Title :
Research on the Pre-processing Method of Automatic Reading Water Meter System
Author :
Zhang, Zhijia ; Li, Yuan
Author_Institution :
Comput. Vision Group, Shenyang Univ. of Technol., Shenyang, China
Abstract :
Automatic reading system for water meter has been widely used in water supply industries and the method of print wheel region and pointers location is the key technology to automatic reading for water meter. Currently, main problems that affect print wheel region and pointers location of water meter are the complicated background of dial images, interfering information similar to pointers and the tilting situation with arbitrary angles. Aiming at above problems, a new algorithm of print wheel region and pointers location based on Fourier transform is raised in this essay. Firstly, edge detection and mathematical morphology processing are used to filter effective region. Then, it takes advantage of fast Fourier transform to detect tilting angle of dial image and corrects the tilting dial image. Finally, accurately extract the region of print wheel according to horizontal and vertical integral projection operator, and extract the pointers according to the distribution and circularity of pointers. The algorithm can locate the print wheel region and pointers accurately with little computation. It shortens automatic reading system´s running time effectively and has great significance to the real-time automatic reading system.
Keywords :
edge detection; fast Fourier transforms; mathematical morphology; water meters; water supply; automatic reading water meter system; dial images; edge detection; fast Fourier transform; mathematical morphology processing; preprocessing method; print wheel region; water supply industries; Automatic meter reading; Computer industry; Computer vision; Fourier transforms; Image edge detection; Image enhancement; Information filtering; Information filters; Morphology; Wheels;
Conference_Titel :
Artificial Intelligence and Computational Intelligence, 2009. AICI '09. International Conference on
Conference_Location :
Shanghai
Print_ISBN :
978-1-4244-3835-8
Electronic_ISBN :
978-0-7695-3816-7
DOI :
10.1109/AICI.2009.154