Title :
PC based number plate recognition system
Author :
Coetzee, Charl ; Botha, Charl ; Weber, David
Author_Institution :
Dept. of Electr. & Electron. Eng., Stellenbosch Univ., South Africa
Abstract :
A PC based number plate recognition system is presented. Digital gray-level images of cars are thresholded using the Niblack algorithm, which was found to outperform all binarization techniques previously used in similar systems. A simple yet highly effective rule-based algorithm detects the position and size of number plates. Characters are segmented from the thresholded plate using blob-colouring, and passed as 15×15 pixel bitmaps to a neural network based optical character recognition (OCR) system. A novel dimension reduction technique reduces the neural network inputs from 225 to 50 features. Six small networks in parallel are used, each recognising six characters. The system can recognize single and double line plates under varying lighting conditions and slight rotation. Successful recognition of complete registration plates is about 86.1%
Keywords :
image segmentation; microcomputer applications; neural nets; optical character recognition; Niblack algorithm; PC based number plate recognition system; binarization techniques; bitmaps; blob-colouring; digital gray-level images thresholding; dimension reduction technique; double line number plates; image segmentation; neural network based optical character recognition; neural network inputs; position detection; rule-based algorithm; single line number plates; size detection; slight rotation; varying lighting conditions; Air traffic control; Artificial neural networks; Character recognition; Image recognition; Image segmentation; Neural networks; Optical character recognition software; Optical computing; Optical fiber networks; Pixel;
Conference_Titel :
Industrial Electronics, 1998. Proceedings. ISIE '98. IEEE International Symposium on
Conference_Location :
Pretoria
Print_ISBN :
0-7803-4756-0
DOI :
10.1109/ISIE.1998.711680
