关键词: 三维模型检索, 函数投影, 角点, Hausdorff距离, 相似性匹配

Abstract: Heczko algorithm is easy to lose some important information of three-dimensional model outline, thus the matching accuracy is reduced. In view of this question, three-dimensional model similarity matching algorithm based on outline characteristic point was proposed. Through the function projection, the outline of three-dimensional model was extracted， and then the vertex of each outline that was taken as the characteristic point was withdrawn. A set of points was constituted by the characteristic point curvature value. The similarity matching was carried out by calculating the Hausdorff distance of the set of points. The experiment results indicate the retrieval accuracy of the three-dimensional model is improved.

Key words: three-dimensional model retrieval, function projection, vertex, Hausdorff distance, similar match