计算机辅助设计与图形学学报
計算機輔助設計與圖形學學報
계산궤보조설계여도형학학보
Journal of Computer-Aided Design & Computer Graphics
2015年
11期
2142-2148
,共7页
韩丽%徐建国%黎琳%唐棣
韓麗%徐建國%黎琳%唐棣
한려%서건국%려림%당체
形状分析%Laplacian特征映射%谱图理论%多特征融合%聚类方法
形狀分析%Laplacian特徵映射%譜圖理論%多特徵融閤%聚類方法
형상분석%Laplacian특정영사%보도이론%다특정융합%취류방법
shape analysis%Laplacian eigenmap%spectral graph theory%multi-feature fusion%clustering method
面向三维模型的统一结构描述与智能检索的技术需求, 提出一种Laplacian多特征映射的三维模型形状分析方法. 首先提取三维模型的表面形状与体积特征, 建立融合测地线距离、角距离和空间体积的多特征相似度矩阵; 其次根据 Laplacian 特征映射算法实现三维模型由空域到谱域的转换以及多谱特征分析; 最后通过对 Laplacian 矩阵特征值之间的本征间隙自适应确定聚类数目, 并结合 K-means 聚类方法实现模型的自动结构识别与分割. 实验结果表明, 在同一类模型的结构特征提取与统一分割应用中, 该方法是高效、鲁棒的, 对于实现模型的高层次语义描述、模型配准以及模型检索具有重要的意义.
麵嚮三維模型的統一結構描述與智能檢索的技術需求, 提齣一種Laplacian多特徵映射的三維模型形狀分析方法. 首先提取三維模型的錶麵形狀與體積特徵, 建立融閤測地線距離、角距離和空間體積的多特徵相似度矩陣; 其次根據 Laplacian 特徵映射算法實現三維模型由空域到譜域的轉換以及多譜特徵分析; 最後通過對 Laplacian 矩陣特徵值之間的本徵間隙自適應確定聚類數目, 併結閤 K-means 聚類方法實現模型的自動結構識彆與分割. 實驗結果錶明, 在同一類模型的結構特徵提取與統一分割應用中, 該方法是高效、魯棒的, 對于實現模型的高層次語義描述、模型配準以及模型檢索具有重要的意義.
면향삼유모형적통일결구묘술여지능검색적기술수구, 제출일충Laplacian다특정영사적삼유모형형상분석방법. 수선제취삼유모형적표면형상여체적특정, 건립융합측지선거리、각거리화공간체적적다특정상사도구진; 기차근거 Laplacian 특정영사산법실현삼유모형유공역도보역적전환이급다보특정분석; 최후통과대 Laplacian 구진특정치지간적본정간극자괄응학정취류수목, 병결합 K-means 취류방법실현모형적자동결구식별여분할. 실험결과표명, 재동일류모형적결구특정제취여통일분할응용중, 해방법시고효、로봉적, 대우실현모형적고층차어의묘술、모형배준이급모형검색구유중요적의의.
Aiming at the demands of consistent descriptor and intelligent retrieval technology for 3D shapes, we pro-pose a 3D shape analysis based on Laplacian multi-eigenmap. Firstly, we extract the surface and volumetric features of 3D models and construct a multi-feature affinity matrix based on the measurement of geometric distance, angular dis-tance and volumetric distance. Secondly, our method converts 3D spatial domain to spectral domain by using Laplacian multi-eigenmap which effectively reveals the intrinsic invariance and consistent structure among shapes. Finally, we analyze the eigengap to adaptively determine the clustering number and implement automatic structural recognition and segmentation by combining theK-means clustering method. A series of experimental results have shown its robustness and efficiency in shape matching and shape segmentation. Our work has important significance for the high-level se-mantic description, shape registration and shape retrieval.