Four cornered code based Chinese character recognition system.

by Tham Yiu-Man.Thesis (M.Phil.)--Chinese University of Hong Kong, 1993.Includes bibliographical references.Abstract --- p.iAcknowledgements --- p.iiiTable of Contents --- p.ivChapter Chapter I --- IntroductionChapter 1.1 --- Introduction --- p.1-1Chapter 1.2 --- Survey on Chinese Character Recognition --- p.1-4Chapter 1.3 --- Methodology Adopts in Our System --- p.1-7Chapter 1.4 --- Contributions and Organization of the Thesis --- p.1-11Chapter Chapter II --- Pre-processing and Stroke ExtractionChapter 2.1 --- Introduction --- p.2-1Chapter 2.2 --- Thinning --- p.2-1Chapter 2.2.1 --- Introduction to Thinning --- p.2-1Chapter 2.2.2 --- Proposed Thinning Algorithm Cater for Stroke Extraction --- p.2-6Chapter 2.2.3 --- Thinning Results --- p.2-9Chapter 2.3 --- Stroke Extraction --- p.2-13Chapter 2.3.1 --- Introduction to Stroke Extraction --- p.2-13Chapter 2.3.2 --- Proposed Stroke Extraction Method --- p.2-14Chapter 2.3.2.1 --- Fork point detection --- p.2-16Chapter 2.3.2.2 --- 8-connected fork point merging --- p.2-18Chapter 2.3.2.3 --- Sub-stroke extraction --- p.2-18Chapter 2.3.2.4 --- Fork point merging --- p.2-19Chapter 2.3.2.5 --- Sub-stroke connection --- p.2-24Chapter 2.3.3 --- Stroke Extraction Accuracy --- p.2-27Chapter 2.3.4 --- Corner Detection --- p.2-29Chapter 2.3.4.1 --- Introduction to Corner Detection --- p.2-29Chapter 2.3.4.2 --- Proposed Corner Detection Formulation --- p.2-30Chapter 2.4 --- Concluding Remarks --- p.2-33Chapter Chapter III --- Four Corner CodeChapter 3.1 --- Introduction --- p.3-1Chapter 3.2 --- Deletion of Hook Strokes --- p.3-3Chapter 3.3 --- Stroke Types Selection --- p.3-5Chapter 3.4 --- Probability Formulations of Stroke Types --- p.3-7Chapter 3.4.1 --- Simple Strokes --- p.3-7Chapter 3.4.2 --- Square --- p.3-8Chapter 3.4.3 --- Cross --- p.3-10Chapter 3.4.4 --- Upper Right Corner --- p.3-12Chapter 3.4.5 --- Lower Left Corner --- p.3-12Chapter 3.5 --- Corner Segments Extraction Procedure --- p.3-14Chapter 3.5.1 --- Corner Segment Probability --- p.3-21Chapter 3.5.2 --- Corner Segment Extraction --- p.3-23Chapter 3.6 4 --- C Codes Generation --- p.3-26Chapter 3.7 --- Parameters Determination --- p.3-29Chapter 3.8 --- Sensitivity Test --- p.3-31Chapter 3.9 --- Classification Rate --- p.3-32Chapter 3.10 --- Feedback by Corner Segments --- p.3-34Chapter 3.11 --- Classification Rate with Feedback by Corner Segment --- p.3-37Chapter 3.12 --- Reasons for Mis-classification --- p.3-38Chapter 3.13 --- Suggested Solution to the Mis-interpretation of Stroke Type --- p.3-41Chapter 3.14 --- Reduce Size of Candidate Set by No.of Input Segments --- p.3-43Chapter 3.15 --- Extension to Higher Order Code --- p.3-45Chapter 3.16 --- Concluding Remarks --- p.3-46Chapter Chapter IV --- RelaxationChapter 4.1 --- Introduction --- p.4-1Chapter 4.1.1 --- Introduction to Relaxation --- p.4-1Chapter 4.1.2 --- Formulation of Relaxation --- p.4-2Chapter 4.1.3 --- Survey on Chinese Character Recognition by using Relaxation --- p.4-5Chapter 4.2 --- Relaxation Formulations --- p.4-9Chapter 4.2.1 --- Definition of Neighbour Segments --- p.4-9Chapter 4.2.2 --- Formulation of Initial Probability Assignment --- p.4-12Chapter 4.2.3 --- Formulation of Compatibility Function --- p.4-14Chapter 4.2.4 --- Formulation of Support from Neighbours --- p.4-16Chapter 4.2.5 --- Stopping Criteria --- p.4-17Chapter 4.2.6 --- Distance Measures --- p.4-17Chapter 4.2.7 --- Parameters Determination --- p.4-21Chapter 4.3 --- Recognition Rate --- p.4-23Chapter 4.4 --- Reasons for Mis-recognition in Relaxation --- p.4-27Chapter 4.5 --- Introduction of No-label Class --- p.4-31Chapter 4.5.1 --- No-label Initial Probability --- p.4-31Chapter 4.5.2 --- No-label Compatibility Function --- p.4-32Chapter 4.5.3 --- Improvement by No-label Class --- p.4-33Chapter 4.6 --- Rate of Convergence --- p.4-35Chapter 4.6.1 --- Updating Formulae in Exponential Form --- p.4-38Chapter 4.7 --- Comparison with Yamamoto et al's Relaxation Method --- p.4-40Chapter 4.7.1 --- Formulations in Yamamoto et al's Relaxation Method --- p.4-40Chapter 4.7.2 --- Modifications in [YAMAM82] --- p.4-42Chapter 4.7.3 --- Performance Comparison with [YAMAM82] --- p.4-43Chapter 4.8 --- System Overall Recognition Rate --- p.4-45Chapter 4.9 --- Concluding Remarks --- p.4-48Chapter Chapter V --- Concluding RemarksChapter 5.1 --- Recapitulation and Conclusions --- p.5-1Chapter 5.2 --- Limitations in the System --- p.5-4Chapter 5.3 --- Suggestions for Further Developments --- p.5-6References --- p.R-1Appendix User's GuideChapter A .l --- System Functions --- p.A-1Chapter A.2 --- Platform and Compiler --- p.A-1Chapter A.3 --- File List --- p.A-2Chapter A.4 --- Directory --- p.A-3Chapter A.5 --- Description of Sub-routines --- p.A-3Chapter A.6 --- Data Structures and Header Files --- p.A-12Chapter A.7 --- Character File charfile Structure --- p.A-15Chapter A.8 --- Suggested Program to Implement the System --- p.A-1