Open Access Open Access  Restricted Access Subscription Access
Open Access Open Access Open Access  Restricted Access Restricted Access Subscription Access

Vehicle Number Plate Detection and Character Segmentation


Affiliations
1 Department of Electronics Engineering, Vishwakarma Institute of Technology, Pune, India
2 Department of Electronics and Telecommunication, Sinhgad College of Engineering, Pune, India
     

   Subscribe/Renew Journal


In this paper, we present Automatic Number Plate detection and character segmentation for Indian Cars. Number plate design protocols are not followed in India. Characters on plate are in different Indian languages, as well as in English. We present the number plate detection and character segmentation work, with English characters. Number plate detection is quite challenging task, mainly due to diversity of plate formats, and the non-uniform illumination conditions during the image acquisition. To eliminate possible fake candidate, extracted plate regions is evaluated on the basis of geometric features of the plate: density, aspect ratio and horizontal cuts. Character segmentation is done by using connected component and vertical projection analysis. The performances on an average are: Number Plate Detection rate: 85%, Character Segmentation rate: 83%.

Keywords

Vehicle Number Plate, Number Plate Detection, Character Segmentation.
User
Subscription Login to verify subscription
Notifications
Font Size

Abstract Views: 158

PDF Views: 3




  • Vehicle Number Plate Detection and Character Segmentation

Abstract Views: 158  |  PDF Views: 3

Authors

M. M. Shidore
Department of Electronics Engineering, Vishwakarma Institute of Technology, Pune, India
S. P. Narote
Department of Electronics and Telecommunication, Sinhgad College of Engineering, Pune, India

Abstract


In this paper, we present Automatic Number Plate detection and character segmentation for Indian Cars. Number plate design protocols are not followed in India. Characters on plate are in different Indian languages, as well as in English. We present the number plate detection and character segmentation work, with English characters. Number plate detection is quite challenging task, mainly due to diversity of plate formats, and the non-uniform illumination conditions during the image acquisition. To eliminate possible fake candidate, extracted plate regions is evaluated on the basis of geometric features of the plate: density, aspect ratio and horizontal cuts. Character segmentation is done by using connected component and vertical projection analysis. The performances on an average are: Number Plate Detection rate: 85%, Character Segmentation rate: 83%.

Keywords


Vehicle Number Plate, Number Plate Detection, Character Segmentation.