Abstract

Vickers hardness is still measured by human operators for accurate measurement, because automatic measurement sometimes shows poor accuracy due to the slight difference in contrast and shape of the indentation. In this study, for more accurate Vickers hardness automatic measurement, we propose a novel technique by using convolutional neural network (CNN). We examine the usefulness of our novel technique, compared with manual measurement and image processing measurement. The hardness values measured by the CNN method suggest being close to the values measured manually, and more accurate than the image processing method.

Details

Title
Vickers hardness measurement by using convolutional neural network
Author
Tanaka, Y 1 ; Seino, Y 1 ; Hattori, K 1 

 National Metrology Institute of Japan, National Institute of Advanced Industrial Science and Technology (NMIJ-AIST), Tsukuba, Japan 
Publication year
2018
Publication date
Aug 2018
Publisher
IOP Publishing
ISSN
17426588
e-ISSN
17426596
Source type
Scholarly Journal
Language of publication
English
ProQuest document ID
2572717628
Copyright
© 2018. This work is published under http://creativecommons.org/licenses/by/3.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.