Structural Saliency: The Detection of Globally Salient Structures Using a Locally Connected Network
Certain salient structures in images attract our immediate attention without requiring a systematic scan. We present a method for computing saliency by a simple iterative scheme, using a uniform network of locally connected processing elements. The network uses an optimization approach to prod...
| Main Authors: | , |
|---|---|
| Language: | en_US |
| Published: |
2004
|
| Online Access: | http://hdl.handle.net/1721.1/6493 |
| _version_ | 1826197914521698304 |
|---|---|
| author | Ullman, Shimon Sha'ashua, Amnon |
| author_facet | Ullman, Shimon Sha'ashua, Amnon |
| author_sort | Ullman, Shimon |
| collection | MIT |
| description | Certain salient structures in images attract our immediate attention without requiring a systematic scan. We present a method for computing saliency by a simple iterative scheme, using a uniform network of locally connected processing elements. The network uses an optimization approach to produce a "saliency map," a representation of the image emphasizing salient locations. The main properties of the network are: (i) the computations are simple and local, (ii) globally salient structures emerge with a small number of iterations, and (iii) as a by-product of the computations, contours are smoothed and gaps are filled in. |
| first_indexed | 2024-09-23T10:55:35Z |
| id | mit-1721.1/6493 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T10:55:35Z |
| publishDate | 2004 |
| record_format | dspace |
| spelling | mit-1721.1/64932019-04-10T18:33:53Z Structural Saliency: The Detection of Globally Salient Structures Using a Locally Connected Network Ullman, Shimon Sha'ashua, Amnon Certain salient structures in images attract our immediate attention without requiring a systematic scan. We present a method for computing saliency by a simple iterative scheme, using a uniform network of locally connected processing elements. The network uses an optimization approach to produce a "saliency map," a representation of the image emphasizing salient locations. The main properties of the network are: (i) the computations are simple and local, (ii) globally salient structures emerge with a small number of iterations, and (iii) as a by-product of the computations, contours are smoothed and gaps are filled in. 2004-10-04T15:12:55Z 2004-10-04T15:12:55Z 1988-07-01 AIM-1061 http://hdl.handle.net/1721.1/6493 en_US AIM-1061 2792059 bytes 1101302 bytes application/postscript application/pdf application/postscript application/pdf |
| spellingShingle | Ullman, Shimon Sha'ashua, Amnon Structural Saliency: The Detection of Globally Salient Structures Using a Locally Connected Network |
| title | Structural Saliency: The Detection of Globally Salient Structures Using a Locally Connected Network |
| title_full | Structural Saliency: The Detection of Globally Salient Structures Using a Locally Connected Network |
| title_fullStr | Structural Saliency: The Detection of Globally Salient Structures Using a Locally Connected Network |
| title_full_unstemmed | Structural Saliency: The Detection of Globally Salient Structures Using a Locally Connected Network |
| title_short | Structural Saliency: The Detection of Globally Salient Structures Using a Locally Connected Network |
| title_sort | structural saliency the detection of globally salient structures using a locally connected network |
| url | http://hdl.handle.net/1721.1/6493 |
| work_keys_str_mv | AT ullmanshimon structuralsaliencythedetectionofgloballysalientstructuresusingalocallyconnectednetwork AT shaashuaamnon structuralsaliencythedetectionofgloballysalientstructuresusingalocallyconnectednetwork |