基于VM特征值融合的模型检索算法研究

摘要

小型专业模型库具有模型数量相对较小、相似度大、复杂度低等特点,现有的三维模型检索方法很难对其进行即快速又准确的检索.提出了基于VM特征值融合的模型检索算法,结合德国CCCC小组提出的特征融合(Feature Combination),将法向面和视图特征结合起来,使用特征融合技术来增强对模型的描述能力.通过实验证明了在小型专业模型库上能大幅度提高模型检索的准确度和效率.%The small professional model library has a relatively small number of models, large similarity and low complexity, the existing 3D model retrieval method is difficult to make quick and accurate retrieval. This paper put forward a model retrieval algorithm based on VM eigenvalue combination. Combined with feature combination proposed by CCCC team in German. Used feature combination to enhance the description of the model combined normal plane with view characteristic. It proved that the model retrieval algorithm based on the VM eigenvalue combination could greatly improve the retrieval accuracy and efficiency in a small professional model library though the experiment.