Title :
Meter character recognition method based on gray template matching
Author :
Zhang Zhi-Jia ; Li Yuan ; Yuan Wei-qi
Author_Institution :
Shenyang Univ. of Technol., Shenyang, China
Abstract :
Aiming to the problem that spots on meter dial and recurring semi-characters seriously affect character recognition accuracy in the process of automatic meter reading. A template matching algorithm based on gray-scale image is raised for recognizing meter readings. The algorithm firstly locate print wheel region in the print wheel region image on dial after coarse positioning, then match the gray-scale character image with template image one by one. Experiment verify that the algorithm better to overcome the impact of spot caused by meter surface reflection, and both of the whole character and semi-character have a higher recognition rate.
Keywords :
automatic meter reading; image matching; optical character recognition; automatic meter reading; gray template matching algorithm; gray-scale character image recognition; meter character recognition method; meter surface reflection; print wheel region image; Automatic meter reading; Character recognition; Gray-scale; Manganese; Reflection; Wheels; Automatic Meter Reading; Character Recognition; Faculae; Template Matching;
Conference_Titel :
Control Conference (CCC), 2010 29th Chinese
Conference_Location :
Beijing
Print_ISBN :
978-1-4244-6263-6