Back to Search
Start Over
Symmetric mean and directional contour pattern for texture classification.
- Source :
-
Electronics Letters (Wiley-Blackwell) . Nov2021, Vol. 57 Issue 24, p918-920. 3p. - Publication Year :
- 2021
-
Abstract
- In this letter, we propose a simple yet effective texture descriptor, symmetric mean and directional contour pattern (SMDCP), for texture classification. In particular, first the robust symmetric mean pattern (RSMP) that extracts the sign and amplitude information of the local difference through the neighbourhood average in a new scheme of encoding to further enhance the robustness to noise is constructed. Then a local directional and contour pattern (LDCP) to represent the contour information and direction information of adjacent sampling points is extracted. By concatenating the RSMP and LDCP, a robust and effective texture descriptor (SMDCP) for classification is built. Experimental results reveal that the proposed method obtains significant performance and high discrimination in comparison with 10 representative approaches. [ABSTRACT FROM AUTHOR]
Details
- Language :
- English
- ISSN :
- 00135194
- Volume :
- 57
- Issue :
- 24
- Database :
- Academic Search Index
- Journal :
- Electronics Letters (Wiley-Blackwell)
- Publication Type :
- Academic Journal
- Accession number :
- 153676881
- Full Text :
- https://doi.org/10.1049/ell2.12310