Open AccessDamaged Number Plate Recognition
Author(s) -
P. Ezhilarasi,
S. Rajesh Kannan,
A. K. P. Kovendan,
T. Sasilatha,
K. Kayalvizhi
Publication year - 2019
Publication title -
international journal of engineering and advanced technology
Language(s) - English
Resource type - Journals
ISSN - 2249-8958
DOI - 10.35940/ijeat.a1018.1291s219
Subject(s) - matlab , artificial intelligence , computer vision , computer science , segmentation , python (programming language) , process (computing) , image processing , image (mathematics) , operating system
Around the world every vehicle are identified by its number plate. Number plate detection is one of the existing automated video surveillance systems that are used to detect the number plate. This system fails if the number plates are damaged, no proper illumination, blurry images. Thus here we will be able to recognizeze such damaged number plate. The technique involves four main stages viz. pre-processing, localization, recognition and segmentation. The entire process includes capturing the image, erasing the background details and removing the noise, cropping the number plate and then recognizing the characters followed by segmenting in order to recognize the plate. All this is done in Python because it had better results compared to MATLAB. When done in MATLAB, additional error and noise gets added to the input image and can causes inclusion of a new characters in the number plate and leads to misinterpretation of the number plate. About 100 images were gathered and 98 images of them were detected correctly. The efficiency in recognizing the damaged number plate using our system is about 98%.