Comparison of Texture Recognition Algorithms

Texture plays an important role in human everyday life. Through textures humans can distinguish different types of objects. Texture recognition has important application in fields like remote sensing, industrial surface inspection and biomedical image analysis. Vision is the pivotal way in which textures are recognised. Most existing texture identification algorithms use greyscale images to detect textures. In this paper a texture recognition approach based on the use of Gabor filters and Local binary patterns is used in conjunction with an SVM. An existing texture identification dataset is used to perform comparative analysis and results demonstrate that local binary pattern approach has superior performance.