A theory of scene understanding and object recognition.
This dissertation presents a new approach to image interpretation which can produce hierarchical descriptions of visually sensed scenes based on an incrementally learnt hierarchical knowledge base. Multiple segmentation and labelling hypotheses are generated with local constraint satisfaction being...
| Main Author: | |
|---|---|
| Format: | Thesis |
| Language: | English |
| Published: |
Curtin University
1996
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/20.500.11937/194 |
| _version_ | 1848743310067236864 |
|---|---|
| author | Dillon, Craig |
| author_facet | Dillon, Craig |
| author_sort | Dillon, Craig |
| building | Curtin Institutional Repository |
| collection | Online Access |
| description | This dissertation presents a new approach to image interpretation which can produce hierarchical descriptions of visually sensed scenes based on an incrementally learnt hierarchical knowledge base. Multiple segmentation and labelling hypotheses are generated with local constraint satisfaction being achieved through a hierarchical form of relaxation labelling. The traditionally unidirectional segmentation-matching process is recast into a dynamic closed-loop system where the current interpretation state is used to drive the lower level image processing functions. The theory presented in this dissertation is applied to a new object recognition and scene understanding system called Cite which is described in detail. |
| first_indexed | 2025-11-14T05:43:32Z |
| format | Thesis |
| id | curtin-20.500.11937-194 |
| institution | Curtin University Malaysia |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-14T05:43:32Z |
| publishDate | 1996 |
| publisher | Curtin University |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | curtin-20.500.11937-1942017-02-20T06:42:40Z A theory of scene understanding and object recognition. Dillon, Craig scene understanding object recognition Cite This dissertation presents a new approach to image interpretation which can produce hierarchical descriptions of visually sensed scenes based on an incrementally learnt hierarchical knowledge base. Multiple segmentation and labelling hypotheses are generated with local constraint satisfaction being achieved through a hierarchical form of relaxation labelling. The traditionally unidirectional segmentation-matching process is recast into a dynamic closed-loop system where the current interpretation state is used to drive the lower level image processing functions. The theory presented in this dissertation is applied to a new object recognition and scene understanding system called Cite which is described in detail. 1996 Thesis http://hdl.handle.net/20.500.11937/194 en Curtin University fulltext |
| spellingShingle | scene understanding object recognition Cite Dillon, Craig A theory of scene understanding and object recognition. |
| title | A theory of scene understanding and object recognition. |
| title_full | A theory of scene understanding and object recognition. |
| title_fullStr | A theory of scene understanding and object recognition. |
| title_full_unstemmed | A theory of scene understanding and object recognition. |
| title_short | A theory of scene understanding and object recognition. |
| title_sort | theory of scene understanding and object recognition. |
| topic | scene understanding object recognition Cite |
| url | http://hdl.handle.net/20.500.11937/194 |