A recognition system for handwritten Thai numerals | |
| Author | Hor, Ding-chern |
| Call Number | AIT Thesis no. CA-85-13 |
| Subject(s) | Thai language|--Numerals Pattern recognition systems |
| Note | A thesis submitted in partial fulfillment of the requirements for the degree of Master of Science, School of Engineering and Technology |
| Publisher | Asian Institute of Technology |
| Abstract | This study proposes and develops a method for recognition of handwritten Thai numerals. The method combines techniques of simple similarity matching, global feature extraction, and syntactic tree structure analysis. Simple similarity matching, using NXOR function, is used to select few most promising master patterns. Global feature extraction such as numbers of dots, end points, cross points, fork points, and dots of up/down/left/right three lines, is used for initial recognition. Syntactic tree structure analysis, including Freeman chain code tracing, primitive extraction, postfix tree making, and the distance between two trees, is used for final recognition. The recognition rate is over 99% and the average recognition time for a numeral is less than 10 seconds on the IBM-PC. |
| Year | 1985 |
| Type | Thesis |
| School | School of Engineering and Technology (SET) |
| Department | Other Field of Studies (No Department) |
| Academic Program/FoS | Computer Application (CA) |
| Chairperson(s) | Vilas Wuwongse |
| Examination Committee(s) | Kanchana Kanchanasuy ;Huynh, Ngoc Phien |
| Scholarship Donor(s) | The Government of Republic of China |
| Degree | Thesis (M.Sc.) - Asian Institute of Technology, 1985 |