Preprocessing in 3D model retrieval
Zhongyue Li · Jisuanji gongcheng yu sheji · 2006
With more and more 3D modeling and digitizing tools developed,the techniques of content-based 3D model retrieval become necessary.Because 3D models are given in arbitrary units of measurement,before feature extraction the normalization step transforms model into a canonical coordinate frame.The goal of this procedure is that if one chose a differentscale,position,rotation,or orientation of an original model,then the representation in the canonical coordinate frame would still be the same.The normalization step improves the precise of similarity matching algorithm.Effect of preprocessing plays a more dominant role in content-based 3D model retrieval.Preprocessing of PCA and anisotropy transform is analyzed.