Texture descriptor based on local combination adaptive ternary pattern
Faten Sandid, Ali Douik · IET Image Processing · 2015
Material recognition has several applications, such as image retrieval, object recognition and robotic manipulation. To make the material classification more suitable for real‐world applications, it is fundamental to satisfy two characteristics: robustness to scale and to pose variations. In this study, the authors propose a novel discriminant descriptor for texture classification based on a new operator called local combination adaptive ternary pattern (LCATP) descriptor used to encode both colour and local information. They start by building the LCATP descriptor using a combination of three different adaptive thresholding techniques. Moreover, they present a novel operator, mean histogram (MH), used jointly with the LCATP in order to incorporate colour information into the descriptor. This approach is then extended to four different colour spaces: L C 1 C 2 , I 1 I 2 I 3 , LSH uv and O 1 O 2 O 3 . The final descriptor, LCATP fusion (LCATP_F), is produced by fusing the basic histogram (H) and MH extracted from the different colour spaces. Finally, the LCATP_F descriptor properties, such as the robustness to scale and pose changes are evaluated using the challenging KTH‐textures under varying illumination, pose and scale (TIPS2b) dataset along with the least squares support vector machines classifier. The obtained experimental results, using the LCATP_F descriptor, show a significant improvement with respect to the state‐of‐the‐art results.