Transfer Function Fusing

Based on the observation that it is relatively easier for users to generate several good transfer functions (TFs) for different features of volumetric data, we propose TF fusing, which merges several TFs into a comprehensive one, as a new technique for TF design. We treat the TF fusing as a parameter optimization problem, which can then be solved by using a genetic algorithm (GA). We introduce an energy function based on user voting and image similarity to guide the genetic evolution. Experimental results on some real volumetric data demonstrate the effectiveness of our approach. CR Categories: I.3.3 [Computer Graphics]: Picture and Image Generation

• Type: Conference
• Year: 2006
• Where: VIS
• Authors: Yingcai Wu, Huamin Qu, Hong Zhou, Ming-Yuen Chan
• Keywords: IEEE Visualization, Parameter Optimization Problem, Real Volumetric Data, TF Design, VIS 2006, Visualization