Model-based character recognition in low resolution
We propose a combined character separation and recognition approach for low-resolution images of alphanumeric text. By synthesising the image formation process a set of low-resolution templates is created for each character. Cluster algorithms and normalised cross-correlation are then applied to mat...
| Main Authors: | , , |
|---|---|
| Other Authors: | |
| Format: | Conference Paper |
| Published: |
IEEE
2008
|
| Online Access: | http://hdl.handle.net/20.500.11937/24471 |
| _version_ | 1848751439269068800 |
|---|---|
| author | Kuhl, Annika Tan, Tele Venkatesh, Svetha |
| author2 | NA |
| author_facet | NA Kuhl, Annika Tan, Tele Venkatesh, Svetha |
| author_sort | Kuhl, Annika |
| building | Curtin Institutional Repository |
| collection | Online Access |
| description | We propose a combined character separation and recognition approach for low-resolution images of alphanumeric text. By synthesising the image formation process a set of low-resolution templates is created for each character. Cluster algorithms and normalised cross-correlation are then applied to match these templates and thereby allowing both character separation and recognition to be achieved at the same time. Thus characters are recognised using their low-resolution appearance only without applying image enhancement methods. Experiments showed that this approach is able to recognise low-resolution alphanumeric text of down to 5 pixels in size. |
| first_indexed | 2025-11-14T07:52:44Z |
| format | Conference Paper |
| id | curtin-20.500.11937-24471 |
| institution | Curtin University Malaysia |
| institution_category | Local University |
| last_indexed | 2025-11-14T07:52:44Z |
| publishDate | 2008 |
| publisher | IEEE |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | curtin-20.500.11937-244712017-09-13T15:07:15Z Model-based character recognition in low resolution Kuhl, Annika Tan, Tele Venkatesh, Svetha NA We propose a combined character separation and recognition approach for low-resolution images of alphanumeric text. By synthesising the image formation process a set of low-resolution templates is created for each character. Cluster algorithms and normalised cross-correlation are then applied to match these templates and thereby allowing both character separation and recognition to be achieved at the same time. Thus characters are recognised using their low-resolution appearance only without applying image enhancement methods. Experiments showed that this approach is able to recognise low-resolution alphanumeric text of down to 5 pixels in size. 2008 Conference Paper http://hdl.handle.net/20.500.11937/24471 10.1109/ICIP.2008.4711926 IEEE restricted |
| spellingShingle | Kuhl, Annika Tan, Tele Venkatesh, Svetha Model-based character recognition in low resolution |
| title | Model-based character recognition in low resolution |
| title_full | Model-based character recognition in low resolution |
| title_fullStr | Model-based character recognition in low resolution |
| title_full_unstemmed | Model-based character recognition in low resolution |
| title_short | Model-based character recognition in low resolution |
| title_sort | model-based character recognition in low resolution |
| url | http://hdl.handle.net/20.500.11937/24471 |