An Intelligent Methods for Pointer Instrument Reading Based on Machine Vision

DOI

10.2991/msota-16.2016.86How to use a DOI?

Keywords

pointer instrument reading; machine vision; unsupervised learning

Abstract

This paper puts forward to a novel intelligent methods for pointer instrument reading to replace human reading. The images of pointer instrument are captured. Firstly a segmentation algorithm based on unsupervised learning is presented to segment the image for locating the scales and pointer. This algorithm combines the fuzzy C-means method with fuzzy support vector machines, and can subdivide the image into the objects and background efficiently. Secondly the according to the characteristic of pointer instrument, the central of instrument pointer is confirmed by Hough transform. And then the central angles of the scale regions and pointer region are calculated. At last the reading value of pointer instrument is determined. The Experiments prove the method presented by this paper is effective.

Copyright

© 2017, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Huanjun Liu
PY  - 2016/12
DA  - 2016/12
TI  - An Intelligent Methods for Pointer Instrument Reading Based on Machine Vision
BT  - Proceedings of 2016 International Conference on Modeling, Simulation and Optimization Technologies and Applications (MSOTA2016)
PB  - Atlantis Press
SP  - 393
EP  - 396
SN  - 2352-538X
UR  - https://doi.org/10.2991/msota-16.2016.86
DO  - 10.2991/msota-16.2016.86
ID  - Liu2016/12
ER  -