Adaptive transfer function design for volume renering by using a general regression neural network renering read rendering

摘要

The transfer function is responsible for the three-dimensional image classification and its design is a key process in volume visualization applications. However, it is difficult and time-consuming for the users to design new proper transfer function when the types of the studied images change. By introducing a general regression neural network (GRNN) into the transfer function design, together with a proper image evaluation strategy, a new volume rendering framework is proposed in this paper. Experimental results showed that by using GRNN to guide the transfer function design, the robustness of volume rendering is promoted and the corresponding classification process is optimized.