Issuu on Google+

International Journal of Electronics, Communication & Instrumentation Engineering Research and Development (IJECIERD) ISSN 2249-684X Vol. 3, Issue 3, Aug 2013, 81-88 Š TJPRC Pvt. Ltd.,

IDENTIFICATION OF INDIAN VEHICLES BY THEIR NUMBER PLATES SNEHAL B. SALUNKHE Department of Electronics and Telecommunication, RIT (An Autonomous), Islampur, Maharashtra, India

ABSTRACT The Detection of Indian Vehicles by Their Number plates is the most interesting and challenging research topic from past few years.It is shown that the number plates are different shape and size and also have different color in different countries. This paper presents an approach based on simple and efficient morphological operation and sobel edge detection method. We also presents a simple approach to segmented all the letters and numbers used in the number plate using bounding box method. After segmentation of numbers & characters present on number plate we used template matching approach to recognition of numbers & characters. We concentrate on locate the number plate region properly and to segment all the number and letters to identify each number separately. The project develops by using MATLAB 7.10. The algorithm was tested with 20 images such images taken from parking lots and roadside.

KEYWORDS: Vehicle Image, Extraction of Number Plate. Morphological Operation, Edge Detection, Character Segmentation & Recognition of Number Plate

INTRODUCTION Number plates are used for identification of vehicles all over the nations. Vehicles are identified either manually or automatically. Vehicle identification is an image processing technique of identify vehicles by their number plates. Vehicle identification system are used for the purpose of effective traffic control and security applications such as access control to restricted areas and tracking of wanted vehicles. Number plate recognition (NPR) is easier method for vehicle identification. Number plate detection has been studied from many years; it is still a challenging task to detect number plates. Number plate detection investigates an input image to identify some local patches containing license plates. Since a plate can exist anywhere in an image with various sizes, it is infeasible to check every pixel to locate it. Generally, it is preferable to extract some features from images and focus only on those pixels characterized by the license plate. The identification task is challenging because of the nature of the light. LPR system for Indian license plate is difficult compared to the foreign license plate as there is no standard followed for the aspect ratio (length to width ratio) of license plate. In parking, number plates are used to calculate duration of the parking. When a vehicle enters an input gate, number plate is automatically recognized and stored in database. When a vehicle later exits the parking area through an output gate, number plate is recognized again and paired with the first-one stored in the database. The difference in time is used to calculate the parking fee [1] A novel feature-based number plate localization method which consists of many algorithms mainly focusing on the Edge Finding Method and Window Filtering method for the better development of the number plate detection system [2]. As far as extraction of the plate region is concerned, techniques based upon combinations of edge statistics and mathematical morphology [3] featured very good results. License plate location algorithm based on edge Detection, like dilation and erosion and morphology operation like


82

Snehal B. Salunkhe

dilation and erosion, Smoothing, segmentation of characters and recognition of plate characters are described in [4] [5][6][7][9] In [8] introduced detection steps are: Image acquisition by capturing an image of a vehicle from video. License plate detection extraction, by Spectral Analysis Approach and Connected Component Analysis & extract the region of license plate process use spectral analysis, Character segmentation use connected component analysis approach and SVM feature extraction techniques. The advantage of this approach is success full recognition of a moving vehicle. It is difficult to detect the boundary of the Number plate from the input car images in outdoors. Because the color of characters is different from that of the Number plate, Background, the gradients of the original image is adopted to detect candidate number plate regions.[10] P.Anishiya Prof. S. Mary Joans [12] proposed an algorithm based on a combination of morphological operation, segmentation and canny edge detector. Segmentation of the plate characters was achieved by the application of edge detectors, labeling and fill hole approach. The character recognition was accomplished with the aid of optical characters by the process of template matching.

APPLICATION 

Parking : The NPR is used to automatically enter prepaid members and calculate parking fee for non-members

Access Control : A gate automatically opens for authorized members in a secured area, thus replacing or assisting the security guard.

Tolling : The car number is used to calculate the travel fee in a toll-road or used to double check the ticket.

Border Security : The car number is registered in the entry or exits to the country and used to monitor the border crossings.

Traffic Control : The vehicles can be directed to different lanes according to their entry permits. The system reduces the traffic congestions and number of attendants.

Airport Parking : In order to reduce ticket frauds or mistakes, the NPR unit is used to capture the number plate & image of the car.

THE PROPOSED SYSTEM

Figure 1: System Block Diagram


Identification of Indian Vehicles by their Number Plates

83

Input Image This is the first phase in proposed system. This phase deals with acquiring an image by an acquisition method. In the proposed system, we used a 120x160 resolution digital camera or 3.2 megapixel cameras to acquire the input image. The input image is 120 x160 or 1200 x 1600 pixels.

Figure 2 : Sample of Vehicle Images Extraction of Number Plate Location The inputs to the system were the images of vehicles captured by a camera. RGB to gray-scale conversion is adopted, in order to facilitate the plate extraction, and increase the processing speed. Color image (RGB) acquired by a digital camera is converted to gray-scale image based on the RGB to gray-scale conversion technique. Image captured from the camera is first converted to the gray scale image using I gray=0.114*R+0.587*G+0.299*B………(1)

Figure 3: Gray Scale Image The basic step in recognition of vehicle number plate is to detect the plate size. In general number plates are rectangular in shape. Hence we have to detect the edges of the rectangular plate. Mathematical morphology will be used to detect that region. We use here Sobel operator to calculate the threshold value. Using Sobel edge detector we used to high light regions with a high edge magnitude and high edge variance are identified.

Figure 4: Binary Gradient Image with Sobel Edge Detector


84

Snehal B. Salunkhe

The binary gradient mask shows lines of high contrast in the image. These lines do not quite delineate the outline of the object of interest. Compared to the original image, you can see gaps in the lines surrounding the object in the gradient mask. These linear gaps will disappear if the Sobel image is dilated using linear structuring elements. Structuring element is represented as matrices. Structuring element is a characteristic of certain structure and features to measure the shape of an image and is used to carry out other image processing operations, which we can create with the strel function in Matlab. The binary gradient mask is dilated using the vertical structuring element followed by the horizontal structuring element.

Figure 5: Dilated Image Matlab toolbox function provide a function imfill (BW, â€&#x;holesâ€?) that fills holes in the binarized image called BW. The set of background pixels are known as hole that cannot be reached by filling the background from the edge of the image. Figure 6f shows after remove lower than 100 pixels connected components fills the holes. The dilated gradient mask shows the outline of the region quite nicely, but there are still holes in the interior of the region. To fill these holes we use the imfill function in MATLAB.

Figure 6: Binary Image with Filled Holes Remove Connected Objects on Border The region of interest has been successfully segmented, but it is not the only object that has been found. Any objects that are connected to the border of the image can be removed using the imclearborder MATLAB function. The connectivity in the function was set to 4 or 8 to remove diagonal connections. We fill the hole to locate the plate region. Now omitting the lower pixel components to gets the actual plate. Connecting edges will be removes in figure


Identification of Indian Vehicles by their Number Plates

85

Figure 7: Removed Connected Object Image Finally, in order to make the segmented object look natural, we smoothing the object by eroding the image twice with a diamond, disk, line structuring element. We create the diamond structuring element using the strel function.

. Figure 8: Extraction of Number Plate Area Multiply the Segmented Image with gray scale image, we get the only number plate area in a vehicle image with characters and numbers present on it.

Figure 9: Number Plate of Vehicle Image Characters Segmentation Segmentation is one of the most important processes in the number plate recognition, because all further steps rely on it. If the segmentation fails, a character can be improperly divided into two pieces, or two characters can be improperly merged together. We use boundingbox to measure the properties of the image region Once a bounding box created over each character and numbers presented on number plate, separate out the each character & number for recognition of number plate & result shown in figure 10


86

Snehal B. Salunkhe

Figure 10: Number Plate with Bounding Box Image

Figure 11: Image of Each Character Character Recognition & Display the Result It is employed for the purpose of conversion of images of text into characters. Number plate recognition is now used to compare the each individual character against the complete alphanumeric database using template matching. The matching process moves the template image to all possible positions in a larger source image and computes a numerical index that indicates how well the template matches the image in that position. Matching is done on a pixel by pixel basis. The template is of size 42 Ă— 24 as shown in Figure 12. Since the template size is fixed, it leads to accurate recognition.

Figure 12: Templates used for Template Matching Finally when whole number is recognized, then output of text file is created & the information saved in the following format.

Figure 13: Image of Result

Figure 14: Image of Result Stored at Text File


Identification of Indian Vehicles by their Number Plates

87

CONCLUSIONS In this system , we presented application software designed for the identification of illegally parked vehicles at no parking area using their number plate. Firstly we extracted the plate location, then we separated the plate characters individually by segmentation and finally applied template matching with the use of correlation for recognition of plate characters. This system can be redesigned for the vehicle images captured from different angles & distances in future studies. Some of Possible Difficulties 

Broken number plate.

Blurry images.

Number plate not within the legal specification.

Low resolution of the characters.

Poor maintenance of the vehicle plate. Similarity between certain characters, namely, O and D; 5 and S; 8 and B, E; O and 0………

REFERENCES 1.

Ondrej martinsky,2007.“ Algorithmic and mathematical principles of automatic number plate recognition systems”, B.Sc. Thesis, BRNO university of technology

2.

S.Kranthi, K.Pranathi, A.Srisaila Information Technology,et al, July 2011“Automatic Number Plate Recognition”, International Journal of Advancements in Technology, ISSN 0976-4860, Vol 2, No 3

3.

Serkan Ozbay, and Ergun Ercelebi, november 2005,” Automatic Vehicle Identification by Plate Recognition”, Processing of world academy of science engineering and technology vol.9, ISSN 1307-6884.

4.

Humayun Karim Sulehria, Ye Zhang, Danish Irfan, Atif Karim Sulehria, June 2008 “ Vehicle Number Plate Recognition Using Mathematical Morphology and Neural Networks”, WSEAS TRANSACTIONS on COMPUTERS, Volume 7,ISSN: 1109-2750, Issue 6.

5.

Dr. P.K.Suri, Dr. Ekta Walia, Er. Amit Verma, December 2010. “Vehicle Number Plate Detection using Sobel Edge Detection Technique”, International Journal of Computer Science and Technology, ISSN : 2229 – 4333, IJCST Vol. 1, Issue 2.

6.

Kumar Parasuraman and P.Vasantha Kumar, ,2010 “ An Efficient Method for Indian Vehicle License Plate Extraction and Character Segmentation”, IEEE International Conference on Computational Intelligence and Computing Research.

7.

Lekhana G.C, R.Srikantaswamy , July 2012,“Real time license plate recognition system”, International Journal of Advanced Technology & Engineering Research (IJATER), National Conference on Emerging Trends in Technology (NCET-Tech) ISSN, Volume 2, Issue 4, ISSN No: 2250-3536.

8.

R.Radha1 and C.P.Sumathi2, August 2012 “A Novel approach to extract text from license plate of vehicle”, Signal & Image Processing : An International Journal (SIPIJ) Vol.3, No.4.


88

Snehal B. Salunkhe

9.

Shen Zheng Wang & His-Jian Lee “Detection and Recognition of License Plate Characters with Different Appearances”, IEEE Intelligent Transportation Systems, Proceedings. 2003 , vol.2 , Page(s): 979 - 984

10. Shishir kumar, Shashank Agarwal & Kumar Saurabh, July- December 2008, “ License plate recognition system for Indian vehicles”, International journal for information technology & knowledge management, volume 1, No.2,pp. 311-325,. 11. P.Anishiya, Prof. S. Mary Joans, 2011 , Number Plate Recognition for Indian Cars Using Morphological Dilation and Erosion with the Aid Of OCRs, International Conference on Information and Network Technology IPCSIT, Singapore. vol.4. 12. R. C. Gonzalez and R. E. Woods, Digital Image Processing, 2 nd edition , Pearson Education Asia, 2002. 13. http://www.delhitrafficpolice.nic.in/number-plate-style.htm


10 identification of indian vehicles full