INTERNATIONAL JOURNAL OF SCIENTIFIC DEVELOPMENT AND RESEARCH International Peer Reviewed & Refereed Journals, Open Access Journal ISSN Approved Journal No: 2455-2631 | Impact factor: 8.15 | ESTD Year: 2016
open access , Peer-reviewed, and Refereed Journals, Impact factor 8.15
For Paper presents Faster R-CNN based deep learning implementation of numbering of mechanical parts such as gears. Parts are photographed in real time. In this research works the parts are sorted into three categories- the correctly numbered parts, non-numbered parts and over-ride numbered parts- through image processing followed by deep learning algorithm. For this work Mobile-Net Model on TensorFlow Machine Learning platform to accomplish part identification. Visual inspection validates the technique to 95% accuracy in real time detection.
"Part Marking Detection Using Machine Learning", International Journal of Science & Engineering Development Research (www.ijsdr.org), ISSN:2455-2631, Vol.5, Issue 10, page no.385 - 390, October-2020, Available :http://www.ijsdr.org/papers/IJSDR2010059.pdf
Downloads:
000337212
Publication Details:
Published Paper ID: IJSDR2010059
Registration ID:192661
Published In: Volume 5 Issue 10, October-2020
DOI (Digital Object Identifier):
Page No: 385 - 390
Publisher: IJSDR | www.ijsdr.org
ISSN Number: 2455-2631
Facebook Twitter Instagram LinkedIn