DocumentCode
1840930
Title
Automatic Recognition System for Numeric Characters on Ammeter Dial Plate
Author
Li, Yibo ; Qian, Hongjuan
Author_Institution
Dept. of Auto-control, Shenyang Inst. of Aeronaut. Eng., Shenyang
fYear
2008
fDate
18-21 Nov. 2008
Firstpage
913
Lastpage
918
Abstract
The automatic recognition system for numeric character on ammeter dial plate which can be used on electronic display ammeter and mechanical ammeter is proposed in this paper. This system use binary transformation, projecting algorithm, thinning, Hough transformation, open algorithm and close algorithm as preprocessing, put forward nine segment display projection algorithm based on seven segment display to extract digital characteristics and use layered pattern base to realize numeric character recognition. Characters similar in form can be distinguished better by using nine segment display projection algorithm. The experiments show that the accurate numeric character recognition rate is up to 98% by using the system and the recognition time of 6 digits mechanical ammeter is less than 18 milliseconds. This system is a fast and high accuracy method of numeric character recognition through testing. The system also can be used to other areas such as real time vehicle plate recognition, ID card recognition and passport recognition.
Keywords
Hough transforms; ammeters; character recognition; image thinning; Hough transformation; ammeter dial plate; automatic recognition system; binary transformation; close algorithm; electronic display ammeter; mechanical ammeter; numeric character recognition; open algorithm; projecting algorithm; thinning; Ammeters; Brightness; Character recognition; Computer displays; Flowcharts; Image analysis; Image segmentation; Lenses; Partitioning algorithms; Projection algorithms; Seven segment display; digital recognition; projection;
fLanguage
English
Publisher
ieee
Conference_Titel
Young Computer Scientists, 2008. ICYCS 2008. The 9th International Conference for
Conference_Location
Hunan
Print_ISBN
978-0-7695-3398-8
Electronic_ISBN
978-0-7695-3398-8
Type
conf
DOI
10.1109/ICYCS.2008.498
Filename
4709096
Link To Document