Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
INSPECTION METHOD AND INSPECTION DEVICE
Document Type and Number:
WIPO Patent Application WO/2018/188653
Kind Code:
A1
Abstract:
Disclosed are an inspection device and an inspection method. The method comprises: carrying out X-ray scanning on a container to be inspected so as to obtain a transmission image, then using a convolutional neural network to generate, from the transmission image, a first vector describing the local transmission image, and using a recurrent neural network to generate a word vector, from a text description of cargoes in the container, to serve as a second vector; integrating the first vector and the second vector so as to obtain a third vector expressing the transmission image and the text description; and determining, based on the third vector, the category of the cargoes in the container. According to the embodiments of the present disclosure, the general category of target cargoes can be preliminary determined, thereby facilitating an image determiner in making a further determination.

Inventors:
ZHANG JIAN (CN)
ZHAO ZHANYONG (CN)
GU JIANPING (CN)
LIU YAOHONG (CN)
ZHAO ZIRAN (CN)
Application Number:
PCT/CN2018/083012
Publication Date:
October 18, 2018
Filing Date:
April 13, 2018
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
UNIV TSINGHUA (CN)
NUCTECH CO LTD (CN)
International Classes:
G06K9/62; G06F40/237
Domestic Patent References:
WO2015062352A12015-05-07
Foreign References:
CN104751163A2015-07-01
CN105784732A2016-07-20
Other References:
ZHANG, JIAN ET AL.: "The Application of Neural Network Model for X-ray Image Fusion", COMPUTERIZED TOMOGRAPHY THEORY AND APPLICATIONS, vol. 20, no. 2, 30 June 2011 (2011-06-30), pages 235 - 243, XP009517427, ISSN: 1004-4140
See also references of EP 3611666A4
Attorney, Agent or Firm:
CHINA SCIENCE PATENT & TRADEMARK AGENT LTD. (CN)
Download PDF: