Title:
DUAL-VIEW-ANGLE ASSOCIATED SECURITY CHECK METHOD AND SYSTEM BASED ON NEURAL NETWORK AND MULTI-SOURCE DATA
Document Type and Number:
WIPO Patent Application WO/2023/087653
Kind Code:
A1
Abstract:
Disclosed in the present invention are a dual-view-angle associated security check method and system based on a neural network and multi-source data. The method comprises: inputting input data and output data into a deep neural network model for training; inputting equivalent atomic number information corresponding to an article category needing to be detected into a clustering algorithm for training to obtain an equivalent atomic number classifier; and acquiring X-ray images acquired by a primary X-ray imaging system and a secondary X-ray imaging system and the corresponding equivalent atomic number information, inputting the X-ray images and the corresponding equivalent atomic number information into the trained deep neural network model for identification, and inputting the identified equivalent atomic number information of the article into the trained equivalent atomic number classifier to obtain an associated detection result. According to the present invention, article identification is performed on the X-ray image by means of the deep neural network model, the equivalent atomic number of the article is classified, detected results are associated by means of an association strategy, and the X-ray image of the article which is not retrieved is automatically labeled, such that an article detection rate is improved, and the article detection efficiency is improved.
Inventors:
DENG YIQI (CN)
LONG XIAOHAI (CN)
SHENG CHENGGONG (CN)
PENG XIAN (CN)
XU JIAHUI (CN)
DUAN YADONG (CN)
LONG XIAOHAI (CN)
SHENG CHENGGONG (CN)
PENG XIAN (CN)
XU JIAHUI (CN)
DUAN YADONG (CN)
Application Number:
PCT/CN2022/094768
Publication Date:
May 25, 2023
Filing Date:
May 24, 2022
Export Citation:
Assignee:
HUNAN SUKE INTELLIGENT TECH CO LTD (CN)
International Classes:
G06N3/04
Foreign References:
| CN113792826A | 2021-12-14 | |||
| CN110488368A | 2019-11-22 | |||
| CN111290040A | 2020-06-16 | |||
| CN113159110A | 2021-07-23 | |||
| CN109946746A | 2019-06-28 | |||
| US20210256296A1 | 2021-08-19 |
Other References:
AYDIN ILHAN; KARAKOSE MEHMET; AKIN ERHAN: "A New Approach for Baggage Inspection by using Deep Convolutional Neural Networks", 2018 INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND DATA PROCESSING (IDAP), IEEE, 28 September 2018 (2018-09-28), pages 1 - 6, XP033507101, DOI: 10.1109/IDAP.2018.8620749
Attorney, Agent or Firm:
CHANGSHA LUCHUANG TIMES PATENT AGENCY (GENERAL PARTNER) (CN)
Download PDF: