关键词: 三维测量, 臀部体型, 概率神经网络, 识别模型

Abstract: It is a key issue that how to achieve precise body shape identification. In order to improve the fitting of garment on hips, the characteristic of young female’s hip was taken considered in this paper, and a recognition model for young females’ hip shapes using Probabilistic Neural Network (PNN) method based on 3D body measurement was constructed. At first, hip sizes had acquired based on 3D body measurement, 6 characteristic indices were extracted, and hip shapes were classified; then, Probabilistic Neural Network (PNN) method was introduced, a model, whose input layer contained six characteristic indices, output layer was shape types and pattern layer was Radial Basis Function (RBF) was constructed; after then, the simulation was completed by MATLAB R2009a, and the exact and steady model was obtained by training; at last, the accuracy of model was tested. The result showed that the model had excellent performance, with high prediction accuracy, so that it could provide a new method to recognize young female’ hip shapes and widen applicability of PNN method as well.

Key words: 3-D body measurement, hip shape, probabilistic neural network method, recognition model