Many Local Pattern Texture Features: Which Is Better for Image-Based Multilabel Human Protein Subcellular Localization Classification?
Table 5
Summarization of local pattern features focusing on bioimage informatics studies.
Number
Name of local pattern features
Brief description
Types
1
Local binary pattern (LBP)
A pioneer of local structural model quantization and the concatenate histogram statistics.
Type 1: focus on the gradient changes of the center pixel in specified directions.
2
Local ternary pattern (LTP)
Using a ternary arithmetic coding given a threshold based on LBP.
3
Local quinary pattern (LQP)
Two thresholds enhancement based on LTP.
4
Completed local binary pattern (CLBP)
Enhance by taking magnitude and center pixel level information into account based on Type 1.
5
Local ternary cooccurrence pattern (LTCoP)
Encodes the cooccurrence of similar ternary edges calculated between the center pixel and its neighbors based on LTP; belongs to rotational invariant feature.
6
Local derivative pattern (LDP)
High-order local pattern descriptor and encodes directional pattern features based on local derivative variations; belongs to a specific direction rotational variant feature.
Type 2: focus on transformation consistency statistics of directional derivative in specified directions between the center pixel and its neighbors.
7
Local tetra pattern (LTrP)
Encodes the relationship of transformation consistency between the center pixel and its neighbors based on vertical and horizontal directions.
Italic type denotes the local pattern features investigated in this study.