Title:
LEARNING DEVICE, IMAGE RECOGNITION DEVICE, LEARNING METHOD, AND PROGRAM
Document Type and Number:
WIPO Patent Application WO/2018/198233
Kind Code:
A1
Abstract:
Provided are a learning device, an image recognition device, a learning method, and a program whereby it is possible to improve the accuracy with which a captured image is recognized using a classifier that has been trained using CG images. An intermediate feature quantity identification unit (44) identifies an intermediate feature quantity. An offset feature quantity identification unit (46) identifies an offset feature quantity on the basis of a CG intermediate feature quantity and a captured image intermediate feature quantity. A post-offset intermediate feature quantity identification unit (48) identifies a post-offset intermediate feature quantity associated with a CG image, on the basis of an intermediate feature quantity and an offset feature quantity that are associated with the CG image. A second classifier training unit (50) trains a second classifier (40b), which receives an intermediate feature quantity associated with a captured image when the captured image is recognized using a post-offset intermediate feature quantity associated with a CG image.
Inventors:
ONO DAICHI (JP)
Application Number:
PCT/JP2017/016565
Publication Date:
November 01, 2018
Filing Date:
April 26, 2017
Export Citation:
Assignee:
SONY INTERACTIVE ENTERTAINMENT INC (JP)
International Classes:
G06T7/00; G06V10/764
Foreign References:
| JPH0573663A | 1993-03-26 | |||
| JP2014137756A | 2014-07-28 |
Other References:
KENTARO TAJI ET AL.: "Fingerspelling Recognition based on AdaBoost with Hand-shape CG images", IEICE TECHNICAL REPORT, vol. 111, no. 472, 2 March 2012 (2012-03-02), pages 1 - 2, XP055635507
MASAMLTSU TSUCHIYA ET AL.: "Hybrid Transfer Learning for Efficient Learning in Object Detection", IEICE TECHNICAL REPORT, vol. 112, no. 386, 16 January 2013 (2013-01-16), pages 1 - 2, XP055635514, DOI: 10.1109/ACPR.2013.8
See also references of EP 3617991A4
MASAMLTSU TSUCHIYA ET AL.: "Hybrid Transfer Learning for Efficient Learning in Object Detection", IEICE TECHNICAL REPORT, vol. 112, no. 386, 16 January 2013 (2013-01-16), pages 1 - 2, XP055635514, DOI: 10.1109/ACPR.2013.8
See also references of EP 3617991A4
Attorney, Agent or Firm:
HARUKA PATENT & TRADEMARK ATTORNEYS (JP)
Download PDF: