TY - GEN
T1 - License plate detection and recognition in complex scenes using mathematical morphology and support vector machines
AU - Rabee, Ayman
AU - Barhumi, Imad
PY - 2014
Y1 - 2014
N2 - In this paper we propose a highly reliable license plate detection and recognition approach using mathematical morphology and support vector machines (SVM). The approach is composed of three main stages including license plate detection, character segmentation and recognition. A preprocessing step is applied to improve the performance of license plate localization and character segmentation in case of severe imaging conditions. The first and second stages utilize edge detection, mathematical morphology followed by connected component analysis. While SVM is employed in the last stage to construct a classifier to categorize the input numbers of the license plate into one of 9 classes. The algorithm has been applied on 208 car images with different backgrounds, license plate angles, distances, lightning conditions, and colors. The average accuracy of the license plate localization is 97.60%, 90.74% for license plate identification, and 97.89% for number recognition.
AB - In this paper we propose a highly reliable license plate detection and recognition approach using mathematical morphology and support vector machines (SVM). The approach is composed of three main stages including license plate detection, character segmentation and recognition. A preprocessing step is applied to improve the performance of license plate localization and character segmentation in case of severe imaging conditions. The first and second stages utilize edge detection, mathematical morphology followed by connected component analysis. While SVM is employed in the last stage to construct a classifier to categorize the input numbers of the license plate into one of 9 classes. The algorithm has been applied on 208 car images with different backgrounds, license plate angles, distances, lightning conditions, and colors. The average accuracy of the license plate localization is 97.60%, 90.74% for license plate identification, and 97.89% for number recognition.
KW - Digital image processing
KW - License Plate Identification
KW - Support vector machines
UR - http://www.scopus.com/inward/record.url?scp=84903978062&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84903978062&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:84903978062
SN - 9789531841917
T3 - International Conference on Systems, Signals, and Image Processing
SP - 59
EP - 62
BT - Proceedings - 21st International Conference on Systems, Signals and Image Processing, IWSSIP 2014
PB - IEEE Computer Society
T2 - 21st International Conference on Systems, Signals and Image Processing, IWSSIP 2014
Y2 - 12 May 2014 through 15 May 2014
ER -