3D Model Retrieval Using Relevance Feedback based Semantic Kernel PCA

作     者：Xinying WANG~(1,+) Shengsheng WANG~1 Tianyang LV~2 Zhengxuan WANG~1 ~1 College of Computer Science and Technology,Jilin University,Changchun 130012,China ~2College of Computer Science and Technology,Harbin Engineering University,Harbin 150001,China 

会议名称：《第四届全国信息检索与内容安全学术会议》

会议日期：2008年

学科分类：08[工学] 080203[工学-机械设计及理论] 0802[工学-机械工程] 

基　　金：supported by the National Natural Science Foundation of China under Grant Nos.60773096,60603030 Foundation for the Doctoral Program of the Chinese Ministry of Education under Grant No.20060183041 

关 键 词：3D Model Retrieval Relevance Feedback Latent Semantic Kernel Kernel PCA 

摘      要：3D model retrieval is an important part of multimedia information *** solve the drawbacks of the traditional text-based method,current researches concentrate on the content-based 3D model ***, the performance of the content-based method isn’t satisfying because of the semantic *** this paper,we provide a method of semantic kernel PCA for dimensionality reduction and feature extraction in content-based 3D model *** data of users’long-term relevance feedback were used to construct a semantic kernel,and then we use the semantic kernel to assist Gaussian kernel in kernel PCA to reduce dimension of 3D model features. Experimental results on Princeton Shape Benchmark have shown the effectiveness of our proposed method.