Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
INSPECTION SYSTEM, IMAGE RECOGNITION SYSTEM, RECOGNITION SYSTEM, DISCRIMINATOR GENERATION SYSTEM, AND LEARNING DATA GENERATION DEVICE
Document Type and Number:
WIPO Patent Application WO/2019/176993
Kind Code:
A1
Abstract:
In order to provided technique capable of generating a discriminator with high inference accuracy at low cost, this inspection system generates, from first image data, multiple sets of second image data of a product; determines, by means of a first discriminator, whether or not to adopt each set of second image data as learning data; generates a learning data set on the basis of the second image data that was determined to be adopted as learning data; by applying machine learning utilizing the generated learning data set, constructs a second discriminator for determining the acceptability of a product; and uses the constructed second discriminator to determine the acceptability of a product in target image data.

Inventors:
IJIRI YOSHIHISA (JP)
Application Number:
PCT/JP2019/010183
Publication Date:
September 19, 2019
Filing Date:
March 13, 2019
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
OMRON TATEISI ELECTRONICS CO (JP)
International Classes:
G06N3/08; G06N3/04; G06V10/764
Foreign References:
JP2015191426A2015-11-02
JP2017168057A2017-09-21
JP2012026982A2012-02-09
Other References:
SALAMON, JUSTIN ET AL.: "Deep Convolutional Neural Networks and Data Augmentation for Environmental Sound Classification", 28 November 2016 (2016-11-28), pages 1 - 5, XP080720674, Retrieved from the Internet > [retrieved on 20190514]
UM T., TERRY ET AL.: "Data Augmentation of Wearable Sensor Data for Parkinson's Disease Monitoring using Convolutional Neural Networks", PROCEEDINGS OF THE 19TH ACM INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION, 13 November 2017 (2017-11-13), pages 216 - 220, XP081281539, Retrieved from the Internet [retrieved on 20190514]
TRAN, TOAN ET AL.: "A Bayesian Data Augmentation Approach for Learning Deep Models", 29 October 2017 (2017-10-29), pages 1 - 10, XP080832636, Retrieved from the Internet > [retrieved on 20190514]
Attorney, Agent or Firm:
TACHIBANA, Kenji et al. (JP)
Download PDF: