Contourlet features for 3D surface texture classification and fusion

摘要

Contoulet-based features have been paid much attention in image processing applications such as image enhancement, edge detection, image fusion and image retrieval. In this paper, we present a novel approach which takes advantage of the multi-scale and multi-directional properties of the Contourlet transform to extract features of real-world rough surface texture. These features are effectively used for 3D surface texture classification and fusion. The classification scheme based on these features achieves good results even for those test samples not included in the training data sets. Three-dimensional surface texture fusion based on Contourlet can successfully preserve original texture patterns and retain the significant features of input images, which can generate fusion images under arbitrary illumination directions.