.png){kind=icon}
.png){kind=icon}
Return
Jumping and Refined Local Pattern for Texture Classification
.png){kind=icon}
OA
AI
DOI：10.1109/ACCESS.2018.2877729.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
The local binary pattern (LBP) model is a simple and effective method of texture classification, but it is sensitive to rotational and noisy images. Although many variants of LBP are proposed by scholars, there are still several urgent problems, such as poor noise and rotation immunity. In this paper, we propose a robust texture descriptor, jumping and refined local pattern (JRLP) for texture classification. In particular, we first extract jumping local difference count pattern (JLDCP) consisting of second-order difference count pattern and diagonal difference count pattern to represent the jumping information in a local domain. To capture the detail information left by JLDCP, we extract a refined completed LBP (RCLBP). By concatenating the JLDCP and RCLBP, we build a JRLP-based robust texture descriptor for classification. Experimental results on four representative texture databases (Brodatz, CUReT, UIUC, and VisTex) reveal that our proposed texture classification method is effective and robust for noise, rotation, scale, and illumination variants and outperforms six representative methods.
Keywords:
Jumping and refined local pattern
local binary pattern
rotation invariant
texture classification
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
3.6
Papers:
9.8W
Citations:
29.4W
Organization
No organization information available