A Review: Recognition of Automatic License Plate in ?· A Review: Recognition of Automatic License ...…

Download A Review: Recognition of Automatic License Plate in ?· A Review: Recognition of Automatic License ...…

Post on 02-Jul-2018




0 download

Embed Size (px)


<ul><li><p>International Journal of All Research Education and Scientific Methods (IJARESM) </p><p>ISSN: 2455-6211, Volume 4, Issue 6, June- 2016 </p><p> 92 </p><p>A Review: Recognition of Automatic License </p><p>Plate in Image Processing </p><p>Babita1, Ms. Meenu</p><p>2 </p><p>1M.Tech Student, CSE Deptt, VCE Rohtak </p><p> 2Assistant Professor, CSE Deptt, VCE Rohtak </p><p>ABSTRACT </p><p> In this paper a detailed study on Automated License plate recognition is given. In this paper we are proposing a </p><p>method for implementing Automatic License Plate Recognition using Speed up robust feature matching SURF </p><p>technique for plate detection and Advanced Radial basis function for matching characters. Automatic License Plate </p><p>Recognition algorithms generally consist of following steps for effective processing: - 1) Identification and detection of </p><p>the license plate area; 2) Segmentation of the plate characters; and 3) Optical Character Reader. Image processing </p><p>techniques such as filtering, edge detection, Thresholding etc are normally used to perform the first two steps of the </p><p>ALPR process. This proposed work has been implemented by image processing Toolbox under the MATLAB </p><p>software. </p><p>Keywords: SURF, RBF, Neural Network, OCR, MATLAB, Segmentation, Radial Basis Function and Ransac. </p><p>1. INTRODUCTION </p><p>Computer vision techniques have led to new innovation in the automation in license plate localization. Number </p><p>plate localization has been a major and vital part of the license plate recognition system .This technique can </p><p>solve various traffic management problems such as Highway toll collection, Parking management, vehicle Theft </p><p>detection etc [3]. </p><p>2. LITERATURE REVIEW </p><p>Character Recognition is a technique which is most widely used for authentication of person as well as </p><p>document. Character Recognition is performed On-line as well as Off-line. Optical Character Recognition is </p><p>performed Off-line after the writing has been completed [2]. In Off-line, each character is differentiating by </p><p>analysis of character shape and comparing the features . [5]. Whereas, In On-line Recognition, computer </p><p>recognizes the character as they are drawn [2]. </p><p>In Character Recognition System, firstly a database is prepared which consists of printed English alphabet. Then, </p><p>the characters are scanned and pre-processing technique is used for the detection and removal of noise and </p><p>improve the quality of images. Various methods used in character recognition are Image Pre-processing, </p><p>Segmentation, Feature Extraction, Classification and Recognition and Pattern Matching [1,3]. Techniques used </p><p>in this are Neural Network Algorithm, Image processing Toolbox created in MATLAB software, SURF Feature, </p><p>Ransac Algorithm and Radial Basis Function [4,6]. </p><p>3. PROPOSED METHOD </p><p> A. Optical Character Recognition </p><p>Optical Character Recognition (OCR) using Neural Netwok is basically used in the field of research. Character recognition technique is mainly used for tolerate the defects in license plate such as license plate may be tilted or </p><p>bent with respect to position of camera. The proposed method consists of basically topological sorting method </p><p>which includes the number of end points, number of holes. This approach provides the feature in character </p><p>recognition with quality despite of quantitative nature. Steps of Optical Character Recognition are shown in fig </p><p>1. </p><p> B. Steps of Optical Character Recognition </p></li><li><p>International Journal of All Research Education and Scientific Methods (IJARESM) </p><p>ISSN: 2455-6211, Volume 4, Issue 6, June- 2016 </p><p> 93 </p><p>Fig 1: Steps of Optical Character Recognition [4] </p><p> 1. Image Acquisition </p><p>In Image Acquisition, this approach acquires an input in the form of scanned image and also provides the </p><p>location from where it is acquired. All the scanned images which we are using must be in a specific format such </p><p>as JPEG, JPG etc. These images can be input to the system through any type of suitable input device such as scanner, digital camera or any analog or digital input device. Image Acquisition process is shown in fig.2 [4]. </p><p>Fig 2: Sample Dataset [2] </p><p>2. Pre-Processing </p><p>The pre-processing consist a series of steps which are performed on the raw data to prepare it for another </p><p>processing . It basically consists of three tasks labelling of connected components, thresholding and removal of </p><p>noise which are performed in a sequential manner. The labelling of components selects the useful data from a </p><p>large collection of data Normally, in this approach, transformation is used to manipulate raw data to produce a </p><p>single input and normalization is used to manage the data in a more suitable way so that ease to access. The </p><p>process of Pre-processing is shown in fig 3. [1] </p><p>Fig 3: Gray-Scale Image [1] </p><p>i) RGB to Gray Conversion: First of all the coloured image is converted into a gray colour format and the </p><p>scanned image is stored in a JPEG format but we can also use the other formats of images like BMP, JPG etc for character recognition. There is a specified format for these image called RGB format. A converted gray scale </p><p>image compromises of number of pixels which are expressed within a minimum and maximum value and lies </p><p>between a range of 0 to 255 where 0 shows the total absence i.e. black and 1 shows the total presence i.e. white. </p></li><li><p>International Journal of All Research Education and Scientific Methods (IJARESM) </p><p>ISSN: 2455-6211, Volume 4, Issue 6, June- 2016 </p><p> 94 </p><p>In this process each pixel contains a single set called black and white and composed of shades of gray where </p><p>black at the weakest intensity and white at the strongest. [5]. </p><p>ii) Thresholding Approach or Binarization: Thresholding is a process in which a image consisting of Gray </p><p>Scale is converted into a image of 0 and 1 i.e. machine readable form Image using a technique named as </p><p>Thresholding. This approach also stores an image in the form of row and column known as matrix form , but in this a point consisting of pixels can only be coloured as either Black or White. It assigns value True i.e. 1 for </p><p>white and False i.e. 0 for Black. </p><p>iii) Noise Reduction: connected line segments can be affected by Noise results to disconnection of line </p><p>segments, bumps, and also creates gaps in lines and filled loops which are created by either scanning device or </p><p>any other suitable writing approach. A process, named as Median filter is used for reducing the noise. By using </p><p>Filter process of Median , the value of a point consisting of pixels is replaces by the median of gray levels near </p><p>of that pixel [1]. </p><p>iv) Thinning: This approach is morphological operation process. It is used in binary image to remove the </p><p>foreground pixels from the scanned images. This process takes the archaeological image as an input and after </p><p>performing the thinning process it provides an thinned image of one pixel width characters. This approach can be done by using two types of algorithms: Sequential and parallel Thinning algorithms. </p><p> [2]. </p><p>v) Edge Detection Approach and Erosion: Edge detection process is used to find the boundaries of objects </p><p>within images. To produce the pre-processed image for segmentation, these operations are performed in the last </p><p>two stages. Edge detection consists of mainly three steps:- </p><p>a. Smoothing </p><p>b. Edge enhancement </p><p>c. Edge localization </p><p>3. Detection/Localisation </p><p>i) SURF: For Licence Plate Localization, a method is used named as SURF feature extraction. SURF method </p><p>which is used for feature detection and extraction is based on Hessian Matrix. SURF method is basically </p><p>dependent on the determinant of Hessian Matrix. For Hessian Matrix, we use a continuous function of two </p><p>variables with the value of the function at (x; y) is given by f(x; y). Hessian matrix, H, is denoted as the matrix </p><p>of partial derivates of the function f . SURF Feature Extraction method is shown in fig 4. [3]. </p><p>Fig 4: Matched features [3] </p><p>ii) Ransac: Ransac stands for Random Sample Consensus. Ransac algorithm is used for finding outlier </p><p>detection after finding the interest point for accurate detection. For finding outliers we provided parameters of </p><p>inliers and outliers based on which we removed the regions that were wrongly classified as plate region. </p><p>The RANSAC algorithm is consists of basically two steps which are performed in repeated manner, </p><p>Hypothesize and Test framework [3]. </p><p>(a) Hypothesize: From set of input datasets minimal sample sets (MSSs) are selected firstly. It is a formal </p><p>statement of relationship between two or more variables. The instances are considered using only minimal </p><p>sample sets (MSSs) which consist of a number of elements It provides the facility of data collection, data </p><p>analysis and data interpretation.[3]. </p></li><li><p>International Journal of All Research Education and Scientific Methods (IJARESM) </p><p>ISSN: 2455-6211, Volume 4, Issue 6, June- 2016 </p><p> 95 </p><p>(b) Testing of Framework: In the first step, by using the model parameters, RANSAC approach is used to </p><p>check the elements in dataset for removal of inconsistency. The collection of these elements is known as </p><p>Consensus set (CS). RANSAC approach will quit only when the probability of finding a batter ranked ConS </p><p>will be less than a specific value. The number plate with inliers features is shown in fig 5 [3] </p><p>Fig 5: Located number plate with inliers features [3] </p><p>4. Segmentation </p><p>Segmentation is a process in which we segments the latters in different parts and stores them at some folder. </p><p>Morphological operations are used for segmentation. In this dilation, close, open operations are used to find the </p><p>connected components lower than a certain threshold value and extracted all the components as characters. </p><p>These characters are later fed into recognition module of ANN [7]. </p><p>Some of the segmentation results are shown in fig: 6. </p><p>Fig 6: Segmented letters in GUI [7] </p><p>5. Pattern Matching </p><p> Pattern Matching comes when the segmentation process is complete and each character has been individually </p><p>extracted. In Pattern Matching, we created a database of 26 alphabets and numbers of size 24x42 pixels using </p><p>Adobe Photoshop CS3. This database contains multiple samples of one character for Neural Network training </p><p>purpose. Using Pattern Matching step, the speed and accuracy of overall recognition process is increased. For </p><p>Pattern Matching, RBF network is used. RBF network is a Radial Basis Feed Forward Propagation Neural </p></li><li><p>International Journal of All Research Education and Scientific Methods (IJARESM) </p><p>ISSN: 2455-6211, Volume 4, Issue 6, June- 2016 </p><p> 96 </p><p>Network which consist of basically three layers: Input, Hidden and Output. Basic structure of RBF is shown in </p><p>fig7 [2]. </p><p>Fig 7: RBF basic structure [2] </p><p>In this figure there are a number of inputs from p1,p2 to pr and input to the radial basis transfer function(radbas) </p><p>is a vector which is used to show the distance between weight vector w and the input vector p, multiplied by the </p><p>bias b. (The || dist || box in the above fig. The radial bias function accepts p as the input vector and the single </p><p>row input weight matrix, and produces the output as a dot product of the two.) In RBF network, we use the input </p><p>layer for providing the signal and then all the weights are connected to hidden layer which have assigned a value </p><p>one and radial basis function is used as an activation function [2]. </p><p>4. TECHNIQUES USED </p><p>NEURAL NETWORK: A Neural Network can be thought as a collection of number of nodes which are </p><p>interconnected to each other which provides an adaptive neural processor. Firstly, the basic reason behind its </p><p>higher speed is that it works on the procedure of parallelism; it can perform the calculation at a higher rate as </p><p>compared to the classical techniques. Because a neural network provides a dynamic environment, so it provides </p><p>ease to changes in data and learn the features of input signal which are provided by input layer. In this network </p><p>output from one node is fed to another node and the final output resides on the complex co-operations of all </p><p>nodes. In this architecture output of one node fed in to input of other nodes and follows in a sequential manner. </p><p>The structure of Neural Network is shown in fig 8. [2] </p><p>Fig 8: Neural Network [2] </p><p>Characteristics of Neural Network </p><p>a. Training and Learning </p><p>b. Fault Tolerant </p></li><li><p>International Journal of All Research Education and Scientific Methods (IJARESM) </p><p>ISSN: 2455-6211, Volume 4, Issue 6, June- 2016 </p><p> 97 </p><p>c. Evidential Response </p><p>d. Adaptively </p><p>e. Activation Function </p><p>f. Generalization </p><p>g. Noise Immunity </p><p>CONCLUSION </p><p>The main aim of this paper is to simulate and examine the results of Automatic License Plate Recognition using </p><p>Speed Up Robust Feature (SURF) Method for detection of License Plate Region. In this we have also used </p><p>Radial Basis Function (RBF) for character recognition which is successful in recognizing characters segmented </p><p>with Blurry and Noisy background. All the experiments and simulations have been performed with MATLAB </p><p>2011. </p><p>REFRENCES </p><p> [1]. Shradha Chadokar and Jijo S Nair. A Survey on Offline Prompt Signature Recognition and Verification. </p><p>International Journal of Advanced Research in Computer Science and Software Engineering, Vol. 4, pp. 1432-1438 (2014). </p><p>[2]. Reetika Verma and Mrs. Rupinder kaur. Enhanced Character Recognition Using SURF Features and Neural Network Techniques. </p><p>[3]. International Journal of Computer Science and Information Technologies. Vol. 5, pp. 5565-5570(2014). [4]. Abhay Chaturvedi and Nidhi Sethi. Automatic Licence Plate Recognition System SURF Features and RBF </p><p>Neural Network. International Journal of Computer Application, Vol. 70, pp. 37-41 (2013). </p><p>[5]. Kauleshwar Prasad, devvrat C. Nigam, Ashmika Lakhotiya and Dheeren Umre. Character Recognition Using Matlabs Neural Network Toolbox .International Journal of U- and e- service, Science and Technology. Vol. 6, pp. 13-20(2013). </p><p>[6]. Md. Alamgir Badsha, Md. Akkas Ali, Dr. Kaushik Deb and Md. Nuruzzaman Bhuiyan. Handwritten Bangla Character Recognition Using Neural Network. International Journal of Advanced Research in Computer Science and Software Engineering. Vol. 2, pp. 307-312(2012). </p><p>[7]. Pal S, Chanda S, Pal U, Franke K and Blumenstein M. Off-line Signature Verification Using G-SURF. Intelligent System Design and Applications, Vol. 2, pp. 586-591(2012). </p><p>[8]. Gaganjot Kaur, Monika Agarwal. Artificial Intelligent System for Character Recognition Using Levenberg-Marquardt Algorithm. International Journal of Advanced Research in Computer Science and Software Engineering, Vol. 2, Issue 5, pp. 220-223(2012). </p><p>[9]. Amit Choudhary and Rahul Rishi. Improving the Character Recognition Efficiency of Feed Forward Neural Network. International General of Computer Science and Information Technology, Vol. 1, pp. 85-96(2011). </p><p>[10]. Patel C.I., Patel R. and Patel P. Handwritten Character Recognition Using Neural Network. International Journal of Computer Science and Engineering Research, Vol. 2, pp. 1-6(2011). </p><p>[11]. Anita Pal and Daya...</p></li></ul>


View more >