Human Body Feature Curve Generating Method Based on Neural Network for 3D Human Body Modelling

This paper presents a method of human body feature curve generating for 3D (three dimensional) human modeling. In the proposed approach, the model of four-layer feed forward BP(back-propagation) neural network is given, by making use of the real human body data, the training samples of the neck, bust, waist and hip are obtained. The weight and the feature curve modeling of the neck, bust, waist and hip can be got respectively after training. Finally, the error analysis is done and the results show that the method can approach the real human body feature curve. Thus it is an effective modelling way for the human body feature curve generating.