Abstract

For an intelligent transport system license plate location and vehicle license plate recognition is an important phase. The objective of this work is to design & implement a method for Number Plate Recognition (NPR) of Kannada number plates. This paper presents a method of number plate recognition, segmentation & recognition of the characters present in the Kannada number plate. The images of various vehicles have been taken manually and converted into gray-scale images. The wiener2 filter is used to remove the noise located in the number plates. The segmentation of gray-scale image generated by finding edges using sobel filter for smoothing image is used to reduce the number of connected component & then bwlabel is used to calculate the connected component & at the last single character is detected. The result shows that the proposed method have achieved accuracy of 85%.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call