A Scene Images Classification Method Based on Local Binary Patterns and Nearest-Neighbor Classifier

Classification of textures in scene images is very difficult due to the high variability of the data within and between images caused by effects such as non-homogeneity of the textures, changes in illumination, shadows, foreshortening and self-occlusion. For these reasons, finding proper features and representative training samples for a classifier is very problematic. Even defining the classes that can be discriminated with texture information is not so straightforward. In this paper, a visualization-based approach for training a texture classifier is presented. A improved multi-channel local binary patterns (LBP) in RGB color space are used as textured color features and a K-NN is employed for visual training and classification, providing very promising results in the classification of outdoor scene images.