Title:
IMAGE CLASSIFICATION METHOD AND SYSTEM BASED ON KNOWLEDGE-DRIVEN DEEP LEARNING
Document Type and Number:
WIPO Patent Application WO/2023/108968
Kind Code:
A1
Abstract:
The present application relates to the technical field of image classification and provides an image classification method and system based on knowledge-driven deep learning. The method comprises: constructing an image classification model based on knowledge-driven deep learning, and training the constructed model; obtaining an image to be classified, and using a feature extraction module to perform feature extraction on the image to obtain a feature vector; and respectively inputting the feature vector into a prior knowledge pre-training module and an image classification module to obtain a prior knowledge multi-label classification result and an image classification result.
Inventors:
E HAIHONG (CN)
SONG MEINA (CN)
HE JIAWEN (CN)
HU TIANYI (CN)
ZHANG RURU (CN)
LI GUOYING (CN)
WANG LIFEI (CN)
YUAN LIFEI (CN)
SONG MEINA (CN)
HE JIAWEN (CN)
HU TIANYI (CN)
ZHANG RURU (CN)
LI GUOYING (CN)
WANG LIFEI (CN)
YUAN LIFEI (CN)
Application Number:
PCT/CN2022/087216
Publication Date:
June 22, 2023
Filing Date:
April 15, 2022
Export Citation:
Assignee:
BEIJING UNIV OF POSTS&TELECOMMUNICATIONS (CN)
International Classes:
G06V10/764; G06N3/04
Foreign References:
CN114266920A | 2022-04-01 | |||
CN109934261A | 2019-06-25 | |||
CN108665901A | 2018-10-16 | |||
CN113781465A | 2021-12-10 | |||
CN111429421A | 2020-07-17 | |||
CN111028153A | 2020-04-17 | |||
CN112560668A | 2021-03-26 | |||
US20040052328A1 | 2004-03-18 |
Attorney, Agent or Firm:
TSINGYIHUA INTELLECTUAL PROPERTY LLC (CN)
Download PDF: