Dissertation > Excellent graduate degree dissertation topics show

Design and Implementation of System of Tables with Handwritten Content

Author: WangZuo
Tutor: LuHongWei
School: Huazhong University of Science and Technology
Course: Computer System Architecture
Keywords: Pattern Recognition Mathematical Morphology Tables Recognition Handwritten Digits Recognition
CLC: TP391.41
Type: Master's thesis
Year: 2011
Downloads: 0
Quote: 0
Read: Download Dissertation

Abstract


With the development of computer hardware, and the constant improvement of artificial intelligence, more and more simple and repetitive mental work begins to be replaced by computers. As the result, it not only improves the work efficiency greatly, but also helps people to get rid of dull mental work. For there are still many documents of handwritten tables which need to be input computers manually, a input system of handwritten tables is designed under the theories of mathematical morphology and pattern recognition in this paper. This system can automatically analyze variety of papers, documents, questionnaires and then submits them into computer. Through this system, the efficiency of statistical work can be significantly improved and the input of human resources can be reduced.The system is designed by the modular principle and it will become a platform for recognition of different types of files by the combination of different modules. The information inputting has three steps: first, system will prepossess the scanned pictures to remove the noise and interference, and to stress the useful information; second, the table structure will be extracted and the location information of table cells will be get, the images for recognition will be output according to the cells which they belong to; third, the images will be recognized by the structure recognition methods and then be input into computers, different character sets will have different structure recognition methods, at the same time the system will throw out the ambiguous characters for artificial recognition.The experiment shows that the input system of handwritten tables can find the statistical information and recognize it accurately and effectively, the recognition rate of the system can meet the application requirements. If the system works with the office All-in-Ones printers which can batch-scan documents quickly, it can be used for variety handwritten tables recognition, the information input efficiency will be improved obviously and more human resources will be saved.

Related Dissertations

  1. The Classification of High Dimsnsion Flew Field Based on Manifold Learning,V231.3
  2. Tongue Feature Extraction and Research of Fusion Classification,TP391.41
  3. Research on Text Classification Based on Biomimetic Pattern Recongnition,TP391.1
  4. The Properties of Laser Speckle Based on the Mathematical Morphology,O29
  5. Road extraction algorithm based on region segmentation of remote sensing image,TP751
  6. Technology of Blood Vessel Diameter Measurement Automatic Based on Digital Image Processing,R310
  7. Research on Identification System of Cashmere and Wool Fiber,TS101.921
  8. Intrusion detection based on the ultrasonic echo envelope in the military security patrols,E919
  9. The Application of Ant Colony Algorithm in Meteorological Satellite Cloud Pictures Segmentation,TP391.41
  10. Based on high-resolution remote sensing data mining houses information extraction,TP751
  11. Research on Key Technologies of Turning Expert System Based on SE300,TP182
  12. Improved Mathematical Model of Spatial Information Processing Based on Fuzzy Technology,O159
  13. Research and Implementation of Dwt-based Video Codec System at Low Bit Rates,TN919.81
  14. The EMG Pattern Recognition System Based on Generalized Dynamic Fuzzy Neural Network,TP183
  15. A Study on the Value Indictors System of Cultural Heritages in Henan,G122
  16. Action surface EMG nonlinear characteristic of,TH772
  17. CUDA-based video fire detection system,TP391.41
  18. Dollar bill image detection of critical information and number identification,TP391.41
  19. SVM Based on SIFT and scene classification,TP391.41
  20. Haze environment image enhancement algorithm and its application,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