The Schatten p-quasi-norm regularized minimization problem has attracted extensive attention in machine learning, image recognition, signal reconstruction, etc. Meanwhile, the l_(2,1)-regularized matrix optimization m...The Schatten p-quasi-norm regularized minimization problem has attracted extensive attention in machine learning, image recognition, signal reconstruction, etc. Meanwhile, the l_(2,1)-regularized matrix optimization models are also popularly used for its joint sparsity. Naturally, the pseudo matrix norm l_(2,p) is expected to carry over the advantages of both l_p and l_(2,1). This paper proposes a mixed l_(2,q)-l_(2,p) matrix minimization approach for multi-image face recognition. To uniformly solve this optimization problem for any q ∈ [1,2] and p ∈(0,2], an iterative quadratic method(IQM) is developed. IQM is proved to iescend strictly until it gets a stationary point of the mixed l_(2,q)-l_(2,p)matrix minimization. Moreover, a more practical IQM is presented for large-scale case. Experimental results on three public facial image databases show that the joint matrix minimization approach with practical IQM not only saves much computational cost but also achievez better performance in face recognition than state-of-the-art methods.展开更多
基金supported by National Natural Science Foundation of China(Grant Nos.11471159 and 61661136001)
文摘The Schatten p-quasi-norm regularized minimization problem has attracted extensive attention in machine learning, image recognition, signal reconstruction, etc. Meanwhile, the l_(2,1)-regularized matrix optimization models are also popularly used for its joint sparsity. Naturally, the pseudo matrix norm l_(2,p) is expected to carry over the advantages of both l_p and l_(2,1). This paper proposes a mixed l_(2,q)-l_(2,p) matrix minimization approach for multi-image face recognition. To uniformly solve this optimization problem for any q ∈ [1,2] and p ∈(0,2], an iterative quadratic method(IQM) is developed. IQM is proved to iescend strictly until it gets a stationary point of the mixed l_(2,q)-l_(2,p)matrix minimization. Moreover, a more practical IQM is presented for large-scale case. Experimental results on three public facial image databases show that the joint matrix minimization approach with practical IQM not only saves much computational cost but also achievez better performance in face recognition than state-of-the-art methods.
