Heritage Debris Classification Based on 3D Texture Feature and SVM

A heritage debris classification based on 3D texture feature and SVM is proposed in this paper. We compute the bidirectional histogram and correlation function of Lambertian, isotropic, randomly rough surfaces which are common in real-world scenes firstly, and final classification results are gained with SVM. Performance is evaluated by employing 600 texture images corresponding to 61 real-world surface samples extracted from the Columbia-Utrecht reflectance and texture (CUReT) database. The experiments produce good classification results, and we discuss the advantages and disadvantages of this methods and its scope of application.