Symmetric mean and directional contour pattern for texture classification

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 th...

وصف كامل

التفاصيل البيبلوغرافية
الحاوية / القاعدة:Electronics Letters
المؤلفون الرئيسيون: Yongsheng Dong, Boshi Zheng, Hong Liu, Zhiyong Zhang, Zhumu Fu
التنسيق: مقال
اللغة:الإنجليزية
منشور في: Wiley 2021-11-01
الموضوعات:
Other topics in statistics
Image recognition
Computer vision and image processing techniques
الوصول للمادة أونلاين:https://doi.org/10.1049/ell2.12310
الوصف
الملخص: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.
تدمد:0013-5194
1350-911X

مواد مشابهة