Individual discriminative subspace for face recognition under uncontrolled conditions

Most face recognition (FR) algorithms require the face images to satisfy certain restrictions in various aspects like view angle, illumination, occlusion, etc. But what is needed in general is the techniques that can recognize any face images recognizable by human beings. This paper provides one potential solution to this problem. A method named Individual Discriminative Subspace (IDS) is proposed for robust face recognition under uncontrolled conditions. IDS is the subspace where only the images from one particular person converge around the origin while those from others scatter. Each IDS can be used to distinguish one individual from others. There is no restriction on the face images fed into the algorithm, which makes it practical for real-life applications. In the experiments, IDS is tested on two large face databases with extensive variations and performs significantly better than 12 existing FR techniques.

Immunology-based subspace detectors for anomaly detection

A key problem in high dimensional anomaly detection is that the time spent in constructing detectors by the means of generateand-test is tolerable. In fact, due to the high sparsity. of the data, it is ineffective to construct detectors in the whole data space. Previous investigations have shown that most essentIal patterns can be discovered in different subspaces. This inspires us to construct detectors in signIficant subspaces only for anomaly detection. We first use ENCLUS-based method to discover all significant subspaces and .then use a greedy-growth algorithm to construct detectors in each subspace. The elements used to constItute a detector are gods Instead of data points, which makes the time-consumption irrelevant to the size of the nonnal data. We test the effectiveness and efficiency of our method on both synthetic and benchmark datasets. The results reveal that our method is particularly useful in anomaly detection in high dimensional data spaces.

Facial age estimation by nonlinear aging pattern subspace

Human age estimation by face images is an interesting yet challenging research topic emerging in recent years. This paper extends our previous work on facial age estimation (a linear method named AGES). In order to match the nonlinear nature of the human aging progress, a new algorithm named KAGES is proposed based on a nonlinear subspace trained on the aging patterns, which are defined as sequences of individual face images sorted in time order. Both the training and test (age estimation) processes of KAGES rely on a probabilistic model of KPCA. In the experimental results, the performance of KAGES is not only better than all the compared algorithms, but also better than the human observers in age estimation. The results are sensitive to parameter choice however, and future research challenges are identified.

Regularized nonnegative shared subspace learning

Joint modeling of related data sources has the potential to improve various data mining tasks such as transfer learning, multitask clustering, information retrieval etc. However, diversity among various data sources might outweigh the advantages of the joint modeling, and thus may result in performance degradations. To this end, we propose a regularized shared subspace learning framework, which can exploit the mutual strengths of related data sources while being immune to the effects of the variabilities of each source. This is achieved by further imposing a mutual orthogonality constraint on the constituent subspaces which segregates the common patterns from the source specific patterns, and thus, avoids performance degradations. Our approach is rooted in nonnegative matrix factorization and extends it further to enable joint analysis of related data sources. Experiments performed using three real world data sets for both retrieval and clustering applications demonstrate the benefits of regularization and validate the effectiveness of the model. Our proposed solution provides a formal framework appropriate for jointly analyzing related data sources and therefore, it is applicable to a wider context in data mining.

Nonnegative shared subspace learning and its application to social media retrieval

Although tagging has become increasingly popular in online image and video sharing systems, tags are known to be noisy, ambiguous, incomplete and subjective. These factors can seriously affect the precision of a social tag-based web retrieval system. Therefore improving the precision performance of these social tag-based web retrieval systems has become an increasingly important research topic. To this end, we propose a shared subspace learning framework to leverage a secondary source to improve retrieval performance from a primary dataset. This is achieved by learning a shared subspace between the two sources under a joint Nonnegative Matrix Factorization in which the level of subspace sharing can be explicitly controlled. We derive an efficient algorithm for learning the factorization, analyze its complexity, and provide proof of convergence. We validate the framework on image and video retrieval tasks in which tags from the LabelMe dataset are used to improve image retrieval performance from a Flickr dataset and video retrieval performance from a YouTube dataset. This has implications for how to exploit and transfer knowledge from readily available auxiliary tagging resources to improve another social web retrieval system. Our shared subspace learning framework is applicable to a range of problems where one needs to exploit the strengths existing among multiple and heterogeneous datasets.

Supervised subspace learning with multi-class Lagrangian SVM on the Grassmann manifold

Learning robust subspaces to maximize class discrimination is challenging, and most current works consider a weak connection between dimensionality reduction and classifier design. We propose an alternate framework wherein these two steps are combined in a joint formulation to exploit the direct connection between dimensionality reduction and classification. Specifically, we learn an optimal subspace on the Grassmann manifold jointly minimizing the classification error of an SVM classifier. We minimize the regularized empirical risk over both the hypothesis space of functions that underlies this new generalized multi-class Lagrangian SVM and the Grassmann manifold such that a linear projection is to be found. We propose an iterative algorithm to meet the dual goal of optimizing both the classifier and projection. Extensive numerical studies on challenging datasets show robust performance of the proposed scheme over other alternatives in contexts wherein limited training data is used, verifying the advantage of the joint formulation.

Random Subspace Two-Dimensional PCA for face recognition

The two-dimensional Principal Component Analysis (2DPCA) is a robust method in face recognition. Much recent research shows that the 2DPCA is more reliable than the well-known PCA method in recognising human face. However, in many cases, this method tends to be overfitted to sample data. In this paper, we proposed a novel method named random subspace two-dimensional PCA (RS-2DPCA), which combines the 2DPCA method with the random subspace (RS) technique. The RS-2DPCA inherits the advantages of both the 2DPCA and RS technique, thus it can avoid the overfitting problem and achieve high recognition accuracy. Experimental results in three benchmark face data sets -the ORL database, the Yale face database and the extended Yale face database B - confirm our hypothesis that the RS-2DPCA is superior to the 2DPCA itself.

Improved subspace clustering via exploitation of spatial constraints

We present a novel approach to improving subspace clustering by exploiting the spatial constraints. The new method encourages the sparse solution to be consistent with the spatial geometry of the tracked points, by embedding weights into the sparse formulation. By doing so, we are able to correct sparse representations in a principled manner without introducing much additional computational cost. We discuss alternative ways to treat the missing and corrupted data using the latest theory in robust lasso regression and suggest numerical algorithms so solve the proposed formulation. The experiments on the benchmark Johns Hopkins 155 dataset demonstrate that exploiting spatial constraints significantly improves motion segmentation.

Sparse subspace representation for spectral document clustering

We present a novel method for document clustering using sparse representation of documents in conjunction with spectral clustering. An ℓ1-norm optimization formulation is posed to learn the sparse representation of each document, allowing us to characterize the affinity between documents by considering the overall information instead of traditional pair wise similarities. This document affinity is encoded through a graph on which spectral clustering is performed. The decomposition into multiple subspaces allows documents to be part of a sub-group that shares a smaller set of similar vocabulary, thus allowing for cleaner clusters. Extensive experimental evaluations on two real-world datasets from Reuters-21578 and 20Newsgroup corpora show that our proposed method consistently outperforms state-of-the-art algorithms. Significantly, the performance improvement over other methods is prominent for this datasets.

A slice sampler for restricted hierarchical beta process with applications to shared subspace learning

Hierarchical beta process has found interesting applications in recent years. In this paper we present a modified hierarchical beta process prior with applications to hierarchical modeling of multiple data sources. The novel use of the prior over a hierarchical factor model allows factors to be shared across different sources. We derive a slice sampler for this model, enabling tractable inference even when the likelihood and the prior over parameters are non-conjugate. This allows the application of the model in much wider contexts without restrictions. We present two different data generative models – a linear Gaussian-Gaussian model for real valued data and a linear Poisson-gamma model for count data. Encouraging transfer learning results are shown for two real world applications – text modeling and content based image retrieval.

Sparse subspace clustering via group sparse coding

We propose in this paper a novel sparse subspace clustering method that regularizes sparse subspace representation by exploiting the structural sharing between tasks and data points via group sparse coding. We derive simple, provably convergent, and computationally efficient algorithms for solving the proposed group formulations. We demonstrate the advantage of the framework on three challenging benchmark datasets ranging from medical record data to image and text clustering and show that they consistently outperforms rival methods.

Semi-supervised classification based on subspace sparse representation

Graph plays an important role in graph-based semi-supervised classification. However, due to noisy and redundant features in high-dimensional data, it is not a trivial job to construct a well-structured graph on high-dimensional samples. In this paper, we take advantage of sparse representation in random subspaces for graph construction and propose a method called Semi-Supervised Classification based on Subspace Sparse Representation, SSC-SSR in short. SSC-SSR first generates several random subspaces from the original space and then seeks sparse representation coefficients in these subspaces. Next, it trains semi-supervised linear classifiers on graphs that are constructed by these coefficients. Finally, it combines these classifiers into an ensemble classifier by minimizing a linear regression problem. Unlike traditional graph-based semi-supervised classification methods, the graphs of SSC-SSR are data-driven instead of man-made in advance. Empirical study on face images classification tasks demonstrates that SSC-SSR not only has superior recognition performance with respect to competitive methods, but also has wide ranges of effective input parameters.