Fairhurst, M.C. and Hoque, S. (2000) Moving window classifier: approach to off-line image recognition. Electronics Letters, 36 (7). pp. 628-630. ISSN 0013-5194.
| The full text of this publication is not available from this repository. (Contact us about this Publication) | |
| Official URL http://dx.doi.org/10.1049/el:20000494 |
Abstract
A new classification scheme particularly suited Far text processing is presented. Features are extracted from a partial image projected onto a window and a part-classifier computes scores based on its likelihood of belonging to the candidate classes. This is carried out for overlapping part-images and scores are combined for a final classification. Comparisons with other classifier schemes show improved performance characteristics for appropriate task domains.
| Item Type: | Article |
|---|---|
| Subjects: | T Technology > TK Electrical engineering. Electronics Nuclear engineering T Technology > TA Engineering (General). Civil engineering (General) |
| Divisions: | Faculties > Science Technology and Medical Studies > School of Engineering and Digital Arts |
| Depositing User: | O.O. Odanye |
| Date Deposited: | 18 May 2009 23:55 |
| Last Modified: | 25 Jun 2012 13:53 |
| Resource URI: | http://kar.kent.ac.uk/id/eprint/16082 (The current URI for this page, for reference purposes) |
- Depositors only (login required):
