Local ternary patterns explained

Local ternary patterns (LTP) are an extension of local binary patterns (LBP).[1] [2] Unlike LBP, it does not threshold the pixels into 0 and 1, rather it uses a threshold constant to threshold pixels into three values. Considering k as the threshold constant, c as the value of the center pixel, a neighboring pixel p, the result of threshold is:

\begin{cases} 1,&ifp>c+k\\ 0,&ifp>c-kandp<c+k\\ -1&ifp<c-k\\ \end{cases}

In this way, each thresholded pixel has one of the three values. Neighboring pixels are combined after thresholding into a ternary pattern. Computing a histogram of these ternary values will result in a large range, so the ternary pattern is split into two binary patterns. Histograms are concatenated to generate a descriptor double the size of LBP.

See also

Notes and References

  1. Xiaoyang Tan . Triggs . Bill . June 2010 . Enhanced Local Texture Feature Sets for Face Recognition Under Difficult Lighting Conditions . IEEE Transactions on Image Processing . 19 . 6 . 1635–1650 . 10.1109/TIP.2010.2042645 . 20172829 . 1057-7149. 10.1.1.105.3355 .
  2. Ji . Luping . Ren . Yan . Pu . Xiaorong . Liu . Guisong . 2018-07-01 . Median local ternary patterns optimized with rotation-invariant uniform-three mapping for noisy texture classification . Pattern Recognition . 79 . 387–401 . 10.1016/j.patcog.2018.02.009. 2018PatRe..79..387J . 13691471 . free .