Incremental Graph Regulated Nonnegative Matrix Factorization for Face Recognition

Abstract

In a real world application, we seldom get all images at one time. Considering this case, if a company hired an employee, all his images information needs to be recorded into the system; if we rerun the face recognition algorithm, it will be time consuming. To address this problem, In this paper, firstly, we proposed a novel subspace incremental method called incremental graph regularized nonnegative matrix factorization (IGNMF) algorithm which imposes manifold into incremental nonnegative matrix factorization algorithm (INMF); thus, our new algorithm is able to preserve the geometric structure in the data under incremental study framework; secondly, considering we always get many face images belonging to one person or many different people as a batch, we improved our IGNMF algorithms to Batch-IGNMF algorithms (B-IGNMF), which implements incremental study in batches. Experiments show that (1) the recognition rate of our IGNMF and B-IGNMF algorithms is close to GNMF algorithm while it runs faster than GNMF. (2) The running times of our IGNMF and B-IGNMF algorithms are close to INMF while the recognition rate outperforms INMF. (3) Comparing with other popular NMF-based face recognition incremental algorithms, our IGNMF and B-IGNMF also outperform then both the recognition rate and the running time.

Orthogonal incremental non-negative matrix factorization algorithm and its application in image classification

“…We compare our method to the following representative methods: (1) INMF (Bucak and Gunsel 2009), INMFSC (Wang and Cai 2014), L 1/2 INMF (Dang et al 2017), IGNMF (Yu et al 2014), IGNMFSC (Wang and Sun 2017) and IOPNMF Lu 2011, 2013); and (2) NMF (Lee and Seung 1999), ONMF (Yoo and Choi 2008). The first six methods are incremental learning methods and the other two methods are non-incremental algorithms.…”

“…Wang and Cai (2014) proposed an incremental learning algorithm for NMF under sparse constraints (INMFSC) that improves the sparseness of the factor matrices. Yu et al (2014) advanced incremental graph regulated NMF (IGNMF) to achieve a better classification by maintaining the neighborhood distribution structure of the original highdimensional data during the process of dimension reduction. Dang et al (2017) integrated sparse constraints with incremental learning to devise an incremental NMF with L 1/2 sparse constraints (L 1/2 INMF) and successfully applied it to SAR image recognition.…”

Active Set Type Algorithms for Nonnegative Matrix Factorization in Hyperspectral Unmixing

“…In [25], an algorithm based on a clustered multitask network was proposed, which considered sparsity, clustering, and neighborhood information. Extension of different regularized NMF models has received significant attention in data mining [23,[26][27][28][29][30][31][32][33][34]. Most of these regularized NMF models are solved by the MU method because it is easy to implement and often yields good results.…”

Parallel Nonnegative Matrix Factorization with Manifold Regularization

“…Liu et al [16] introduced the geometric structure of data into incremental NMF [17,18] and utilized two efficient sparse approximations, buffering and random projected tree, to process large-scale datasets. Yu et al [19] also presented an incremental GNMF algorithm to improve scalability. But these algorithms only performed well for incremental or streaming datasets and could not deal with large-scale batch datasets.…”