Yi- Chen

Dictionary-based face recognition from video

The main challenge in recognizing faces in video is effectively exploiting the multiple frames of a face and the accompanying dynamic signature. One prominent method is based on extracting joint appearance and behavioral features. A second method models a person by temporal correlations of features in a video. Our approach introduces the concept of video-dictionaries for face recognition, which generalizes the work in sparse representation and dictionaries for faces in still images. Video-dictionaries are designed to implicitly encode temporal, pose, and illumination information. We demonstrate our method on the Face and Ocular Challenge Series (FOCS) Video Challenge, which consists of unconstrained video sequences. We show that our method is efficient and performs significantly better than many competitive video-based face recognition algorithms.

Video-based face recognition via joint sparse representation

In video-based face recognition, a key challenge is in exploiting the extra information available in a video; e.g., face, body, and motion identity cues. In addition, different video sequences of the same subject may contain variations in resolution, illumination, pose, and facial expressions. These variations contribute to the challenges in designing an effective video-based face-recognition algorithm. We propose a novel multivariate sparse representation method for video-to-video face recognition. Our method simultaneously takes into account correlations as well as coupling information among the video frames. Our method jointly represents all the video data by a sparse linear combination of training data. In addition, we modify our model so that it is robust in the presence of noise and occlusion. Furthermore, we kernelize the algorithm to handle the non-linearities present in video data. Numerous experiments using unconstrained video sequences show that our method is effective and performs significantly better than many state-of-the-art video-based face recognition algorithms in the literature.

In-Plane Rotation and Scale Invariant Clustering Using Dictionaries

In this paper, we present an approach that simultaneously clusters images and learns dictionaries from the clusters. The method learns dictionaries and clusters images in the radon transform domain. The main feature of the proposed approach is that it provides both in-plane rotation and scale invariant clustering, which is useful in numerous applications, including content-based image retrieval (CBIR). We demonstrate the effectiveness of our rotation and scale invariant clustering method on a series of CBIR experiments. Experiments are performed on the Smithsonian isolated leaf, Kimia shape, and Brodatz texture datasets. Our method provides both good retrieval performance and greater robustness compared to standard Gabor-based and three state-of-the-art shape-based methods that have similar objectives.

Rotation invariant simultaneous clustering and dictionary learning

In this paper, we present an approach that simultaneously clusters database members and learns dictionaries from the clusters. The method learns dictionaries in the Radon transform domain, while clustering in the image domain. Themain feature of the proposed approach is that it provides rotation invariant clustering which is useful in Content Based Image Retrieval (CBIR). We demonstrate through experimental results that the proposed rotation invariant clustering provides better retrieval performance than the standard Gabor-based method that has similar objectives.

Dictionary Learning from Ambiguously Labeled Data

We propose a novel dictionary-based learning method for ambiguously labeled multiclass classification, where each training sample has multiple labels and only one of them is the correct label. The dictionary learning problem is solved using an iterative alternating algorithm. At each iteration of the algorithm, two alternating steps are performed: a confidence update and a dictionary update. The confidence of each sample is defined as the probability distribution on its ambiguous labels. The dictionaries are updated using either soft (EM-based) or hard decision rules. Extensive evaluations on existing datasets demonstrate that the proposed method performs significantly better than state-of-the-art ambiguously labeled learning approaches.

Dictionaries for image and video-based face recognition [Invited].

In recent years, sparse representation and dictionary-learning-based methods have emerged as powerful tools for efficiently processing data in nontraditional ways. A particular area of promise for these theories is face recognition. In this paper, we review the role of sparse representation and dictionary learning for efficient face identification and verification. Recent face recognition algorithms from still images, videos, and ambiguously labeled imagery are reviewed. In particular, discriminative dictionary learning algorithms as well as methods based on weakly supervised learning and domain adaptation are summarized. Some of the compelling challenges and issues that confront research in face recognition using sparse representations and dictionary learning are outlined.

Ambiguously Labeled Learning Using Dictionaries

We propose a dictionary-based learning method for ambiguously labeled multiclass classification, where each training sample has multiple labels and only one of them is the correct label. The dictionary learning problem is solved using an iterative alternating algorithm. At each iteration of the algorithm, two alternating steps are performed: 1) a confidence update and 2) a dictionary update. The confidence of each sample is defined as the probability distribution on its ambiguous labels. The dictionaries are updated using either soft or hard decision rules. Furthermore, using the kernel methods, we make the dictionary learning framework nonlinear based on the soft decision rule. Extensive evaluations on four unconstrained face recognition datasets demonstrate that the proposed method performs significantly better than state-of-the-art ambiguously labeled learning approaches.

Dictionary-Based Face and Person Recognition From Unconstrained Video

To recognize people in unconstrained video, one has to explore the identity information in multiple frames and the accompanying dynamic signature. These identity cues include face, body, and motion. Our approach is based on video-dictionaries for face and body. Video-dictionaries are a generalization of sparse representation and dictionaries for still images. We design the video-dictionaries to implicitly encode temporal, pose, and illumination information. In addition, our video-dictionaries are learned for both face and body, which enables the algorithm to encode both identity cues. To increase the ability of our algorithm to learn nonlinearities, we further apply kernel methods for learning the dictionaries. We demonstrate our method on the Multiple Biometric Grand Challenge, Face and Ocular Challenge Series, Honda/UCSD, and UMD data sets that consist of unconstrained video sequences. Our experimental results on these four data sets compare favorably with those published in the literature. We show that fusing face and body identity cues can improve performance over face alone.

Salient views and view-dependent dictionaries for object recognition

A sparse representation-based approach is proposed to determine the salient views of 3D objects. The salient views are categorized into two groups. The first are boundary representative views that have several visible sides and object surfaces that may be attractive to humans. The second are side representative views that best represent views from sides of an approximating convex shape. The side representative views are class-specific and possess the most representative power compared to other within-class views. Using the concept of characteristic view class, we first present a sparse representation-based approach for estimating the boundary representative views. With the estimated boundaries, we determine the side representative views based on a minimum reconstruction error criterion. Furthermore, to evaluate our method, we introduce the notion of view-dependent dictionaries built from salient views for applications in 3D object recognition and retrieval. The proposed view-dependent dictionaries encode information on geometry across views and representation of the object. Through a series of experiments on four publicly available 3D object datasets, we demonstrate the effectiveness of our approach compared to two existing state-of-the-art algorithms and one baseline method. HighlightsA sparse representation-based approach is proposed to determine the salient views of 3D objects.The salient views are categorized into boundary representative and side representative views.We present a sparse representation-based approach for estimating the boundary representative views.We determine the side representative views based on a minimum reconstruction error criterion.We introduce view-dependent dictionaries for applications in 3D object recognition and retrieval.

Adaptive representations for video-based face recognition across pose

In this paper, we address the problem of matching faces across changes in pose in unconstrained videos. We propose two methods based on 3D rotation and sparse representation that compensate for changes in pose. The first is Sparse Representation-based Alignment (SRA) that generates pose aligned features under a sparsity constraint. The mapping for the pose aligned features are learned from a reference set of face images which is independent of the videos used in the experiment. Thus, they generalize across data sets. The second is a Dictionary Rotation (DR) method that directly rotates video dictionary atoms in both their harmonic basis and 3D geometry to match the poses of the probe videos. We demonstrate the effectiveness of our approach over several state-of-the-art algorithms through extensive experiments on three challenging unconstrained video datasets: the video challenge of the Face and Ocular Challenge Series (FOCS), the Multiple Biometrics Grand Challenge (MBGC), and the Human ID datasets.