In this paper rotation invariant, single and multiscale Local Binary Patterns and Local Phase Quantization texture based descriptors were evaluated experimentally in the context of land-use and land-cover object-based classification. The texture descriptors were employed in the classification of an IKONOS-2 and a Quickbird-2 image. Experiments showed that both texture characterization approaches perform well, when combined with the grayscale variance. We further investigate a novel descriptor resulting from the concatenation of the grayscale variance histogram and the histogram of codes generated either by Local Binary Patterns or by Local Phase Quantization. These experiments have demonstrated that the proposed descriptor, though more compact, performs as well as a bidimensional histogram representing the joint distribution of both quantities. A final experiment corroborated that the use of descriptors based on Local Binary Patterns or Local Phase Quantization in the remotely sensed images classification delivered produces a 0.1 improvement in the Kappa index in comparison to classifications based on texture features derived from the Gray Level Co-occurrence Matrix (GLCM).
Texture; LBP; LPQ; GLCM; Remote Sensing
