Title :
License Plate Character Recognition Based on Gaussian-Hermite Moments
Author :
Ma, Xiaojuan ; Pan, Renlong ; Wang, Lin
Author_Institution :
Guizhou Key Lab. of Pattern Recognition & Intell. Control, Guizhou Univ. for Nat., Guiyang, China
Abstract :
Character recognition plays an important role in the automatic license plate recognition (ALPR) system. In this paper, we propose a new method to recognize the license plates characters by using 2D Gaussian-Hermite moments (GHMs) of different orders with 231 GHMs features as the input vector of BP neural network. The system worked under variable illumination, variable size of plate and dynamic backgrounds. The experimental results demonstrate robust and efficient of our method.
Keywords :
Gaussian processes; backpropagation; character recognition; computer vision; neural nets; BP neural network; Gaussian Hermite moments; license plate character recognition; Character recognition; Gaussian processes; Image recognition; Image segmentation; Intelligent transportation systems; Licenses; Neural networks; Pattern analysis; Pattern recognition; Robustness; BP neural network; Gaussian-Hermite moments (GHMs); character recognition; license plate recognition;
Conference_Titel :
Education Technology and Computer Science (ETCS), 2010 Second International Workshop on
Conference_Location :
Wuhan
Print_ISBN :
978-1-4244-6388-6
Electronic_ISBN :
978-1-4244-6389-3
DOI :
10.1109/ETCS.2010.591
