TY - JOUR
T1 - An Intelligent Instrument Reader
T2 - Using Computer Vision and Machine Learning to Automate Meter Reading
AU - Sowah, Robert R.
AU - Ofoli, Abdul R.
AU - Mensah-Ananoo, Eugene
AU - Mills, Godfrey A.
AU - Koumadi, Koudjo M.M.
N1 - Publisher Copyright:
© 1975-2012 IEEE.
PY - 2021/7/1
Y1 - 2021/7/1
N2 - A novel algorithm using computer vision and machine learning techniques has been developed in this research and applied to automate the reading of analog meters. This approach does not rely on any prior information about the meter being read or any human intervention during the process. High-level features of the meter, including the graduation values and angles, are extracted using a cascade of image contour filters with a series of digit classifiers. The features are refined and used to train regression models that return the reading of the analog meter automatically.
AB - A novel algorithm using computer vision and machine learning techniques has been developed in this research and applied to automate the reading of analog meters. This approach does not rely on any prior information about the meter being read or any human intervention during the process. High-level features of the meter, including the graduation values and angles, are extracted using a cascade of image contour filters with a series of digit classifiers. The features are refined and used to train regression models that return the reading of the analog meter automatically.
UR - http://www.scopus.com/inward/record.url?scp=85104652680&partnerID=8YFLogxK
U2 - 10.1109/MIAS.2021.3063082
DO - 10.1109/MIAS.2021.3063082
M3 - Article
AN - SCOPUS:85104652680
SN - 1077-2618
VL - 27
SP - 45
EP - 56
JO - IEEE Industry Applications Magazine
JF - IEEE Industry Applications Magazine
IS - 4
M1 - 9405071
ER -