Two new parameters for the ordinal analysis of images
This work provides an incremental improvement in image processing for texture analysis, potentially aiding fields like statistical physics and image classification.
The authors tackled the problem of classifying textures in images by identifying three types of 2x2 pixel patterns and deriving two parameters from their statistics, which effectively describe and distinguish textures, particularly for isotropic structures.
Local patterns play an important role in statistical physics as well as in image processing. Two-dimensional ordinal patterns were studied by Ribeiro et al. who determined permutation entropy and complexity in order to classify paintings and images of liquid crystals. Here we find that the 2 by 2 patterns of neighboring pixels come in three types. The statistics of these types, expressed by two parameters, contains the relevant information to describe and distinguish textures. The parameters are most stable and informative for isotropic structures.