Local ternary patterns

{{Short description|Image processing process}}

{{more citations needed|date=November 2012}}

Local ternary patterns (LTP) are an extension of local binary patterns (LBP).{{Cite journal |last1=Xiaoyang Tan |last2=Triggs |first2=Bill |date=June 2010 |title=Enhanced Local Texture Feature Sets for Face Recognition Under Difficult Lighting Conditions |url=https://ieeexplore.ieee.org/document/5411802 |journal=IEEE Transactions on Image Processing |volume=19 |issue=6 |pages=1635–1650 |doi=10.1109/TIP.2010.2042645 |pmid=20172829 |issn=1057-7149|citeseerx=10.1.1.105.3355 }}{{Cite journal |last1=Ji |first1=Luping |last2=Ren |first2=Yan |last3=Pu |first3=Xiaorong |last4=Liu |first4=Guisong |date=2018-07-01 |title=Median local ternary patterns optimized with rotation-invariant uniform-three mapping for noisy texture classification |journal=Pattern Recognition |volume=79 |pages=387–401 |doi=10.1016/j.patcog.2018.02.009|bibcode=2018PatRe..79..387J |s2cid=13691471 |doi-access=free }} 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, & \text{if } p>c+k \\

0, & \text{if } p>c-k \text{ and } p

-1 & \text{if } p

\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.