Binbin Pan

Incremental Nonnegative Matrix Factorization for Face Recognition

Nonnegative matrix factorization (NMF) is a promising approach for local feature extraction in face recognition tasks. However, there are two major drawbacks in almost all existing NMF-based methods. One shortcoming is that the computational cost is expensive for large matrix decomposition. The other is that it must conduct repetitive learning, when the training samples or classes are updated. To overcome these two limitations, this paper proposes a novel incremental nonnegative matrix factorization (INMF) for face representation and recognition. The proposed INMF approach is based on a novel constraint criterion and our previous block strategy. It thus has some good properties, such as low computational complexity, sparse coefficient matrix. Also, the coefficient column vectors between different classes are orthogonal. In particular, it can be applied to incremental learning. Two face databases, namely FERET and CMU PIE face databases, are selected for evaluation. Compared with PCA and some state-of-the-art NMF-based methods, our INMF approach gives the best performance.

Incremental learning based on block sparse kernel nonnegative matrix factorization

Nonnegative matrix factorization (NMF) is a promising method for local feature extraction in face recognition. However, NMF is time-consuming when performing on a large matrix. Another limitation of NMF is that it cannot update the factors incrementally as new training data are available. To overcome these limitations, this paper proposes a block sparse kernel nonnegative matrix factorization (BSKNMF) based on the block strategy. The block trick not only reduces the computational costs, but also helps to update the factors of NMF incrementally. The kernel strategy and sparse technique are incorporated into NMF, leading to a more powerful method for feature extraction. The ORL and Yale face databases are chosen for evaluation on time efficiency and recognition rate. Compared with NMF and PNMF, the proposed approach gives the best performance.

Efficient learning of supervised kernels with a graph-based loss function

This paper presents our study of the problems associated with learning supervised kernels from a large amount of side information. We propose a new loss function derived from the Laplacian matrix of a special complete graph that is generated from the side information. We analyze the relationship between the proposed loss function and the kernel alignment. Our theoretical analysis shows that the proposed loss function has a close relationship with kernel alignment, that is, they both make use of side information that is fused in a matrix, in addition to a similar regularization strategy. Moreover, the proposed loss function has a linear form, and thus it is more efficient in learning side information than kernel alignment that has to be performed nonlinearly. The proposed loss function is used to generate new kernels as low-cost alternatives of kernels learned by certain state-of-the-art methods. The empirical results demonstrate the superiority of the proposed method over state-of-the-art methods in terms of classification accuracy and computational cost.

A novel constraint non-negative matrix factorization criterion based incremental learning in face recognition

This paper addresses incremental learning and time-consuming problems in non-negative matrix factorization (NMF) of face recognition. When the training samples or classes are incremental, almost all existing NMF based methods must implement repetitive learning. Also, they are usually very time-consuming. To overcome these limitations, we proposed a novel constraint block NMF (CBNMF) method, which is based on a new constraint NMF criterion and our previous block technique in NMF. CMU PIE face database is selected for evaluation. Comparing with Block NMF (BNMF), NMF and PCA methods, experimental results show that our proposed CBNMF approach gives the best performance.

A sparse representation and dictionary learning based algorithm for image restoration in the presence of Rician noise

Rician noise removal for Magnetic Resonance Imaging (MRI) is very important because the MRI has been widely used in various clinical applications and the associated Rician noise deteriorates the image quality and causes errors in interpreting the images. Great efforts have recently been devoted to develop the corresponding noise-removal algorithms, particularly the development based on the newly-established Total Variation (TV) theorem. However, all the TV-based algorithms depend mainly on the gradient information and have been shown to produce the so called blocky artifact, which also deteriorates the image quality and causes image interpretation errors. In order to avoid producing the artifact, this paper presents a new de-noising model based on sparse representation and dictionary learning. The Split Bregman Iteration strategy is employed to implement the model. Furthermore, an appropriate dictionary is designed by the use of the Kernel Singular Value Decomposition method, resulting in a new Rician noise removal algorithm. Compared with other de-noising algorithms, the presented new algorithm can achieve superior performance, in terms of quantitative measures of the Structural Similarity Index and Peak Signal to Noise Ratio, by a series of experiments using different images in the presence of Rician noise.

Block kernel Nonnegative Matrix Factorization and its application to Face Recognition

Traditional nonnegative matrix factorization (NMF) is an unsupervised method for linear feature extraction. Recently, NMF with block strategy is shown to be able to extract more sparse and discriminative information of the images. To enhance the discriminative power of NMF, this paper proposes a block kernel nonnegative matrix factorization (BKNMF) based on the kernel theory and block technique. Kernel method is an effective way to model the nonlinear relations, which could help us to extract nonlinear features. Furthermore, we make use of the class label information to reduce the within-class distance for further improving the discriminative performance. We theoretically analyze the convergence of the proposed method. Three face databases, namely Yale, ORL and FERET databases, are chosen for evaluations. Compared with some state-of-the-art methods, experimental results show that our BKNMF approach achieves superior performance.

A new parallel MRI image reconstruction model with elastic net regularization

It is known that lots of MRI imaging reconstruction approaches usually encounter ill-posed problem. To address this problem, we propose a novel method for MRI imaging reconstruction via a new regularization constraint term. The regularization term is inspired by elastic net and is a combination of elastic net and total-variation(TV). The proposed MRI imaging reconstruction model is solved using the alternating direction method of multipliers(ADMM). In addition, our approach also achieves good performance for image reconstruction under noised image situation. Experimental results show that our method is effective and superior to the traditional methods.

A Novel Nonnegative Matrix Factorization Algorithm for Multi-manifold Learning

Nonnegative matrix factorization (NMF) is a promising approach to extract the sparse features of facial images. It is known that the facial images usually reside on multi-manifold due to the variations of illumination, pose and facial expression. However, NMF lacks the ability of modeling the structure of data manifold. To improve the performance of NMF for multi-manifold learning, we propose a novel Manifold based NMF (Mani-NMF) algorithm which incorporates the multi-manifold structure. The proposed algorithm simultaneously minimizes the local scatter in the same manifold and maximizes the non-local scatter between different manifolds. It theoretically proves the convergence of the algorithm. Finally, experiments on the face databases demonstrate the superiority of our method over some state of the art algorithms.