AUTOMATIC NUMBER PLATE DETECTION USING IMAGE PROCESSING AND PAYMENT AT TOLL PLAZA

Transcription

1 Reg. No.: DOI:V4I3P13 AUTOMATIC NUMBER PLATE DETECTION USING IMAGE PROCESSING AND PAYMENT AT TOLL PLAZA Meet Shah, Information Technology, KJSCE Mumbai, India. Akshaykumar Timbadia, Information Technology, KJSCE Mumbai, India. Prof. Sunayana Jadhav Faculty of Information Technology, KJSCE Mumbai, India. Abstract ANPR system is a system which plays important role in Automatic toll collection system at toll plaza. The model of a system performs OCR (using Contour analysis) on the video for automatic number plate recognition and uses infrared sensors, microcontroller, motor driver, motor and camera for automatic toll collection system. The information is highly required for both traffic management as well as reduction of time at toll plaza. Number plate recognition is an effective way for automatic vehicle identification. In this system, the Optical Character Recognition (OCR) technique was the prominent technique used to analyse the image of number plate of the vehicle. This project proposes a combination of image processing technique and OCR to obtain the accurate number plate recognition for vehicle in India. The outcome of this study is the system capable to detect characters and numbers of vehicle s number plate accurately. This study also involves the development of Graphical User Interface (GUI) to ease user in recognizing the characters and numbers in the vehicle plates. Keywords Vehicle plate detection system, Image processing technique, Optical Character Recognition, Contour analysis, Templet matching. I. Introduction Automatic number plate recognition system is an Image Processing technology which uses optical character recognition to identify or recognize the vehicle from their number plate or license plate. Every

2 vehicle has their own and unique number plate. There are no external cards, tags or transmitters needed. Automatic number plate recognition system is used for identifying number and obtaining owner information. The basic steps in ANPR system are, firstly, the camera captures the images of front portion of vehicle which contains number plate. From that, the number plate is extracted and this number plate consists of numbers and alphabets. And then different image processing algorithms are applied to analyse this image and extract the numbers and alphabets from that image. Now the second part is recognition, in this after getting the exact number, this number is searched in large database of registration details to obtain the owner s information. This process verifies whether users are authenticated or not. With the movement of inter-state vehicles and goods, there is rise in the number of toll roads and bridges which overall increases the loads on highways. Hence scientific tracking and monitoring system becomes a need of the toll tax department. The proper collection of toll fees can generate a huge quantum of funds for the maintenance of aging bridges and the large road network. Automatic toll collection system is fast and efficient toll collection system because vehicles do not need to stop at toll plaza to pay the toll and the payment automatically gets deducted from vehicle owner account. This removes the unnecessary traffic, saves time and can keep an eye on vehicle which is not correctly registered. There are certain factors which make the number difficult to recognize from the number plate. i. Numbers are cluttered with other objects. It is difficult to tell which pieces go together as part. ii. Parts of the number may be hidden behind other objects. iii. The intensities of the pixels are determined much by lighting as opposed to the nature of the object. For instance black pixels on bright light will give much more intense pixels than the white surface in a gloomy light. iv. An image may be captured from various viewpoints. Changes in viewpoint cause changes in images thus the same information occurs in different pixels. This problem Reg. No.: DOI:V4I3P13 Page:2

3 cannot cope up with standard machine learning approaches. captures the video of the current scenario at toll plaza. II. Methodology 2) PC performs image enhancement: A. Smoothing: Smoothing is also called as blurring, is a simple and frequently used image processing operation. It is usually done to reduce noise and camera artefacts. NOTE: Placing of hardware components may vary. Detailed Implementation Steps: Step 1: Vehicle stops near IR Step 2: As the IR logic is equal to 1, IR sends a signal to microcontroller. ARM7 microcontroller sends this information to the PC with the help of USB-TTL. Step 3: PC performs the following steps 1) Video Capturing: PC sends the command to camera to capture the video. Camera B. Conversion of colour image to grayscale: After the smoothing operation is performed on video, it is then converted into grayscale. C. Thresholding: Thresholding is the simplest method of image segmentation. It is a non-linear operation that converts a grayscale image into a binary image where the two levels are assigned to pixels that are below or above the specified threshold value. D. Erosion and Dilation: As the result of thresholding operation gives black and white image. But this image contains lots of noise in it. To reduce the noise Reg. No.: DOI:V4I3P13 Page:3

4 erosion and dilation operations are perform. 3) Perform OCR(On the Contour using Contour Analysis): The contour is a boundary of object, a population of points (pixels), and separating object from a background. In a CA, the contour is encoded by the sequence consisting of complex numbers. On a contour, the point which is called as starting point is fixed. Then, the contour is scanned (is admissible - clockwise), and each vector of offset is noted by a complex number a+ib. Where a - point offset on x axis, and b - offset on y axis. Offset is noted concerning the previous point. 4) Generate Number Plate String: This step will display all the characters and numbers on the screen. Now, then we have to rearrange all the characters and numbers in their proper order with the help of sorting algorithms. This will give us vehicle Number Plate. 5) Search in Database: Once the number plate is obtained, this number plate string is searches in the database for the verification purpose. If the number plate string is present in the database then it will indicate the vehicle is authorized otherwise not. 6) Update Database: Once it is confirmed that vehicle is authenticated then toll or money regarding that vehicle gets deducted from vehicle owner account. This will make an entry in database every time that vehicle passes from that toll plaza. Step 4: PC sends success command to Microcontroller: Step 5: Microcontroller open the Gate: After the toll deducted from vehicle owners account, that vehicle is ready to go. Microcontroller sends a command to motor driver to open the gate. Step 6: Microcontroller close the Gate: Once the vehicle passes through the gate, after few seconds microcontroller again sends command to motor driver to close the gate. So that the next vehicle stops at toll plaza to pay toll. Step 7: Repeat: Repeat the steps 1 6 for the next vehicle. Reg. No.: DOI:V4I3P13 Page:4

5 III. Results IV. Conclusion As a conclusion, a captured image of the non-moving vehicle in India was chosen as a sample to be used in pre-processing technique in order to recognize the characters of number plate of the vehicle. Four main techniques were applied in preprocessing technique. They are smoothing, conversion of colour to grayscale image, thresholding and erosion and dilation. The characters and numbers in the image of the vehicle plate are correctly identified. Besides, the GUI is successfully working and displaying necessaries information and results. For the future work, might need to improve the incapability of the system to differentiate between S and 5. The stand-alone vehicle plate recognizer will be developed as well. References [1] ASAD ALI SAFI, MUHAMMAD AZAM, SHAHBAZ KIANI, NADEEM DAUDPOTA Online Vehicles License Plate Detection and Recognition System using Image Processing Techniques, Proceedings of the 5th WSEAS International Conference on Applied Computer Science, Hangzhou, China, April 16-18, 2006 Reg. No.: DOI:V4I3P13 Page:5

6 [2] Abdul Mutholib, Teddy Surya Gunawan,Mira Kartiwi Design and Implementation of Automatic Number Plate Recognition on Android Platform.International Conference on Computer and Communication Engineering (ICCCE 2012), 3-5 July 2012 [3] Er. Kavneet Kaur,Vijay Kumar Banga NUMBER PLATE RECOGNITION USING OCR TECHNIQUE,IJRET: International Journal of Research in Engineering and Technology [4] Hanit Karwal,Akshay Girdhar Number Plate Detection System for Indian Vehicles,2015 IEEE International Conference on Computational Intelligence Communication Technology [5] Jayapriyaa. CT,Y. Bevish Jinila Short Time Automated Toll Fee Collection for Private Group Transportation,IEEE Sponsored 2J/d International Conference on Innovations in Information, Embedded and Communication systems (ICIIECS)2015 [6] Kumar Rajeev Ranjan, Abhinav Sinha Vehicle Registration System for Tollbooths International Journal of Infinite Innovations in Technology ISSN: Reg. No.: DOI:V4I3P13 Page:6