File Download
There are no files associated with this item.
Supplementary
-
Citations:
- Scopus: 0
- Appears in Collections:
Conference Paper: A novel feature extraction approach for remote sensing image based on the shape-adaptive neighborhood
Title | A novel feature extraction approach for remote sensing image based on the shape-adaptive neighborhood |
---|---|
Authors | |
Keywords | Color feature Feature extraction Shape adaptive neighborhood Shape feature Texture feature |
Issue Date | 2008 |
Citation | 29th Asian Conference on Remote Sensing 2008, ACRS 2008, 2008, v. 1, p. 440-445 How to Cite? |
Abstract | Feature extraction is a significant procedure for target recognition and classification of remotely sensed images. In this paper, the previous feature extraction methods were considered to consist of three layers: the abstract layer, the methodology layer and the feature layer. A new feature extraction approach based on the shape adaptive neighborhood (SAN) in the abstract layer was proposed. Firstly, the heterogeneity based on the color characteristics was defined to determine the SAN for each pixel. Then all the color, texture and shape features were extracted from each SAN, and fused together by a feature level fusion method. In the experiment, the features were used to execute the classification work. As the results showed, most of the SANs contained enough pixels for the texture and shape analysis, and the total precision was 0.9354. |
Persistent Identifier | http://hdl.handle.net/10722/277617 |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Zhang, Hongsheng | - |
dc.contributor.author | Li, Yan | - |
dc.date.accessioned | 2019-09-27T08:29:29Z | - |
dc.date.available | 2019-09-27T08:29:29Z | - |
dc.date.issued | 2008 | - |
dc.identifier.citation | 29th Asian Conference on Remote Sensing 2008, ACRS 2008, 2008, v. 1, p. 440-445 | - |
dc.identifier.uri | http://hdl.handle.net/10722/277617 | - |
dc.description.abstract | Feature extraction is a significant procedure for target recognition and classification of remotely sensed images. In this paper, the previous feature extraction methods were considered to consist of three layers: the abstract layer, the methodology layer and the feature layer. A new feature extraction approach based on the shape adaptive neighborhood (SAN) in the abstract layer was proposed. Firstly, the heterogeneity based on the color characteristics was defined to determine the SAN for each pixel. Then all the color, texture and shape features were extracted from each SAN, and fused together by a feature level fusion method. In the experiment, the features were used to execute the classification work. As the results showed, most of the SANs contained enough pixels for the texture and shape analysis, and the total precision was 0.9354. | - |
dc.language | eng | - |
dc.relation.ispartof | 29th Asian Conference on Remote Sensing 2008, ACRS 2008 | - |
dc.subject | Color feature | - |
dc.subject | Feature extraction | - |
dc.subject | Shape adaptive neighborhood | - |
dc.subject | Shape feature | - |
dc.subject | Texture feature | - |
dc.title | A novel feature extraction approach for remote sensing image based on the shape-adaptive neighborhood | - |
dc.type | Conference_Paper | - |
dc.identifier.scopus | eid_2-s2.0-84865663692 | - |
dc.identifier.volume | 1 | - |
dc.identifier.spage | 440 | - |
dc.identifier.epage | 445 | - |