On the Purpose of Low-level Vision
This article advances the thesis that the purpose of low-level vision is to encode symbolically all of the useful information contained in an intensity array, using a vocabulary of very low-level symbols: subsequent processes should have access only to this symbolic description. The reason is one of...
| Main Author: | |
|---|---|
| Language: | en_US |
| Published: |
2004
|
| Online Access: | http://hdl.handle.net/1721.1/5800 |
| _version_ | 1811077156072062976 |
|---|---|
| author | Marr, David |
| author_facet | Marr, David |
| author_sort | Marr, David |
| collection | MIT |
| description | This article advances the thesis that the purpose of low-level vision is to encode symbolically all of the useful information contained in an intensity array, using a vocabulary of very low-level symbols: subsequent processes should have access only to this symbolic description. The reason is one of computational expediency: it allows the low-level processes to run almost autonomously: and it greatly simplifies the application of criteria to an image, whose representation in terms of conditions on the initial intensities, or on simple measurements made from them, is very cummbersome. The implications of this thesis for physiological and for computational approaches to vision are discussed. A list is given of several computational problems in low-level vision: some of these are dealt with in the accompanying articles. |
| first_indexed | 2024-09-23T10:38:46Z |
| id | mit-1721.1/5800 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T10:38:46Z |
| publishDate | 2004 |
| record_format | dspace |
| spelling | mit-1721.1/58002019-04-12T08:28:01Z On the Purpose of Low-level Vision Marr, David This article advances the thesis that the purpose of low-level vision is to encode symbolically all of the useful information contained in an intensity array, using a vocabulary of very low-level symbols: subsequent processes should have access only to this symbolic description. The reason is one of computational expediency: it allows the low-level processes to run almost autonomously: and it greatly simplifies the application of criteria to an image, whose representation in terms of conditions on the initial intensities, or on simple measurements made from them, is very cummbersome. The implications of this thesis for physiological and for computational approaches to vision are discussed. A list is given of several computational problems in low-level vision: some of these are dealt with in the accompanying articles. 2004-10-01T20:37:26Z 2004-10-01T20:37:26Z 1974-12-01 AIM-324 http://hdl.handle.net/1721.1/5800 en_US AIM-324 29 p. 1596892 bytes 1254045 bytes application/postscript application/pdf application/postscript application/pdf |
| spellingShingle | Marr, David On the Purpose of Low-level Vision |
| title | On the Purpose of Low-level Vision |
| title_full | On the Purpose of Low-level Vision |
| title_fullStr | On the Purpose of Low-level Vision |
| title_full_unstemmed | On the Purpose of Low-level Vision |
| title_short | On the Purpose of Low-level Vision |
| title_sort | on the purpose of low level vision |
| url | http://hdl.handle.net/1721.1/5800 |
| work_keys_str_mv | AT marrdavid onthepurposeoflowlevelvision |