citation:
Assignee:
WANG XIAOGANG (CN)
International Classes:
G06V10/25
Foreign References:
| CN103955718A | 2014-07-30 | |||
| CN104102919A | 2014-10-15 | |||
| CN104268521A | 2015-01-07 | |||
| US20150363634A1 | 2015-12-17 |
Attorney, Agent or Firm:
INSIGHT INTELLECTUAL PROPERTY LIMITED (CN)
Download PDF: