A Completed Modeling of Local Binary Pattern Operator for Texture Classification

Abstract

Abstract-In this paper, a completed modeling of the LBP operator is proposed and an associated completed LBP (CLBP) scheme is developed for texture classification. A local region is represented by its center pixel and a local difference sign-magnitude transform (LDSMT). The center pixels represent the image gray level and they are converted into a binary code, namely CLBP-Center (CLBP_C), by global thresholding. LDSMT decomposes the image local differences into two complementary components: the signs and the magnitudes, and two operators, namely CLBP-Sign (CLBP_S) and CLBP-Magnitude (CLBP_M), are proposed to code them. The traditional LBP is equivalent to the CLBP_S part of CLBP, and we show that CLBP_S preserves more information of the local structure than CLBP_M, which explains why the simple LBP operator can extract the texture features reasonably well. By combining CLBP_S, CLBP_M, and CLBP_C features into joint or hybrid distributions, significant improvement can be made for rotation invariant texture classification.

Classification of urban areas from GeoEye-1 imagery through texture features based on Histograms of Equivalent Patterns

“…As it was already reported by Guo et al [2010], better texture classification accuracy than the state-of-the-art LBP algorithms can be obtained by fusing the CLBP_S, CLBP_M and CLBP_C codes, either in a joint or in a hybrid way. The ranking drawn up by Fernández et al [2013] presented CLBP_S_MxC as the best texture descriptor of the five HEP mappings tested in this work, followed by ILBP, BGC1, LBP and CLBP_MxC respectively.…”

“…[6]). On a different note, Completed Local Binary Patterns (CLBP) are actually combinations of the three basic operators such as CLBP_Sign (CLBP_S), CLBP_Magnitude (CLBP_M) and CLBP_Center (CLBP_C) described by Guo et al [2010]. CLBP_S is just an alias for LBP, only changing the values of the binary thresholding function (Eq.…”

“…Texture classification has rapidly evolved during the last 20 years and many new approaches have been proposed. Several new texture descriptors such as Local Binary Patterns (LBP) [Ojala et al, 2002], Improved Local Binary Patterns (ILBP) [Jin et al, 2004], Binary Gradient Contours (BGC) [Fernández et al, 2011] or Completed Local Binary Patterns (CLBP) [Guo et al, 2010], have been described in literature. The vast majority of the new available descriptors have been presented in the field of computer vision and pattern recognition and many have never tested in remote sensing applications.…”

Classification of Emphysema Subtypes: Comparative Assessment of Local Binary Patterns and Related Texture Features

“…Thus, the purpose of this study was to comparatively assess the usefulness of LBP and related texture features, namely completed local binary patterns (CLBP) [21] and local ternary patterns (LTP) [22], for the classification of emphysema subtypes on low-dose CT images. LBP was introduced and promoted by Ojala et al [17], and CLBP and LTP were developed as extensions of LBP.…”

“…LBP is a local texture descriptor, whose advantages are computational simplicity, robustness against gray-scale variations, and that against rotation variations. In CLBP, local texture is represented by three components (sign component, magnitude component, and center gray level), and is more discriminant than LBP [21]. While LTP is also a discriminant local texture descriptor, LTP is less sensitive to image noise than LBP [22].…”