Content-based high-resolution remote sensing image retrieval with local binary patterns

Texture is a very important feature in image analysis including content-based image retrieval (CBIR). A common way of retrieving images is to calculate the similarity of features between a sample images and the other images in a database. This paper applies a novel texture analysis approach, local binary patterns (LBP) operator, to 1m Ikonos images retrieval and presents an improved LBP histogram spatially enhanced LBP (SEL) histogram with spatial information by dividing the LBP labeled images into k*k regions. First different neighborhood P and scale factor R were chosen to scan over the whole images, so that their labeled LBP and local variance (VAR) images were calculated, from which we got the LBP, LBP/VAR, and VAR histograms and SEL histograms. The histograms were used as the features for CBIR and a non-parametric statistical test G-statistic was used for similarity measure. The result showed that LBP/VAR based features got a very high retrieval rate with certain values of P and R, and SEL features that are more robust to illumination changes than LBP/VAR also obtained higher retrieval rate than LBP histograms. The comparison to Gabor filter confirmed the effectiveness of the presented approach in CBIR.