A relevance feedback scheme based on Hidden Markov Model Regression for 3D model retrieval

Relevance feedback is an iterative search technique to bridge the semantic gap between the high level user intention and low level data representation. This technique interactively determines a user's desired output or query concept by asking the user whether certain proposed 3D models are relevant or not. For a relevance feedback algorithm to be effective, it must grasp a user's query concept accurately. In this paper, we propose a relevance feedback framework based on Hidden Markov Model Regression (HMMR) in content-based 3D model retrieval systems. Given a 3D model retrieval system, we collect and store user's feedback and use HMMR to enhance the retrieval performances. Experimental results show that this algorithm achieves higher search accuracy than traditional query refinement schemes.

[1]  Liu Yujie,et al.  SHREC’08 entry: 3D model retrieval based on the V system invariant moment , 2008, 2008 IEEE International Conference on Shape Modeling and Applications.

[2]  Kui Wu,et al.  Fuzzy relevance feedback in content-based image retrieval systems using radial basis function network , 2005, 2005 IEEE International Conference on Multimedia and Expo.

[3]  Paul M. Baggenstoss.  A modified Baum-Welch algorithm for hidden Markov models with multiple observation spaces , 2001, IEEE Trans. Speech Audio Process..

[4]  Hema Raghavan,et al.  Active Learning with Feedback on Features and Instances , 2006, J. Mach. Learn. Res..

[5]  Thomas S. Huang,et al.  Relevance feedback: a power tool for interactive content-based image retrieval , 1998, IEEE Trans. Circuits Syst. Video Technol..

[6]  Pang-Ning Tan,et al.  Semi-supervised learning with data calibration for long-term time series forecasting , 2008, KDD.

[7]  Ioannis Pratikakis,et al.  Efficient 3D shape matching and retrieval using a concrete radialized spherical projection representation , 2007, Pattern Recognit..

[8]  Rong Jin,et al.  A unified log-based relevance feedback scheme for image retrieval , 2006, IEEE Transactions on Knowledge and Data Engineering.

[9]  Yang Bai-lin.  A 3D Model Similarity Matching Algorithm Based on Spherical Harmonics Descriptor , 2007 .

[10]  Zhi-Hua Zhou,et al.  Enhancing relevance feedback in image retrieval using unlabeled data , 2006, ACM Trans. Inf. Syst..

[11]  Daniela Giorgi,et al.  Size functions for comparing 3D models , 2008, Pattern Recognit..

[12]  Jun Qin,et al.  Content based 3D model retrieval: A survey , 2008, 2008 International Workshop on Content-Based Multimedia Indexing.

[13]  Gil-Joo Park,et al.  EVALUATION OF KERNEL BASED METHODS FOR RELEVANCE FEEDBACK IN 3D SHAPE RETRIEVAL , 2005 .

[14]  Arthur W. Toga,et al.  Laplace-Beltrami nodal counts: A new signature for 3D shape analysis , 2009, 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro.

[15]  R. Jones,et al.  Active Learning with Feedback on Both Features and Instances , 2006 .

[16]  Zhang Yao,et al.  Content-Based 3-D Model Retrieval: A Survey , 2007, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[17]  Jing Hu,et al.  A Powerful Partial Relevance Feedback for 3D Model Retrieval , 2009, J. Multim..