Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
DEEP LEARNING-BASED FACE IMAGE EVALUATION METHOD AND APPARATUS, DEVICE, AND MEDIUM
Document Type and Number:
WIPO Patent Application WO/2022/126917
Kind Code:
A1
Abstract:
A deep learning-based face image evaluation method and apparatus, a device, and a medium. The method comprises: acquiring a face image used for training, and acquiring an image recognition area thereof; graying the image recognition area to obtain a gray scale image; calculating a gradient value of the gray scale image to obtain the gradient value corresponding to the gray scale image; performing vector extraction according to a face evaluation model; performing dimensionality reduction on an obtained basic vector to obtain a target vector, and updating parameters of the face evaluation model according to the target vector and marking data to obtain a trained face evaluation model; and inputting a face image to be evaluated into the trained face evaluation model, and outputting the evaluation result. The present application further relates to blockchain technology, and the face image to be evaluated is stored in a blockchain. In the method, by training the face evaluation model, the degree of blurring of the face image to be evaluated is output, such that the evaluation precision of a face image can be improved.

Inventors:
CHEN DAN (CN)
LU JIN (CN)
CHEN BIN (CN)
LIU YUYU (CN)
Application Number:
PCT/CN2021/083750
Publication Date:
June 23, 2022
Filing Date:
March 30, 2021
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
PING AN TECH SHENZHEN CO LTD (CN)
International Classes:
G06T7/00
Foreign References:
CN112529888A2021-03-19
CN103839033A2014-06-04
CN108171254A2018-06-15
CN105160336A2015-12-16
US20180204094A12018-07-19
Attorney, Agent or Firm:
SHENZHEN TALENT PATENT SERVICE (CN)
Download PDF: