This paper will discuss an automatic recognition system to facilitate the activities of reading and recording of the electricity kWh meter. The system will analyze a captured image of the electricity kWh meter display using character recognition method. Prior to applying this method, each photo image of the kWh meter display will be pre-processed (i.e. converting the image to grayscale and determining the threshold). To detect the kWh meter display area, a smearing approach will be applied which connected the component labeling to character segmentation. To recognize each number, a template matching will be used. This study show that these steps were not yields good result in recognizing the characters in the electricity kWh meter. This is due to several factors, such as the persistence of noise that interfered with the character recognition, camera angles, lighting effect and the effect of the smearing limit.
Copyrights © 2015