On Boundary Detection
A description is given of how edge erase of prismatic objects appear through a television camera serving as visual input to a computer. Two types of edge-finding predicates are proposed and compared, one linear in intensity, the other non-linear. A statistical analysis of both is carried out, assumi...
| Main Authors: | , |
|---|---|
| Language: | en_US |
| Published: |
2004
|
| Online Access: | http://hdl.handle.net/1721.1/5867 |
| _version_ | 1811095843398221824 |
|---|---|
| author | Herskovits, Annette Binford, Thomas O. |
| author_facet | Herskovits, Annette Binford, Thomas O. |
| author_sort | Herskovits, Annette |
| collection | MIT |
| description | A description is given of how edge erase of prismatic objects appear through a television camera serving as visual input to a computer. Two types of edge-finding predicates are proposed and compared, one linear in intensity, the other non-linear. A statistical analysis of both is carried out, assuming input data distorted by a Gaussian noise. Both predicates have been implemented as edge-verifying procedures, ie. Procedures aiming at high sensitivity and limited to looking for edges when approximate location and directions are given. Both procedures have been tried on actual scenes. Of the two procedures the non-linear one emerged as a satisfactory solution to line-verification because it performs well in spite of surface irregularities. |
| first_indexed | 2024-09-23T16:30:45Z |
| id | mit-1721.1/5867 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T16:30:45Z |
| publishDate | 2004 |
| record_format | dspace |
| spelling | mit-1721.1/58672019-04-10T18:30:38Z On Boundary Detection Herskovits, Annette Binford, Thomas O. A description is given of how edge erase of prismatic objects appear through a television camera serving as visual input to a computer. Two types of edge-finding predicates are proposed and compared, one linear in intensity, the other non-linear. A statistical analysis of both is carried out, assuming input data distorted by a Gaussian noise. Both predicates have been implemented as edge-verifying procedures, ie. Procedures aiming at high sensitivity and limited to looking for edges when approximate location and directions are given. Both procedures have been tried on actual scenes. Of the two procedures the non-linear one emerged as a satisfactory solution to line-verification because it performs well in spite of surface irregularities. 2004-10-01T20:50:15Z 2004-10-01T20:50:15Z 1970-07-01 AIM-183 http://hdl.handle.net/1721.1/5867 en_US AIM-183 65 p. 28999168 bytes 1279420 bytes application/postscript application/pdf application/postscript application/pdf |
| spellingShingle | Herskovits, Annette Binford, Thomas O. On Boundary Detection |
| title | On Boundary Detection |
| title_full | On Boundary Detection |
| title_fullStr | On Boundary Detection |
| title_full_unstemmed | On Boundary Detection |
| title_short | On Boundary Detection |
| title_sort | on boundary detection |
| url | http://hdl.handle.net/1721.1/5867 |
| work_keys_str_mv | AT herskovitsannette onboundarydetection AT binfordthomaso onboundarydetection |