| Author | Rattapoom Waranusast |
| Call Number | AIT Thesis no.CS-05-19 |
| Subject(s) | Pattern recognition systems
|
| Note | A thesis submitted in partial fulfillment of the requirements for the
degree of Master of Engineering, School of Advanced Technologies |
| Publisher | Asian Institute of Technology |
| Series Statement | Thesis ; no. CS-05-19 |
| Abstract | Apart from linguistic communication, people also use non-verbal communication to help clarify their ideas. Enabling computers to understand non-verbal language is crucial to making human-computer interaction more natural. Sketching is one important form of non-verbal communication. This research aims to develop algorithms to recognize and interpret medical annotation symbols. The input to this algorithm, an array of time-stamped stroke pixels, is processed to extract primitive stroke elements using speed and direction change. These elements are encoded according to their types and directions and then fed to hidden Markov models (HMMs). These HMMs are used to recognize symbols depending on the sequences of encoded stroke elements. Information depending on recognized symbols, for instance, positions of arrow tips, is the output of this algorithm. A prototype system was built to test this approach. Experiments with the prototype on sets of medical annotation symbols show robustness to noise and flexibility in adding new symbols |
| Year | 2005 |
| Corresponding Series Added Entry | Asian Institute of Technology. Thesis ; no. CS-05-19 |
| Type | Thesis |
| School | School of Advanced Technologies (SAT) |
| Department | Department of Information and Communications Technologies (DICT) |
| Academic Program/FoS | Computer Science (CS) |
| Chairperson(s) | Haddawy, Peter; |
| Examination Committee(s) | Guha, Sumanta;Dailey, Matthew; |
| Scholarship Donor(s) | Asian Institute of Technology Fellowship /
Naresuan University Scholarship; |
| Degree | Thesis (M.Eng.) - Asian Institute of Technology, 2005 |