Combining Local Binary Patterns for Scene Recognition

Recently, spatial principal component analysis of census transform histograms (PACT) was proposed to recognize instance and categories of places or scenes in an image. An improved representation called Local Difference Binary Pattern (LDBP) also was proposed and performed better than that of PACT. LDBP is based on the comparisons between center pixel and its neighboring pixels, but the relationship among neighbor pixels is not considered. In this paper, we propose to combine Local Neighbor Binary Pattern (LNBP) with LDBP to construct a spatial representation for scene recognition, because that LNBP can provide complementary information regarding neighboring pixels for LDBP. Experiments on widely used datasets demonstrate that the performance of image recognition is further improved with proposed method.