Optimising connectionist models and attributed relational graph matching for object recognition
This research work describes in depth investigation into optimising connectionist models and their applications in rigid object and pattern recognition by attributed relational graph (ARG) matching. The ARG representation is chosen because it encodes relational semantic information in itself and per...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis |
| Language: | English |
| Published: |
2009
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/10356/19661 |
| _version_ | 1826130245602770944 |
|---|---|
| author | Suganthan P. N. |
| author2 | Teoh, Earn Khwang |
| author_facet | Teoh, Earn Khwang Suganthan P. N. |
| author_sort | Suganthan P. N. |
| collection | NTU |
| description | This research work describes in depth investigation into optimising connectionist models and their applications in rigid object and pattern recognition by attributed relational graph (ARG) matching. The ARG representation is chosen because it encodes relational semantic information in itself and performs well under clutter and partial occlusion. The matching of model and scene ARGs is performed using optimising con-nectionist models. Since the connectionist models offer parallel and distributed process-ing, and cost effective hardware implementation, optimising connectionist model-based recognition systems can be employed to solve practical recognition problems. |
| first_indexed | 2024-10-01T07:53:19Z |
| format | Thesis |
| id | ntu-10356/19661 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T07:53:19Z |
| publishDate | 2009 |
| record_format | dspace |
| spelling | ntu-10356/196612023-07-04T15:47:14Z Optimising connectionist models and attributed relational graph matching for object recognition Suganthan P. N. Teoh, Earn Khwang School of Electrical and Electronic Engineering DRNTU::Engineering This research work describes in depth investigation into optimising connectionist models and their applications in rigid object and pattern recognition by attributed relational graph (ARG) matching. The ARG representation is chosen because it encodes relational semantic information in itself and performs well under clutter and partial occlusion. The matching of model and scene ARGs is performed using optimising con-nectionist models. Since the connectionist models offer parallel and distributed process-ing, and cost effective hardware implementation, optimising connectionist model-based recognition systems can be employed to solve practical recognition problems. Doctor of Philosophy (EEE) 2009-12-14T06:20:24Z 2009-12-14T06:20:24Z 1996 1996 Thesis http://hdl.handle.net/10356/19661 en NANYANG TECHNOLOGICAL UNIVERSITY 230 p. application/pdf |
| spellingShingle | DRNTU::Engineering Suganthan P. N. Optimising connectionist models and attributed relational graph matching for object recognition |
| title | Optimising connectionist models and attributed relational graph matching for object recognition |
| title_full | Optimising connectionist models and attributed relational graph matching for object recognition |
| title_fullStr | Optimising connectionist models and attributed relational graph matching for object recognition |
| title_full_unstemmed | Optimising connectionist models and attributed relational graph matching for object recognition |
| title_short | Optimising connectionist models and attributed relational graph matching for object recognition |
| title_sort | optimising connectionist models and attributed relational graph matching for object recognition |
| topic | DRNTU::Engineering |
| url | http://hdl.handle.net/10356/19661 |
| work_keys_str_mv | AT suganthanpn optimisingconnectionistmodelsandattributedrelationalgraphmatchingforobjectrecognition |