| High Level Representation and Recognition of 3D Objects From 2D Images (2007) | |||||||||||||||||
Abstract | |||||||||||||||||
| This paper deals with state-of-the-art novel ideas in high level visualization, understanding and interpretation of 3D objects from 2D images. A new strategy using parallel pattern representation and matching is presented, which is aimed at learning, representing, visualizing, and interpreting 2D line drawings as 3D objects with only very few learning samples. The conventional linear combination method is improved and extended to handle articulated objects. An articulated feature extraction scheme is also presented. The new approach can strengthen advantages of current key methods while overcoming their drawbacks. Furthermore, it is able to distinguish objects with very similar patterns and is more accurate than other existing methods in the literature. Several illustrative examples are demonstrated, including learning, recognizing, visualization and interpretation of 3D object patterns. Future direction and research topics also discussed. Keywords: 2D line drawing visualization and interpretation, 3D objects, learning, representation, parallel matching 1 Introduction | |||||||||||||||||
Publication details | |||||||||||||||||
| |||||||||||||||||