Dissertation > Excellent graduate degree dissertation topics show

Design and Implementation of image character recognition algorithm

Author: ZhangDa
Tutor: JiangChunHua
School: University of Electronic Science and Technology
Course: Applied Computer Technology
Keywords: Character Recognition Ellipse fitting Principal Component Analysis
CLC: TP391.41
Type: Master's thesis
Year: 2010
Downloads: 232
Quote: 1
Read: Download Dissertation

Abstract


By means of a mathematical theory research and progress, as well as the development of computer technology, digital image processing techniques are increasingly applied to various fields. Pattern recognition by machines instead of human eyes of the unknown judge has a higher value, and thus become an important branch in the field of image processing. Character recognition technology has broad application prospects, has been rapid development, so far, has been successfully applied to OCR, and license plate recognition. Character recognition, however, is associated with the specific work scenarios to meet the specific requirements, with some difficulty, and is still in the research stage of exploration. Herein signage character recognition subsystem includes original image preprocessing, elliptical signage positioning, character region extraction, character segmentation, character recognition, several processes. Image pre-processing, through analysis of the background information on the grayscale images using a global thresholding segmentation binary image, and the background is divided into several types according to the actual situation. Morphological methods to remove a small area of ??connectivity, combined oval feature to remove the interference area. Oval signage positioning and character segmentation part, using the least squares fitting method fitting of elliptic boundary the elliptical geometry parameters, including the oval coordinates of the center, the length of shaft length and tilt angle. Based on the Hough transform to detect the slope of the line to rotate the image, based on the the ellipse fitting geometric parameters of the image cut wrong and the scaling transformation. After this series of geometric transformation to obtain the approximate perfect circular area. The the oval center position, and the oval shape characteristics split the rectangle character region. Analysis of the strengths and weaknesses of character segmentation method of the projection method, the split character projection method combined with a priori knowledge. Character recognition part, to discuss the selection of several eigenvalue analysis of the respective strengths and weaknesses. For template matching method with the penalty factor, select communication background area over heart horizontal lines to both sides of the line segment of the character region, the midpoint as penalty points. The design and implementation of the principal component analysis class walks matrix to generate a matrix of character recognition algorithms. BP neural network recognition method, the input and output data format is designed to determine the number of input and output layer neurons, the transfer function of the trials to select the appropriate number of hidden layer neurons. Sample data to test various pattern recognition algorithms, analysis and comparison of recognition results, while the use of two identification methods to identify the results to improve credibility identification method.

Related Dissertations

  1. The Fatigue State Recognition of the Driver Based on Eye Detection,TP391.41
  2. Application of Improved Principal Component Analysis Algorithm in Course Construction,G642.4
  3. Research of Diagnosing Cucumber Diseases Based on Hyperspectral Imaging,S436.421
  4. The Impact of Tourism on Typical Vegetation in Luya Mountain Nature Reserve, Shanxi Province,S759.9
  5. Macaca mulatta palm morphological study of pattern ridge count,Q954
  6. Zhaoguan Lower Coal Group water inrush prediction and control techniques,TD745
  7. Research on Cultural Industrial Competitiveness of Chong Qing,F224
  8. Vehicle License Plate Recognition Algorithm Based on the PowerPC Architecture,TP391.41
  9. The Research of Prairie Road Light Environment Effects on Physiological Indicators of Drivers,U491.254
  10. Design and implementation of intelligent transportation system based on license plate recognition technology,TP391.41
  11. Research on Feature Extraction, Selection and Classification Algorithms for Pulmonary CAD,TP391.41
  12. Research Onamethod for Human Face Recognition Based on MMTD,TP391.41
  13. Research and Realization of License Plate Character Recognition Algorithm Based on SVM,TP391.41
  14. The Software Development of Coaxiality Error Measuring Equipment Based on Non-diffracting Beam,TP391.41
  15. Competitiveness’ Evaluation and Development Strategy of the Tourism Industry in Huanggang City,F592.7
  16. Research on Rural Information Promoting Urban-rural Integration in Jiangsu Southern Area,F127;F224
  17. The Design of Information System of Power Equipment Current-carrying Faults Diagnosis,TP311.52
  18. The Research of E-government System Performance Evaluation Index System in Linyi City Based on the Principal Component Analysis,G206
  19. Gradient -based license plate recognition algorithm template feature,TP391.41
  20. Face recognition algorithm based on feature fusion research,TP391.41
  21. Visual underwater target detection and recognition,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