Dissertation > Excellent graduate degree dissertation topics show

Image Processing Based on Pattern Recognition and Its Application to License Plate Recognition

Author: SunZuoChao
Tutor: LiXueBin
School: Beijing University of Chemical Technology
Course: Applied Computer Technology
Keywords: License Plate Recognition License Plate Location Character segmentation Character recognition
CLC: TP391.41
Type: Master's thesis
Year: 2009
Downloads: 352
Quote: 4
Read: Download Dissertation

Abstract


With the rapid development of economy and society , the sharp increase in car ownership , road transport has become an important transportation route , increasingly congested city traffic requires more advanced , more efficient traffic management and control tool. The use of electronic information technology to build intelligent transportation systems (IntelligentTransportation System, ITS) to improve management efficiency, traffic efficiency , traffic management has become the main direction of development . LPR (License Plate Recognition, LPR) is a research hotspot of intelligent transportation systems , intelligent transportation systems also affect modern key factor. License Plate Recognition comes to digital image processing, pattern recognition, artificial intelligence, and many other subjects , its implementation process is generally divided into the positioning plate , license plate character segmentation and character recognition in three parts. In this paper, texture, color and other characteristics as well as morphological and neural network technology, the license plate recognition system, a preliminary study , the main work is as follows : 1. For car license plate recognition system, the problem of poor image quality , is proposed based on blind enhanced deconvolution algorithm, and presents a combination of textures and colors of license plate location method . The method utilizes a vertical plate character has obvious characteristics of texture , the vertical edge image edge detection for combined morphological and inherent feature of the license plate to determine the suspected license area ; while in the HSV color space for color segmentation , extract color features to meet the license plate zone. (2) using Radon algorithm to achieve a tilted plate image correction , and designed a peak projection information using the character segmentation algorithms. Experiments show that , with the license plate character width , spacing and other fixed ratio between the a priori knowledge , the use of the vertical projection method for character segmentation can achieve better results for complex environments shooting car images. 3 combined with contour matching method and the improved BP neural network algorithm to achieve a digital character recognition. BP algorithm exists for slow convergence , easy to fall into local minimum drawback , namely the introduction of momentum factor and adaptive learning rate to improve it . Recognition results are good , the overall recognition rate of 96.3% . Experimental results show that the system can accurately positioning, segmentation and identification plate , the performance is good.

Related Dissertations

  1. Research of License Plate Recognition Based on Rough Sets and Fuzzy SVM,TP391.41
  2. Vehicle License Plate Recognition Algorithm Based on the PowerPC Architecture,TP391.41
  3. Research and Design on License Plate Location in Complex Background,TP391.41
  4. Based on Fuzzy Theory automatic vehicle number plate recognition system design and implementation,TP391.41
  5. Traffic video monitoring of certain key algorithm design and application,TP391.41
  6. High-speed detection and bayonet vehicle license identification information,TP391.41
  7. Based on high-definition images of the bayonet vehicle information recognition system design and implementation,TP391.41
  8. Car License Plate Recognition Method,TP391.41
  9. Haze environment image enhancement algorithm and its application,TP391.41
  10. License plate recognition system is a key technology research,TP391.41
  11. License plate recognition system and its hardware implementation of,TP391.41
  12. Research on Plate Positioning Algorithm Based on Image Processing,TP391.41
  13. The Research Based on the Restoration Approach of Super-Resolution Distilled from Highway Video Monitoring,TP391.41
  14. Research on Key Techniques of License Plate Recognition,TP391.41
  15. Numeral recognition technology based on image processing,TP391.41
  16. License Plate Recognition System License Plate Location Algorithm,TP391.41
  17. Vehicle Information Acquisition and Processing on Intelligent Transportation System,TP391.41
  18. Research on New Type License Plate Recognition Based on Neural Network,TP391.41
  19. License Plate Recognition Based on Gray Information,TP391.41
  20. Automatic license plate location and character segmentation,TP391.41
  21. New Approach to Recognition of Blurred License Plate Based on Improved Natural Image Matting Algorithm,TP391.41

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