Automatic number plate recognition system using super-resolution technique

Abstract

Super resolution is a technique which is used to enhance the visual quality of a sequence of low resolution image by constructing a single high resolution image. This paper is interested in acquiring the automatic number plate recognition system from the traffic surveillance video. The proposed system detects the number plate of a vehicle from video input and then performs the super resolution technique. Applying the Optical Character Recognition Technique it acquires the text from the super resolution image of vehicle number plate by means it compares with the RTO database and then it display the details of the vehicle such as owners name, vehicle registration etc.

Survey on Automatic Number Plate Recognition System

“…If the content cannot be identified clearly by the ocr it has to go through super resolution till the content is recognized by ocr. And the text is stored in the database [11].…”

“…Where I is the input frame from which we will crop the necessary part to relate super resolution, while x1, y1, x2, and y2 shows the axis of the rectangle, and then show the image from the frame [11]. In the proposed system as we ponder on number plate detection, we extract the license plate, and store it in our database.…”

“…In our proposed system we are extracting the necessary part of an image frame which we have collected from the camera video input file [11]. Cropping can be stated as follows, A = I (x1, y1, x2, y2)…”

“…In this system the video input is acquired from the LPR camera and then we locate the number plate in the video frame, which will find out the license plate of the vehicle automatically using lpr algorithm [11].…”

“…The ocr text database has stored vehicle number plate details is compared with the RTO database if the search is found then it display the details of the owner of the vehicle [11]. …”