Corroded Bolt Identification Using Mask Region-Based Deep Learning Trained on Synthesized Data

Corroded Bolt Identification Using Mask Region-Based Deep Learning Trained on Synthesized Data

The performance of a neural network depends on the availability of datasets, and most deep learning techniques lack accuracy and generalization when they are trained using limited datasets. Using synthesized training data is one of the effective ways to overcome the above limitation. Besides, the pr...

Full description

Bibliographic Details
Main Authors: Quoc-Bao Ta, Thanh-Canh Huynh, Quang-Quang Pham, Jeong-Tae Kim
Format: Article
Language:English
Published: MDPI AG 2022-04-01
Series:Sensors
Subjects:
deep learning
vision-based approach
Mask-RCNN
bolt corrosion
image processing
bolted connection
Online Access:https://www.mdpi.com/1424-8220/22/9/3340

Internet

https://www.mdpi.com/1424-8220/22/9/3340

Similar Items