Open AccessTexture Feature Extraction by Using Local Binary Pattern
Author(s) -
Esa Prakasa
Publication year - 2016
Publication title -
inkom: jurnal informatika, sistem kendali komputer
Language(s) - English
Resource type - Journals
ISSN - 2302-6146
DOI - 10.14203/j.inkom.420
Subject(s) - local binary patterns , histogram , pattern recognition (psychology) , texture (cosmology) , artificial intelligence , feature (linguistics) , texture filtering , image texture , pixel , feature extraction , computer vision , mathematics , computer science , image (mathematics) , image processing , linguistics , philosophy
Local Binary Pattern (LBP) is a method that used to describe texture characteristics of the surfaces. By applying LBP, texture pattern probability can be summarised into a histogram. LBP values need to be determined for all of the image pixels. Texture regularity might be determined based on the distribution shape of the LBP histogram. The implementation results of LBP on two texture types - synthetic and natural textures - shows that extracted texture feature can be used as input for pattern classification. Euclidean distance method is applied to classify the texture pattern obtained from LBPcomputation.