.png){kind=icon}
.png){kind=icon}
Return
Multiresolution deep feature learning for pointer meters reading recognition
.png){kind=icon}
PRE
AI
DOI：10.1016/j.jmapro.2024.02.010.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
With the digital transformation of the manufacturing industry, monitoring and data collection in the manufacturing process have become crucial. Pointer meter reading recognition (PMRR), as a key element in data monitoring during the manufacturing process, is essential for improving production efficiency and product quality. This paper utilizes the idea of key point detection and proposes Multiresolution Deformable Convolutional Net (MR-DcnNet) for PMRR, a multi-resolution network architecture incorporating attention mechanisms and deformable convolution concepts. Through extensive experimental evaluation, the proposed method significantly enhances the accuracy and reliability of data monitoring in existing manufacturing systems. Furthermore, it provides a rapid and cost-effective approach for the upgrade and innovation of manufacturing systems.
Keywords:
Pointer meters
Intelligent manufacturing
Reading recognition
Deep learning
Journal
IF:
6.8
Papers:
7.6K
Citations:
3.5W