Title:
ARTIFICIAL-INTELLIGENCE-BASED VENEER DEFECT DETECTION METHOD, SYSTEM AND DEVICE
Document Type and Number:
WIPO Patent Application WO/2019/114372
Kind Code:
A1
Abstract:
Disclosed are an artificial-intelligence-based veneer defect detection method, system and device. An image of a veneer to be detected that has been subjected to reverse permeable irradiation is acquired; the image of the veneer to be detected is recognized and matched according to a defect detection model after machine learning is conducted; and quality information of the veneer to be detected is obtained according to a result of recognition and matching. The present invention solves the problems in conventional machine vision methods, such as the problem that only color or texture defects of a veneer can be detected, and the thickness uniformity of the veneer cannot be detected.
Inventors:
DING LEI (CN)
ZHANG XIANYAO (CN)
ZHANG XIANYAO (CN)
Application Number:
PCT/CN2018/108551
Publication Date:
June 20, 2019
Filing Date:
September 29, 2018
Export Citation:
Assignee:
BEIJING WOOD AI TECH LTD (CN)
International Classes:
G01N21/88; G01N21/89
Foreign References:
| CN108362702A | 2018-08-03 | |||
| CN101669023A | 2010-03-10 | |||
| JP2014215233A | 2014-11-17 | |||
| CA2514788A1 | 2006-02-06 |
Other References:
CHENG, WEI ET AL.: "Design of the Veneer Automatic Classification System based on computer vision", CHINA WOOD INDUSTRY, vol. 21, no. 3, 30 May 2007 (2007-05-30), pages 25
Attorney, Agent or Firm:
BEIJING CHEN QUAN INTELLECTUAL PROPERTY LAW FIRM (CN)
Download PDF: