Elastic Net Constraint-Based Tensor Model for High-Order Graph Matching
- 13 September 2019
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cybernetics
- Vol. 51 (8) , 4062-4074
Abstract
The procedure of establishing the correspondence between two sets of feature points is important in computer vision applications. In this article, an elastic net constraint-based tensor model is proposed for high-order graph matching. To control the tradeoff between the sparsity and the accuracy of the matching results, an elastic net constraint is introduced into the tensor-based graph matching model. Then, a nonmonotone spectral projected gradient (NSPG) method is derived to solve the proposed matching model. During the optimization of using NSPG, we propose an algorithm to calculate the projection on the feasible convex sets of elastic net constraint. Further, the global convergence of solving the proposed model using the NSPG method was proved. The superiority of the proposed method is verified through experiments on the synthetic data and natural images.Keywords
Funding Information
- National Natural Science Foundation (61671253, 61701259)
- China Postdoctoral Science Foundation (2016M591891)
- Natural Science Foundation of Jiangsu Province (BK20150864)
- Hong Kong Research Grants Council (C1007-15G)
This publication has 56 references indexed in Scilit:
- Regularization and Variable Selection Via the Elastic NetJournal of the Royal Statistical Society Series B: Statistical Methodology, 2005
- A global solution to sparse correspondence problemsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2003
- A new point matching algorithm for non-rigid registrationComputer Vision and Image Understanding, 2003
- Algorithm 813ACM Transactions on Mathematical Software, 2001
- Nonmonotone Spectral Projected Gradient Methods on Convex SetsSIAM Journal on Optimization, 2000
- On the Best Rank-1 and Rank-(R1 ,R2 ,. . .,RN) Approximation of Higher-Order TensorsSIAM Journal on Matrix Analysis and Applications, 2000
- A graduated assignment algorithm for graph matchingIEEE Transactions on Pattern Analysis and Machine Intelligence, 1996
- An algorithm for associating the features of two imagesProceedings Of The Royal Society B-Biological Sciences, 1991
- Two-Point Step Size Gradient MethodsIMA Journal of Numerical Analysis, 1988
- The Hungarian method for the assignment problemNaval Research Logistics Quarterly, 1955