With increasing number of population and higher rate of development the problem of road accident is also increasing rapidly. So the basic concept is to develop a model that can be useful as a security system in the society and can monitoring the vehicle speed.
A License Plate Recognition (LPR) System is one kind of an Intelligent Transport monitoring System and is of considerable interest because of its potential applications in highway electronic toll collection and traffic monitoring systems. This type of applications puts high demands on the reliability of an LPR System. A lot of work has been done regarding LPR systems for Korean, Chinese, European and US license plates that generated many commercial products. However, little work has been done for Indian license plate recognition systems.
The purpose of this thesis was to develop a real time application which recognizes license plates from cars at a gate, for example at the entrance of a parking area or a border crossing. The system, based on regular PC with video camera, catches video frames which include a visible car license plate and processes them. Once a license plate is detected, its digits are recognized, displayed on the User Interface or checked against a database. The focus is on the design of algorithms used for extracting the license plate from a single image, isolating the characters of the plate and identifying the individual characters.
The proposed system has been implemented using Vision Assistant 7,1 and LabVIEW 7,1. The performance of the system has been investigated on real images of about 100 vehicles. The recognition of about 98% vehicles shows that the system is quite efficient.
Table of Contents
Chapter 1 :Literature Review
1.1 Introduction
1.2 Image Acquisition
1.3 License Plate Extraction
1.4 Segmentation
1.5 Recognition
1.6 Commercial Products
1.6.1 IMPS (Integrated Multi-Pass System)
1.6.2 Perceptics
1.6.3 Vehicle Identification System for Parking Areas (VISPA)
1.6.4 Hi-Tech Solution
1.7 Summary
CHAPTER-2 Introduction:
2.1 Introduction
2.2 Applications of LPR Systems
2.3 Elements of Typical LPR System
2.4 Working of Typical LPR System
2.5 Structure of the Proposed System
2.5.1 Image Acquisition
2.5.2 License Plate Extraction
2.5.3 License Plate Segmentation
2.5.4 License Plate Recognition
2.6 Objective
Chapter-3 : Software Development
3.1 Digital Images
3.1.1 Definition of a Digital Image
3.2 Vision Assistant: An overview
3.2.1 Acquiring Images
3.2.2 Managing Images
3.2.3 Image Processing Functions
3.3 Script Development
3.3.1 Extracting color planes from image
3.3.2 Brightness, Contrast, Gamma adjustment
3.3.3 Image Mask
3.4 Optical Character Recognition (OCR)
3.4.1 What is OCR
3.4.2 When to Use
3.4.3 Training Characters
3.4.4 Reading Characters
3.4.5 OCR Session
3.4.6 Region of Interest (ROI)
3.4.7 Particles, Elements, Objects, and Characters
3.4.8 Character Segmentation
3.4.9 Thresholding
3.4.10 Threshold Limits
3.4.11 Character Spacing
3.4.12 Element Spacing
3.4.13 Character Bounding Rectangle
3.4.14 Read Strategy
3.4.15 Read Resolution
3.4.16 Valid Characters
3.4.16 Removing Small Particles
3.4.17 Removing Particles That Touch the ROI
Chapter-4: Problem Formulation & Proposed Solution
4.1 Problem Definition
4.2 Proposed Solution
Chapter 5 : Simulation and Testing
5.1 Introduction to Lab VIEW
5.2 Code Development
5.3 Problems Encountered
Chapter-6: Conclusions and Future Scope
Research Objectives and Core Themes
This thesis aims to develop an efficient, real-time License Plate Recognition (LPR) system designed to identify Indian vehicles by processing video frames. The primary objective is to implement a system using LabVIEW and Vision Assistant to enhance accuracy and speed compared to traditional neural network-based approaches, addressing the challenges posed by varied license plate formats and changing illumination conditions.
- Development of a robust real-time image processing pipeline for LPR.
- Implementation of image enhancement techniques (Brightness, Contrast, Gamma adjustment).
- Advanced character segmentation and recognition using OCR in a LabVIEW environment.
- Optimization of image masking and ROI (Region of Interest) detection for variable light and angle conditions.
Excerpt from the Book
3.4.9 Thresholding
Thresholding is one of the most important concepts in the segmentation process. Thresholding is separating image pixels into foreground and background pixels based on their intensity values. Foreground pixels are those whose intensity values are within the lower and upper threshold values of the threshold range. Background pixels are those whose intensity values lie outside the lower and upper threshold values of the threshold range. OCR includes one manual method and three automatic methods of calculating the thresholding range:
Fixed Range is a method by which you manually set the threshold value. This method processes grayscale images quickly, but requires that lighting remain uniform across the ROI and constant from image to image. The following three automatic thresholding methods are affected by the pixel intensity of the objects in the ROI. If the objects are dark on a light background, the automatic methods calculate the high threshold value and set the low threshold value to the lower value of the threshold limits. If the objects are light on a dark background, the automatic methods calculate the low threshold value and set the high threshold value to the upper value of the threshold limits.
Summary of Chapters
Chapter 1 :Literature Review: This chapter reviews previous research in the field, detailing methods used for image acquisition, extraction, segmentation, and recognition of license plates.
CHAPTER-2 Introduction:: This chapter covers the applications of LPR systems, describes the components and typical workflow, and defines the structure and objectives of the proposed system.
Chapter-3 : Software Development: This chapter provides a detailed description of image processing tools, software configuration, and OCR functions within Vision Assistant 7.1.
Chapter-4: Problem Formulation & Proposed Solution: This chapter defines the problem regarding vehicle identification and proposes the implementation of a LabVIEW-based solution.
Chapter 5 : Simulation and Testing: This chapter details the LabVIEW implementation, code development, and the results of performance tests on 100 vehicle images.
Chapter-6: Conclusions and Future Scope: This chapter summarizes the project achievements, including the 98% efficiency rate, and discusses future improvements for higher precision.
Keywords
License Plate Recognition, LPR, LabVIEW, Vision Assistant, Image Processing, Optical Character Recognition, OCR, Image Masking, Vehicle Identification, Traffic Monitoring, Image Acquisition, Thresholding, ROI, Character Segmentation, Indian License Plates.
Frequently Asked Questions
What is the core focus of this thesis?
The thesis focuses on the design and real-time implementation of a License Plate Recognition (LPR) system for Indian vehicles using LabVIEW and Vision Assistant software.
What are the central thematic areas?
The work covers image acquisition, license plate extraction, character segmentation, thresholding techniques, and the integration of these processes into a cohesive automated inspection system.
What is the primary research goal?
The goal is to create a robust, high-speed, and accurate LPR system that can function under varied environmental conditions, achieving high recognition rates for real-world application.
Which scientific methods are utilized?
The research uses digital image processing techniques, including LUT (Look-Up Table) transformations for contrast enhancement, advanced masking, and OCR training and reading strategies.
What topics are discussed in the main body?
The main body details the software architecture, the specific LabVIEW code development for image processing, the challenges of working with unstandardized license plates, and an analysis of system accuracy.
Which keywords characterize this work?
Key terms include License Plate Recognition (LPR), LabVIEW, Vision Assistant, OCR, image thresholding, and vehicle identification.
How is the Region of Interest (ROI) handled in this system?
The system uses a dynamically shifting bounding box that scans the masked image to detect characters, rather than relying on fixed coordinates, which improves recognition adaptability.
What were the main problems encountered during the research?
The main challenges included the lack of standardization in Indian license plate font styles and sizes, variable lighting conditions on public roads, and the sensitivity of the system to the angle of image capture.
What efficiency did the proposed system achieve?
Through the optimization of parameters like brightness, contrast, and gamma adjustment, the system achieved an overall recognition efficiency of 98%.
- Citation du texte
- Santosh Kumar Sahoo (Auteur), 2010, A Real-Time Implementation of License Plate Recognition (LPR) System, Munich, GRIN Verlag, https://www.grin.com/document/415659
