Title:
タイヤ画像の認識方法及びタイヤ画像の認識装置
Document Type and Number:
Japanese Patent JP7132701
Kind Code:
B2
Abstract:
A method which includes obtaining a plurality of images of tires that differ from one another in either one of or both of a tire type and a tire condition, the obtained images being regarded as teacher images; converting the teacher images into a size of a predetermined number of pixels; learning by a convolutional neural network using data of the plurality of converted teacher images as learning images, and setting parameters of the convolutional neural network; obtaining a tire image of a recognition-target tire and converting the obtained tire image into a size identical to that of the teacher images; and inputting the converted tire image of the recognition-target tire to the convolutional neural network and determining either one of or both of the type and the condition of the recognition-target tire.
Inventors:
Masayuki Nishii
Yasuo Osawa
Tadatsu Wakao
Yasuo Osawa
Tadatsu Wakao
Application Number:
JP2017156115A
Publication Date:
September 07, 2022
Filing Date:
August 10, 2017
Export Citation:
Assignee:
Bridgestone Corporation
International Classes:
G01M17/02; B60C11/03; B60C11/24; B60C13/00; G06T7/00
Domestic Patent References:
| JP10255048A | ||||
| JP2015148979A |
Other References:
Lei Zhang, Fan Yang, Yimin Daniel Zhang, and Ying Julie Zhu,ROAD CRACKDETECTION USING DEEP CONVOLUTIONAL NEURAL NETWORK,2016 IEEE InternationalConference on Image Processing (ICIP),IEEE,2016年 9月25日,pp.3708-3712,DOI:10.1109/ICIP.2016.533052
Attorney, Agent or Firm:
Yasuo Miyazono