Automatic License Plate Recognition System Using GA and CCAT

(1)

76

Automatic License Plate Recognition System

Using GA and CCAT

PRASANNA VENKATESWARAN.S, GUNASEKARAN.V

Abstract -- In this paper, a design for automatic license plate number Recognition system is to be developed. A novel genetic algorithm is introduces to detect and extract the license plate . This performs two level of segmentation process. Then Connected Component Analysis technique is used to extract individual characters i.e. numbers and alphabets in the image. Then followed by template matching method with loaded database, where the database consist of 10 to 15 image samples of all possible numeric values and alphabets of different size and font. As a result of Template matching system we will get the recognized numbers from image to Text format.

Key words -- License plate Recognition system, Genetic algorithm, Connected component analysis, Template matching.

I. INTRODUCTION

The Automatic number plate recognition (ANPR) is a mass surveillance method that uses optical character recognition on images to read the license plates on vehicles. They can use existing closed-circuit television or road-rule enforcement cameras, or ones specifically designed for the task. They are used by various police forces and as a method of electronic toll collection on pay-per-use roads and monitoring traffic activity, such as red light adherence in an intersection. ANPR 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. A powerful flash is included in at least one version of the intersection monitoring cameras, serving both to illuminate the picture and to make the offender aware of his or her mistake. ANPR technology tends to be region-specific, owing to plate variation from place to place.

Manuscript received May, 2016.

Prasanna Venkateswaran.S, PG Scholar, Department of Electrical and electronics engineering Veltech multitech Dr.rangarajan Dr. Sakunthala engineering college.

Gunasekaran.V Assistant Professor,Department of Electrical and electronics engineering Veltech multitech Dr.rangarajan Dr. Sakunthala engineering college.

The objective of the paper is to successfully locate standard Egyptian number plate, segment characters and recognize them given a car image. The system must deal with different angles, distances, scales, resolutions and illumination conditions.

Most of the number plate localization algorithms merge several procedures, resulting in long computational (and accordingly considerable execution) time (this may be reduced by applying less and simpler algorithms). The results are highly dependent on the image quality, since the reliability of the procedures severely degrades in the case of complex, noisy pictures that contain a lot of details. Unfortunately the various procedures barely offer remedy for this problem, precise camera adjustment is the only solution. This means that the car must be photographed in a way that the environment is excluded as possible and the size of the number plate is as big as possible. Adjustment of the size is especially difficult in the case of fast cars, since the optimum moment of exposure can hardly be guaranteed. Number Plate Localization on the Basis of Edge Finding: The algorithms rely on the observation that number plates usually appear as high contrast areas in the image (and-white or black-and-yellow). First, the original car image in color is converted to black and white image gray-scale image. The original image is converted to gray-scale image which is in high contrast as shown above. Now, we need to identify the location of the number plate horizontally in which row it’s present. The letters and numbers are placed in the same row (i.e. at identical vertical levels) resulting in frequent changes in the horizontal intensity. This provides the reason for detecting the horizontal changes of the intensity, since the rows that contain the number plate are expected to exhibit many sharp variations.

II. PROPOSED SYSTEM

(2)

77 A. Segmentation

Here the first process is segmentation License plate from the captured vehicle image. And the segmentation of license plate has been carried out in two stages. The first level of image segmentation ensures the availability of license plate in the captured image. Initially size of captured image is calculated and the row size has been cropped to one-third of the total image depending upon the location of the license plate.

Then license plate can be a yellow board or white board so the count of yellow and white components in the segmented image is obtained. Threshold for white component has been fixed to 165 and this value has been checked on all the three planes, similarly for yellows its 65. And also with these values a vehicle can be classified as own or rental vehicle. These estimated yellow and white components are replaced with holes. And that region has been mapped to the Level-1 segmented image and cropped which gives the license plate alone.

B. Connected Component Analysis

The extracted license plate has been converted to binary image. And a structuring element has be defined and initialized with zeros. All the non-zero element position in segmented license image has been extracted. This is followed by dilation operation on the binary image and intersection is been performance to the dilated image and the input image until both becomes same. Finally all non-zero elements are been found and each element has been labelled by a name or number. This gives total number of elements in the matrix. Using the labels all the connected components have been extracted individually.

C. Recognition

Initially database has been created and this database consists of all the numeric values from 0 to 9 and alphabets from A-Z with 15 samples in each. All these samples are binarized and loaded as a database i.e. a matrix which has all the features of the samples in database.

Then all the extracted individual components from connected component analysis have been matched to the features in the database and the character of components has been analyzed. This gives the exact transformation of license plate image to text.

III. SIMULATION AND RESULTS The entire process has been designed in MATLAB 2007a with MATLAB programming language. Graphical User Interface has been created for the code.

The figure.1 shows the input image to the License plate recognition system

Figure.1.Vehicle image with license plate

(3)

78

Figure.3.Holes filled to the white or yellow component

Figure.4. segmented license plate image

Figure.5.Recognized license number

Figure.6. Final output on GUI.

Figure.7. Account details

(4)

79

V. CONCLUSION

Thus an automatic License plate recognition system has been developed. Here segmentation of license plate has been developed using a novel Genetic segmentation algorithm, which performs segmentation of license plate as two level process. Then Connected Component Analysis technique has been used to extract individual characters of the license plate image finally followed by template matching with loaded database. Finally we have Extracted license plate number in text format from the captured vehicle image.

An automated toll plaza has been developed as hardware resource for testing purpose. This application has been developed using LPC2148 processor. Along with GSM for balance sms.

VI. REFERENCES

[1]. F. PirahanSiah, S. N. H. S. Abdullah, and S. Sahran, “Adaptive image segmentation based on peak signal-to-noise ratio for a license plate recognition system,” in Proc. ICCAIE, 2010, pp. 468–472.

[2]. S. Nomura, K. Yamanaka, O. Katai, H.

Kawakami, and T. Shiose, “A novel adaptive morphological approach for degraded character image segmentation,” Pattern Recognit., vol. 38, no. 11, pp. 1961–1975, Nov. 2005.

[3]. Broumandnia and M. Fathy, “Application of pattern recognition for Farsi license plate recognition,” ICGST Int. J. Graph., Vis. Image Process., vol. 5, no. 2, pp. 25–31, Jan. 2005. [4]. M. Rasooli, T. Branch, S. Ghofrani, and E.

Fatemizadeh, “Farsi license plate detection based on element analysis and characters recognition,” Int. J. Signal Process., Image Process. Pattern Recognit., vol. 4, no. 1, pp. 65– 80, Mar. 2011. [5]. F. PirahanSiah, S. N. H. S. Abdullah, and S.

Sahran, “Adaptive image segmentation based on peak signal-to-noise ratio for a license plate recognition system,” in Proc. ICCAIE, 2010, pp. 468–472.

[6]. S. H. Kasaei, S. M. Kasaei, and S. A. Kasaei, “New morphology based method for robust Iranian car plate detection and recognition,” Int. J. Comput. Theory Eng., vol. 2, no. 2, pp. 264– 268, Apr. 2010.

[7]. F. M. Kazemi, S. Samadi, H. R. Poorreza, and M. R. Akbarzadeh-T, “Vehicle recognition based on Fourier, wavelet and curvelet transforms— A comparative study,” in Proc. ITNG, 2007, pp. 939–940.

[8]. F. M. Kazemi, S. Samadi, H. R. Poorreza, and M. R. Akbarzadeh-T, “Vehicle recognition using curvelet transform and SVM,” in Proc. ITNG, 2007, pp. 516–521.

[9]. V. Beëanoviéa, M. Kermitb, and A. J. Eidec, “Feature extraction from photographical images using a hybrid neural network,” in Proc. SPIE 9th Workshop Virtual Intell./Dyn. Neural Netw., 1999, vol. 3728, pp. 351–361.

[10]. K. Jung, “Neural network-based text location in color images,” Pattern Recognit. Lett., vol. 22, no. 14, pp. 1503–1515, Dec. 2001.

[11]. R. Brunelli, Template Matching Techniques in

Computer Vision: Theory and Practice.

Hoboken, NJ, USA: Wiley, 2009.

[12]. N. Zimic, J. Ficzko, M. Mraz, and J. Virant, “The fuzzy logic approach to the car number plate locating problem,” in Proc. IIS, 1997, pp. 227– 230.

[13]. S. M. Youssef and S. B. AbdelRahman,

“RETRACTED: A smart access control using an efficient license plate location and recognition approach,” Exp. Syst. Appl., vol. 34, no. 1, pp. 256–265, Jan. 2008.

[14]. H. Kwanicka and B. Wawrzyniak, “License plate localization and recognition in camera pictures,” in Proc. 3rd Symp. Methods Artif. Intell., 2002, pp. 243–246.

[15]. H. Bai, J. Zhu, and C. Liu, “A fast license plate extraction method on complex background,” in Proc. IEEE Intell. Transp. Syst., 2003, pp. 985– 987.

[16]. D. Zheng, Y. Zhao, and J. Wang, “An efficient method of license plate location,” Pattern Recognit. Lett., vol. 26, no. 15, pp. 2431–2438, Nov. 2005.

[17]. R. W. Rodieck, The First Steps in Seeing. Sunderland, MA, USA:

Sinauer Associates, 1998.

[18]. E. R. Lee, P. K. Kim, and H. J. Kim, “Automatic recognition of a car license plate using color image processing,” in Proc. IEEE ICIP, 1994, pp. 301–305.

[19]. C.-C. Lin and W.-H. Huang, “Locating license plate based on edge features of intensity and saturation subimages,” in Proc. 2nd ICICIC, 2007, p. 227.

(5)

80

[21]. Y. Yanamura, M. Goto, D. Nishiyama, M. Soga, H. Nakatani, and H. Saji, “Extraction and tracking of the license plate using Hough transform and voted block matching,” in Proc. IEEE Intell. Veh. Symp., 2003, pp. 243–246.