Dissertation > Excellent graduate degree dissertation topics show

Research of Handwritten Digit Recognition Based on Structural and Statistical Method

Author: ZhangYong
Tutor: LuHongWei
School: Huazhong University of Science and Technology
Course: Computer System Architecture
Keywords: Handwritten digit recognition Support vector classifier Feature combination Skeleton decomposition Tree-like classifier
CLC: TP391.41
Type: Master's thesis
Year: 2011
Downloads: 53
Quote: 0
Read: Download Dissertation

Abstract


Off-line handwritten digit recognition is a problem not solved perfect so far, so it is very challenging. There are so many potential applications such as bank check processing, postal mail sorting, automatic reading of tax forms and various handwritten and printed materials that a lot of researcher persistent to research it.Previous researches and tendency of handwritten digit recognition are introduced. Pre-processing such as image binaryzation, image segmentation, normalization and thinning are discussed. Feature combination do a good contribution to recognition rate but classifier combination not. I research a statistical method use Support vector classifier which has excellent classified ability to classify combined features of gradient and curvature and wavelet features. The method of extract features and using tool of support vector classifier are illustrate in detail.A structural method is researched. More specifically, based on three kinds of feature points, first we extract ten kinds of primitive segments for each image. And then, a tree-like classifier based on the extracted feature points and primitives is applied to classify the numerals. This method needn’t a study procedure and run fast. Finally, to get a good reliability rate, using the two methods to recognize a batch of handwritten digit samples at the same time to get two recognition results and get the final result if two digits are same.The result of experiments shows that our methods are simple and convenient, at the same time, the error rate can accept. The combined recognition even lost some recognition rate but obtain a high reliability rate.

Related Dissertations

  1. Research on Design Method of Parts Based on Manufacturing Features,TH161.1
  2. Korean inherent color of semantic analysis,H55
  3. Based on multi- feature combination and SVM classification algorithm for video content automatically,TP391.41
  4. Research on Feature Ex-traction and Recognition for Ani-mation Resource,TP391.41
  5. The Technique of Trademark Image Retrieval Based on Multi-feature Combination,TP391.3
  6. Research of Affect Recognition from GSR Using Two Improved PSO Algorithms,TN911.7
  7. Applications of the Plant Phenology in the Seasonal Landscape Design,TU986.2
  8. Pages to noise classification algorithm,TP393.092
  9. Based on a combination of standardized local feature image retrieval,TP391.41
  10. Research on Combinatorial Feature’s Reduction, Cluster and Recognition Algorithm for Board Strips Surface Defects,TH878
  11. The Method of Serial Number Identifying on RMB Banknote,TP391.4
  12. Study on Programmable Device Application in PD Online Monitoring System,TM835
  13. Authentication Analysis of Features Based on Lip-Reading Recognition,TP391.4
  14. Relevant Algorithms for General Object Recognition Based on Feature Combination,TP391.4
  15. Research on Content-based Scene and Object Category Recognition,TP391.41
  16. Study on Object Detection and the Semidefinite Programming Relaxed Clustering Algorithm,TP391.41
  17. Research on Parameter Selection of Support Vector Machine and Its Applications in Boiler Unit,TM621.2
  18. Studies on Classfication Algorithms of Motor Imagery-based Brain-computer Interfaces,R319
  19. Research on Key Technologies of Automatic Financial Document Processing System,TH693
  20. Based on Kernel Method Handwritten Digit Recognition,TP391.4
  21. Decision tree classification in the insurance business,TP311.13

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