Automatic vehicle number plate detection & recognition

Page 1

Automatic Vehicle Number Plate Detection & Recognition RAHMAN, MD. ARAFAT • HASAN, MD. MAHMUDUL, HOSSAIN, AL AMIN Abstract— Automatic vehicle recognition system is playing a big role in the modern world. Its use in safety issues, traffic rules and criminal activity resist is remarkable. ANPR based on MATLAB image processing is the mostly used system rather that other systems. But there are many disadvantages & limitations of this system that may cause serious problems. Such as identity duplicate by using number plate cloning is very easy in this system. There are many more disadvantages that must be take into consideration that the system is not good enough for us. On the other hand, RFID based vehicle number plate recognition system is very effective and advanced technology that can be used instead of the ANPR based on MATLAB image processing system. Index Terms— ANPR, RFID, MATLAB, Image Processing, Server.

I. INTRODUCTION (HEADING 1) Now a days automation in every sector of modern life is very important and helpful for all of us. Automation in vehicle number plate recognition is used in most of the counties for many years. The mostly used technology is ANPR using image processing system. For this system an image capturing device is mandatory to capture or video capture the number plate portion of the vehicle. Other than this technology, another modern technology is introduced now a days. It’s vehicle number plate detection & recognition using RFID. This system is very reliable for detecting the vehicle number plate. II. AUTOMATIC VEHICLE NUMBER PLATE RECOGNITION Automatic number plate recognition (ANPR) is a technology that uses optical character recognition on images to read vehicle registration plates. It can use existing closedcircuit television, road-rule enforcement cameras, or cameras specifically designed for the task. ANPR is used by police forces around the world for law enforcement purposes. It is also used for electronic toll collection on pay-per-use roads and as a method of cataloging the movements of traffic for example by highways agencies. Automatic number plate recognition can be used to store the images captured by the cameras as well as the text from the license plate, with some configurable to store a photograph of the driver. Systems commonly use infrared lighting to allow the camera to take the picture at any time of the day. ANPR technology tends to be region-specific, owing to plate variation from place to place. [1] The first step in a process of automatic plate recognition is a detection of a number plate area. This problematic procedure includes algorithms that are capable to detect a rectangular area of the number plate in an original image. The detection of a number plate area includes of a series of convolve operations. In detection and recognition method four main steps are there. [3] • Preprocessing • Localization • Segmentation • Recognition

A. Vehicle Image Captured by Camera: The image of the vehicle whose number plate is to be identified is captured using digital camera of 3.2 megapixel. B. Extraction of Number Plate Location: In this step the number plate is extracted by firstly converting RGB Image i.e., the captured image to Gray Scale Image. Here mathematical morphology is used to detect the region and Sobel operator are used to calculate the threshold value. After this we get a dilated image. Then imfill function is used to fill the holes so that we get a clear binary image. C. Segmentation and Recognition of Plate Character: Here bounding box technique is used for segmentation. The bounding box is used to measure the properties of the image region. The basic step in recognition of vehicle number plate is to detect the plate size. Here the segmented image is multiplied with gray scale image so that we only get the number plate of the vehicle. D. Display Vehicle Number: After undergoing the above steps the number plate is displayed in MATLAB window. III. VEHICLE RECOGNITION USING RFID Vehicle number plate detection & recognition using RFID system is very reliable for detecting the vehicle number plate. RFID technology can be used to track and identify vehicles across the country via storing and remotely retrieving information from small transponders, called RFID tags. These tags have an antenna built into them, which allows for the transmission and reception of radio waves from an RFID transceiver. A. RFID: RFID stands for Radio-Frequency IDentification. The acronym refers to small electronic devices that consist of a small chip and an antenna. The chip typically is capable of carrying 2,000 bytes of data or less. The RFID device serves the same purpose as a bar code or a magnetic strip on the back of a credit card or ATM card; it provides a unique identifier for that object. And, just as a bar code or magnetic strip must be scanned to get the information, the RFID device must be scanned to retrieve the identifying information. [2] A Radio-Frequency Identification (RFID) system has three parts: • A scanning antenna • A transceiver with a decoder to interpret the data • A transponder - the RFID tag - that has been programmed with information. The scanning antenna puts out radio-frequency signals in a relatively short range. The RF radiation does two things: • It provides a means of communicating with the transponder (the RFID tag) AND


• It provides the RFID tag with the energy to communicate (in the case of passive RFID tags). This is an absolutely key part of the technology; RFID tags do not need to contain batteries, and can therefore remain usable for very long periods of time (maybe decades). B. Steps of RFID Vehicle Tracking: RFID Vehicle Tracking Solutions provide accurate, scalable and extremely reliable identification to seamlessly manage and control the movement of vehicles. RFID tags are mounted on vehicles and fixed RFID infrastructure is placed at strategic locations such as entry / exit gates, weigh-bridges, parking lots and equipment [4]. This allows completely automated wireless identification of vehicles without impacting on existing vehicle processes. C. Hardware Implementation: RFID tags are mounted on vehicles and fixed RFID infrastructure is placed at strategic locations such as entry/ exit gates, weigh bridges, and refueling areas. This allows complete automated wireless identification of vehicles without impacting existing vehicle processes. The RFID hardware is protected by an appropriate compact, IP rated enclosure designed for outdoor use. The enclosure includes an RFID reader as well as power and communication hardware. Detected raw RFID data is processed and can be used to drive multiple of applications. For example, a number of components including variable message signs, boom gates, SCADA systems, weigh bridge and fuel bowsers. IV. METHODOLOGY

B. Hardware Implementation of RFID System:

Fig. 1: Car is in position to read the data from the RFID tag.

Fig. 2: Full hardware implementation of the system (Top view) V. SIMULATION RESULTS FOR ANPR USING MATLAB

A. Working Approach The objective of out project is to analysis on ANPR system based on image processing using MATLAB and RFID vehicle number plate recognition system. The goal is to mark the advantages and disadvantages or limitations of the two systems for further development. So that we can find the effective way for the vehicle number plate recognition system. Using image processing based on MATLAB is very effective process but the image must be clear and the resolution also need to be enough so that the system can properly process the image to identify the vehicle number. It’s the main problem of this system. There may be some obstacles to capture the image properly or the light may not be enough to get proper picture to process the image for processing. Heavy traffic may also can create problem to get proper image. To overcome this problems, we need to research more and find the solution. On the other hand, RFID based vehicle tracking system is out of these problems. The system has high quality RFID reader installed and the vehicles also have RFID tag placed in the body. When the vehicle passes the reader then the system automatically gets the information of the vehicles and stores it to memory. To get real time monitoring of the system the data directly sent to server. So, the whole project is done it two parts • •

Number Plate Recognition Using Image Processing RFID Vehicle Number Plate Recognition

The entire process of ANPR implementation using MATLAB is given below:

Fig. 3: Inserted Image.

Fig. 4: Gray Scale image.


Fig. 5: Binary gradient image.

Fig. 9: Number Plate with bounding box image.

Fig. 10: Cropping the selected object.

Fig. 6: Dilated image. Fig. 11: Image of result stored at text file. It displays number plate of the desired vehicle. The above Fig. 11 shows the number plate of the vehicle The above figure shows the image of each character that is and also the date on which the image of the vehicle is present in the number plate of the vehicle sequentially captured. VI. SIMULATION RESULTS FOR RFID VEHICLE NUMBER PLATE RECOGNITION Fig. 7. Binary Image with filled holes.

Fig. 8: Removed connected object image.

Fig. 12: Arduino console showing the status of data sending to server.


REFERENCES

Fig. 13: Data showing in the browser after sending to the server. VII. CONCLUSION After the simulation of ANPR using MATLAB image processing and hardware implementation of the RFID vehicle number plate recognition system we got several findings about those two systems. Image processing of course one of the mostly used vehicle recognition system but there are several findings from our simulation that there are some major limitations of this system. On the other hand, RFID vehicle number plate recognition system is totally automated and it’s a digital vehicle recognition system. Its accuracy is impressive if the total system is implemented perfectly. Although it has few limitations, from our research we found that RFID is better between these two vehicle recognition system.

[1] D.S. Kim and S.I. Chien, “Automatic car license plate extraction using modified generalized symmetry transform and image warping,”, in Proc. ISIE, pp.2022-2027, 2001. [2] [Online] Feb 11, 2016. Available: http://www.technovelgy.com/ct/technology-article.asp [3] Muhammad H Dashtban, Zahra Dashtban and Hassan Bevrani, “A Novel Approach for Vehicle License Plate Localization and Recognition,”, International Journal of Computer Applications (0975 "U 8887) Volume 26"U No.11, July 2011. [4] N. Zimic, J. Ficzko, M. Mraz and J. Virant, “The fuzzy logic approach to car number plate locating problem,”, in Proc. Intelligent Information Systems, pp. 227-230, 1997. [5] T. D. Duan, T. L. Hong Du, T. V. Phuoc and N. V. Hoang, “Building an automatic vehicle license plate recognition system,”, Iin Proc. Int. Conf. Comput.Sci. RIVF, pp. 59-63, 2005. [6] H.J. Lee, S.Y. Chen, and S.Z. Wang, “Extraction and recognition of license plates of motorcycles and vehicles on highways,”, in Proc. ICPR, pp. 356-359, 2004. [7] Paolo Magrassi (2001). "A World of Smart Objects: The Role of Auto Identification Technologies". Retrieved 2007-06-24.


Turn static files into dynamic content formats.

Create a flipbook
Issuu converts static files into: digital portfolios, online yearbooks, online catalogs, digital photo albums and more. Sign up and create your flipbook.