Title :
Multiresolution gray-scale and rotation invariant texture classification with local binary patterns
Author :
Ojala, Timo ; Pietikäinen, Matti ; Mäenpää, Topi
Author_Institution :
Machine Vision & Media Process. Unit, Oulu Univ., Finland
fDate :
7/1/2002 12:00:00 AM
Abstract :
Presents a theoretically very simple, yet efficient, multiresolution approach to gray-scale and rotation invariant texture classification based on local binary patterns and nonparametric discrimination of sample and prototype distributions. The method is based on recognizing that certain local binary patterns, termed "uniform," are fundamental properties of local image texture and their occurrence histogram is proven to be a very powerful texture feature. We derive a generalized gray-scale and rotation invariant operator presentation that allows for detecting the "uniform" patterns for any quantization of the angular space and for any spatial resolution and presents a method for combining multiple operators for multiresolution analysis. The proposed approach is very robust in terms of gray-scale variations since the operator is, by definition, invariant against any monotonic transformation of the gray scale. Another advantage is computational simplicity as the operator can be realized with a few operations in a small neighborhood and a lookup table. Experimental results demonstrate that good discrimination can be achieved with the occurrence statistics of simple rotation invariant local binary patterns
Keywords :
image classification; image texture; invariance; nonparametric statistics; angular space; computational simplicity; gray-scale variations; local binary patterns; local image texture; multiresolution analysis; multiresolution gray-scale texture classification; nonparametric discrimination; occurrence histogram; prototype distributions; rotation invariant texture classification; sample distributions; spatial resolution; uniform patterns; Gray-scale; Histograms; Image recognition; Image texture; Multiresolution analysis; Pattern recognition; Prototypes; Quantization; Robustness; Spatial resolution;
Journal_Title :
Pattern Analysis and Machine Intelligence, IEEE Transactions on
DOI :
10.1109/TPAMI.2002.1017623