%0 Electronic Article %A Feiniu Yuan %A Jinting Shi %A Xue Xia %A Qinghua Huang %A Xuelong Li %K pixel values %K 1-1 bitwise matching number-to-the-0-0 bitwise matching number %K smoke textures %K second-order variation representation %K smoke dataset %K visual scenes %K dissimilarity matching measure %K texture classification %K spatial variation extraction %K co-occurrence matching %K smoke colours %K texture dataset %K first-order LBP codes %K first-order information %K centre pixel %K similarity matching measure %K dissimilarity matching-based local binary patterns %K final feature vector generation %K DMLBP %K feature extraction method %K rotation invariance %K second-order information %K multiscale neighbourhoods %K scale invariance %K mapping modes %K LBP code pair %K 1-0 number-to-the-0-1 number %K smoke shapes %K smoke recognition %K similarity matching-based local binary patterns %K bit-sequences %K visual adaption %K SMLBP %X It is challenging to recognize smoke from visual scenes due to large variations of smoke colors, textures and shapes. To improve robustness, we propose a novel feature extraction method based on similarity and dissimilarity matching measures of Local Binary Patterns (LBP). Given two bit-sequences of an LBP code pair, the similarity and dissimilarity matching measures are defined as the ratios of the 1–1 bitwise matching number to the 0–0 bitwise matching number and the 1–0 number to the 0–1 number, respectively. To capture local code variations, we calculate the measures between LBP codes of a center pixel and its neighbors. Then we compare each measure with its global mean to propose Similarity Matching based Local Binary Patterns (SMLBP) and Dissimilarity Matching based Local Binary Patterns (DMLBP). Since SMLBP and DMLBP extract spatial variations of the 1st order LBP codes, they actually represent the 2nd order variations of pixel values. Furthermore, we adopt different mapping modes and multi-scale neighborhoods to obtain rotation and scale invariances. Finally, we concatenate the histograms of LBP, SMLBP and DMLBP to generate a feature vector containing 1st and 2nd order information. Experiments show that our method obviously outperforms existing methods. %@ 1751-9632 %T Co-occurrence matching of local binary patterns for improving visual adaption and its application to smoke recognition %B IET Computer Vision %D March 2019 %V 13 %N 2 %P 178-187 %I Institution of Engineering and Technology %U https://digital-library.theiet.org/;jsessionid=21h41c976asbl.x-iet-live-01content/journals/10.1049/iet-cvi.2018.5164 %G EN