IJSRD - International Journal for Scientific Research & Development| Vol. 2, Issue 09, 2014 | ISSN (online): 2321-0613 All rights reserved by www.ijsrd.com 700 Automatic Number Plate Recognition for Video Surveillance System (ANPR): A Survey Trupti Gondaliya 1 Prof. Piyush Gohel 2 1 Student 2 Assistant Professor 1,2 Department of Computer Engineering 1,2 Noble Group Of institutions Junagadh, India Abstract— The aim of the research work described in this paper is to develop a system for automatic car detection of vehicles and character recognition number plate. The image processing has been used for smart traffic surveillance system .Overall work for system comprises of software development and hardware development. Approach uses a single camera system mounted on a pole or traffic light which detects the over speeding vehicle and extracts its number plate. The system works by capturing the video frame of the moving object and by using image processing obtain its differencing image. First of all the moving object detection is done after that we will consider that object for number plate recognition. After object tracking we get the image of the car with number plate. Recognition of the number plate is proposed using different algorithms. Key words: Automatic Number Plate Recognition (ANPR), GMM (Gaussian mixture model), optical flow, boundary and character feature optical character recognition I. INTRODUCTION Automatic License plate recognition is the extraction of vehicle license plate information from an image. It plays an important role in numerous real-life applications such as traffic video surveillance system, parking fee payment, parking access control and recovering of stolen cars. ALPR is also known as automatic vehicle identification, car plate recognition, automatic number plate recognition and optical character recognition. Now a day’s video surveillance system has been developing rapidly. It detects the target in initial stage and then performs the function. The escalating increase of contemporary urban and national road networks over the last three decades emerged the need of efficient monitoring and management of road traffic. Conventional techniques for traffic measurements, such as inductive loops, sensors or EM microwave detectors, suffer from serious shortcomings, expensive to install, they demand traffic disruption during installation or maintenance, they are bulky and they are unable to detect slow or temporary stop vehicles. Traffic surveillance system is an active research topic in computer vision that tries to detect, recognize and track vehicles over a sequence of images and it also makes an attempt to understand and describe object behavior, vehicle activity by replacing the aging old traditional method of monitoring cameras by human operators. A computer vision system can monitor both immediate unauthorized behavior and long term suspicious behavior, and hence alerts the human operator for deeper investigation of the event. The system can be developed for video surveillance system can be manual, semi-automatic, or fully-automatic depending on the human involvement. The Automatic vehicle number plate recognition (ANPR), was invented the Police Scientific Development Branch in United Kingdom’s in 1976 for safety and security reasons. The prototype was implemented in 1979. Automatic vehicle plate detection system was commonly used in parking lot areas and road traffic monitoring system. There are some problems related to Automatic License Plate Recognition like 1) Plate variations which includes location, quantity, size, color, font, occlusion, inclination, standard versus vanity, etc: 2) Environment variations: which includes illumination and backgrounds. Various license plate detection algorithms have been developed in past few years. Each of these algorithms has their own advantages and disadvantages. For most traffic surveillance systems there are three major stages which are used for estimation of desired traffic parameters i.e. vehicle detection, tracking, and classification. The simple flow of process is shown in figure 1.1. This flow chart is basic flow chart for Automatic car detection and number plate recognition for video surveillance system. As shown in the figure, the first step is video acquisition system in which input video is going for the process. Then after using moving object detection technique car is detected from the video for moving objection detection. There are mainly four methods to detect moving object from the video sequences i.e.  Background subtraction  Optical flow  Frame differencing filtering  Block Matching Fig. 1.1: Simple flow of process A. After detecting a car, license plate is extracted from detected area. License Plate extraction can be done by five different methods.  License Plate Extraction Using Boundary/Edge  License Plate Extraction Using Global Image Information  License Plate Extraction Using Texture Features  License Plate Extraction Using Color Features  License Plate Extraction Using Character Features After extraction of license plate, the character segmentation is done. Character segmentation can be done in four different ways. Those are:  Using Pixel Connectivity