Multi-feature based transfer function design for 3D medical image visualization

Visualization of three dimensional volumetric medical data has been widely used. Even though, it still faces a lot of challenges, such as helping users find out structure of their interest, illustrating features which are significant for diagnosis of disease. In our paper, a multi-feature based transfer function is provided to improve the quality of visualization. We compute a multi-feature descriptor for both two-phase clustering and transfer function design. Moreover, we test the transfer function on several medical datasets to show the efficiency and practicability of our method.