Dissertation > Excellent graduate degree dissertation topics show

A New Practicable Vehicle License Plate Location and Recognition System

Author: LiWei
Tutor: SunYouXianï¼›ShenGuoJiang
School: Zhejiang University
Course: Control Theory and Control Engineering
Keywords: License Plate Recognition License Plate Location License plate character segmentation License plate character recognition Hough transform BP neural network
CLC: TP391.41
Type: Master's thesis
Year: 2008
Downloads: 434
Quote: 7
Read: Download Dissertation


Automatic license plate recognition technology is the field of automatic control, and one of the important research topics in the field of traffic engineering, and has a very high theoretical research and practical application value. With the rapid development of automatic control technology, computer technology and communications technology, new research methods and technologies continue to emerge, and shows the enormous power and potential for development in the practical engineering applications. Complete automatic license plate recognition system by the vehicle image in order to obtain the license plate location, license plate character segmentation and license plate character recognition is composed of four parts, including the license plate location, license plate characters recognition technology is the key to the entire automatic license plate recognition system. Papers from the license plate positioning technology, the license plate character segmentation three face automatic license plate recognition technology to carry out a full range of in-depth study of the technology and license plate character recognition technologies. Experimental results show that The research results can effectively identify the license plate, and the effect is significant. The main content of the paper is as follows: 1. Describes the composition, structure and working mechanism of the vehicle monitoring and management system. Analysis license plate location advantages and disadvantages of existing algorithms based on a new type of the comprehensive utilization license plate texture features, color features and geometric characteristics of the fast positioning algorithm. The algorithm uses the mathematical morphology full mining license plate texture features and eliminate the noise, the image is divided into a number of sub-regional, texture condition and color conditions to determine the sub-region a unique classification and clustering fusion, and ultimately from coarse to fine precision to locate the license plate position, then the use of the Hough transform corrective tilt the license plate image and remove the border and rivets, lay a good foundation for the subsequent recognition of license plate character segmentation steps. 3 on the basis of precise positioning of the license plate, according to the geometric characteristics of the arrangement of the law and the character of the license plate character analysis of the license plate the second character of the third inter-character dot character segmentation algorithm adversely affected. Makes the characters and the background clear distinction plate region binarization using Ostu Act. Character segmentation algorithm combines unique both ends of the scanning method and set of a priori knowledge of the license plate character judgment rule, which can effectively eliminate the the dot character segmentation algorithm adverse impact. Firstly, the vertical projection histogram ends scanning, respectively, split the five characters of the first two characters and the rear, on this basis, then the character area splitting and merging. Based on accurate segmentation of license plate characters of the license plate character recognition technologies. Centered license plate character position and size normalization using a coarse mesh simplified character feature extraction methods and the use of improved BP neural network to identify characters. Arranged in accordance with the license plate characters characteristics, training structure of Chinese characters, letters and alphanumeric mixed the three BP neural network classifier accordingly identified by the serial number of the license plate characters, and then recognize the result of a combination plate numbers. Recognition algorithm based on the license plate location using Delphi preparation of the completion of the system software, and packaged as a dynamic link library file. Introduced software program structure, function, functions, interfaces sequence of function calls, as well as instructions for use, in order to facilitate the application called correctly.

Related Dissertations

  1. Research on Feature Extraction and Classification of Tongue Shape and Tooth-Marked Tongue in TCM Tongue Diagnosis,TP391.41
  2. Research on Visual Servo System of Mechanical ARM,TP242.6
  3. Municipal tourism land use planning environmental impact assessment,X820.3
  4. Research on Recognition of Fabric Weave Pattern Based on Space-Frequency Domain,TS101.923
  5. The Research on Evaluation of Living Status Systems of Expressway Relocated People,D523
  6. The Optimization Research of Feedforward Neural Network Based on Genetic Algorithms,TP183
  7. Research on License Plate Location Algorithm of License Plate Recognition System,TP391.41
  8. Vehicle License Plate Recognition Algorithm Based on the PowerPC Architecture,TP391.41
  9. Design of Positive Draw-back Motion of Wool Spinning Frame and Comparison of Prediction Models of Worsted Yarns Performances,TP183
  10. Reliability Robust Design of Impeller of Large Centrifugal Compressor,TH452
  11. Research on the Application of BP Neutral Network Based on Particle Swarm Optimi Zation in Dam Displacement Prediction,TV698.1
  12. Research on Classification and Matching for Hand Vein Image,TP391.41
  13. Planar Region Segmentation of Coloured Point Cloud Data Based on Architecture,TP391.41
  14. Research of Adaptive Active Noise Control Based on Neural Network,TP183
  15. The Applicability of Data Mining Technology for Environmental Protection Management System,TP311.13
  16. Research on the Vision-Based Driver Fatigue Real-Time Detection,TP391.41
  17. Research on Feature Extraction, Selection and Classification Algorithms for Pulmonary CAD,TP391.41
  18. Application of the BP ANN in the Spunmelt Nonwoven Product development,TP183
  19. Research Offingerprint of Communication Behavior,TP311.13
  20. Research and Realization of License Plate Character Recognition Algorithm Based on SVM,TP391.41
  21. Research on Promotional Sales Forecast Based on PCA and Particle Swarm Optimized BP Neural Network,F274

CLC: > Industrial Technology > Automation technology,computer technology > Computing technology,computer technology > Computer applications > Information processing (information processing) > Pattern Recognition and devices > Image recognition device
© 2012 www.DissertationTopic.Net  Mobile