Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
DEBLURRED FACE RECOGNITION METHOD AND SYSTEM AND INSPECTION ROBOT
Document Type and Number:
WIPO Patent Application WO/2021/184894
Kind Code:
A1
Abstract:
The present application is suitable for the technical field of intelligent robots, and provides a deblurred face recognition method and system and an inspection robot. The method comprises: obtaining a video stream from a camera of the inspection robot, and performing video decoding on the video stream to obtain a decoded video image; performing face detection on the video image by using a face detection algorithm to obtain a region image, containing a face ROI region, in the video image; performing blur degree determination on the region image; if the region image is not the blurred image, performing face recognition on the video image to obtain a face recognition result; if the region image is a blurred image, extracting multiple continuous frames of images before and after the video image; inputting the multiple frames of images into a deblurred network to obtain a deblurred image, the deblurred network being a deep learning network obtained by pre-training training samples as which multiple blurred image samples and corresponding clear image samples are used; and performing face recognition on the deblurred image to obtain a face recognition result.

Inventors:
LIU YEPENG (CN)
CHENG JUN (CN)
GU JING (CN)
ZENG YUSHENG (CN)
PANG JIANXIN (CN)
XIONG YOUJUN (CN)
Application Number:
PCT/CN2020/140410
Publication Date:
September 23, 2021
Filing Date:
December 28, 2020
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
UBTECH ROBOTICS CORP LTD (CN)
International Classes:
G06K9/00
Foreign References:
CN111460939A2020-07-28
CN110210432A2019-09-06
CN109087256A2018-12-25
CN108875486A2018-11-23
CN110569809A2019-12-13
CN108109121A2018-06-01
Attorney, Agent or Firm:
SHENZHEN ZHONGYI UNION INTELLECTUAL PROPERTY AGENCY CO., LTD. (CN)
Download PDF: