Dissertation > Excellent graduate degree dissertation topics show

Research on Image Recognition Algorithm of Paper Currency

Author: WeiZhengYi
Tutor: DongJingZuo
School: Harbin University of Science and Technology
Course: Communication and Information System
Keywords: notes sorter image recognition feature extraction neural network
CLC: TP391.41
Type: Master's thesis
Year: 2009
Downloads: 481
Quote: 1
Read: Download Dissertation

Abstract


Image recoganition of paper currency is a popular issue in the pattern recognition area in recently years, and it has very wide applicaton foreground.It is an important means of improving paper currency identification instrument extension, which is maintained at a higher real-time performance and reliability Notes sorter developed by this technology is playing an increasing role at banks and other financial systems. For this reason, this paper carrys out design and improvement of paper currency image denomination, image-oriented, incomplete, and the old and the new identification algorithm,aiming at serious flaws such as weak residual pick, poor classification accuracy and seriously influenced by light intensity and so on.This article applys digital image processing techniques and pattern recognition methods and combines SOFM network to realize real-time identification of paper currency, which making domestic current fourth and fifth edition of the RMB as identification object and based on RMB image gray feature signal in the process of researching notes image recognition algorithm. In this paper,firstly, it uses two straight lines fitting and the geometric model of notes to complete notes image’s border positioning and tip-tilt correction; Secondly, it uses improved size recognition algorithms to complete the measurement of the notes’ size ,in order to determine the denomination of banknotes; Once again, on the basis of denominations of banknotes are identified, it complete four face identification of the notes through establishing and training improved SOFM netwok. Then, it makes binary morphological closing operation on the notes binary image, combined templates Setted up to determine the notes’ incomplete degree and incomplete types by detecting black pixels on template throughout; Finally, in view of the problem that the traditional old and new identification methods of notes are influenced seriously by the light intensity changes, using features that the H and S components in HSI color space are not influenced by light intensity changes, this paper proposes a new and old identification algorithm of notes based on color Image. This paper has comprehensive advantages in real time, reliability, anti-light intensity change impacts, classification accuracy and consistency aspects through the entire identification process of the notes.The experimental results show that, notes sorter formula and image recoganition of paper currency algorithm proposed in this paper satisfy technical requirements of image recoganition and sorting, recoganition accuracy rate is not less than 99%. To current domestic sorter research , it has higher significance.

Related Dissertations

  1. Research on Automatic Detection Algorithm for Substructure Distress of Highway Pavement Based on SVM,U418.6
  2. ISAR Imaging Simulation of Space Targets and Target Recognition Based on ISAR Images,TN957.52
  3. Research on Transductive Support Vector Machine and Its Application in Image Retrieval,TP391.41
  4. Research on Visual Measurement for Spacecraft Rendezvous and Approach,TP391.41
  5. Research on the Image Real-Time Acquisition, Storage and Image Processing System,TP391.41
  6. Feature Extraction, Selection and Combination in Lipreading,TP391.41
  7. Multi-currency Notes Technology Research and Implementation,TP391.41
  8. The Research on Paper Currency Classification Method Based on Harr-Like Feature and Minimal Ball Including Samples,TP391.41
  9. Research on Visual Servo System of Mechanical ARM,TP242.6
  10. Municipal tourism land use planning environmental impact assessment,X820.3
  11. Study on Taste Characteristic of Taste Peptide Enzymatic Production from Oyster Base on A Neural Network Method,TS254.4
  12. Research on Nondestructive Detection Technology for External Qualities of Papayas Based-on Vision,S667.9
  13. Research on Identification System of Cashmere and Wool Fiber,TS101.921
  14. Research of Diagnosing Cucumber Diseases Based on Hyperspectral Imaging,S436.421
  15. Based on Data Mining Technologies in Urban Water Supply Analysis and Decision,F299.24;F224
  16. The Research of Image Matching Method Based on Feature Descriptor,TP391.41
  17. Visual-based Localization Algorithm Design on Humanoid Robot Soccer,TP391.41
  18. Prediction of Binding Affinity of Human Transporter Associated with Antigen Processing,R392.1
  19. The Discrimination of Rice Weeds Based on DSP,TP391.41
  20. Software Project Risk Assessment Based on BP Neural Networks,TP183
  21. Object-Oriented Analysis Based on Neutral Network,TP311.52

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