A Novel Method for Indian Vehicle Registration Number Plate Detection and Recognition using Image Processing Techniques

摘要

Number Plate recognition, also called License Plate realization or recognition using image processing methods is a potential research area in smart cities and Internet of Things. Many of the existing automated number plate recognition systems work only in a controlled environment where images are captured from a straight angle with good illumination, clarity and standard fonts. Another drawback of existing works is that, they are based on UK number plates and may not suite for Indian number plates. This paper presents a novel image processing system for Indian number plate detection and recognition that can deal with, noisy, low illuminated, cross angled, non-standard font number plates. This work employs several image processing techniques such as, morphological transformation, Gaussian smoothing, and Gaussian thresholding in the pre-processing stage. Next, for number plate segmentation, contours are applied by border following and contours are filtered based on character dimensions and spatial localization. Finally, after the region of interest filtering and de-skewing, K-nearest neighbor algorithm is used for character recognition. The proposed methods demonstrated promising results.