Yui Man Lui

Visual object tracking using adaptive correlation filters

Although not commonly used, correlation filters can track complex objects through rotations, occlusions and other distractions at over 20 times the rate of current state-of-the-art techniques. The oldest and simplest correlation filters use simple templates and generally fail when applied to tracking. More modern approaches such as ASEF and UMACE perform better, but their training needs are poorly suited to tracking. Visual tracking requires robust filters to be trained from a single frame and dynamically adapted as the appearance of the target object changes. This paper presents a new type of correlation filter, a Minimum Output Sum of Squared Error (MOSSE) filter, which produces stable correlation filters when initialized using a single frame. A tracker based upon MOSSE filters is robust to variations in lighting, scale, pose, and nonrigid deformations while operating at 669 frames per second. Occlusion is detected based upon the peak-to-sidelobe ratio, which enables the tracker to pause and resume where it left off when the object reappears.

Overview of the Multiple Biometrics Grand Challenge

The goal of the Multiple Biometrics Grand Challenge (MBGC) is to improve the performance of face and iris recognition technology from biometric samples acquired under unconstrained conditions. The MBGC is organized into three challenge problems. Each challenge problem relaxes the acquisition constraints in different directions. In the Portal Challenge Problem, the goal is to recognize people from near-infrared (NIR) and high definition (HD) video as they walk through a portal. Iris recognition can be performed from the NIR video and face recognition from the HD video. The availability of NIR and HD modalities allows for the development of fusion algorithms. The Still Face Challenge Problem has two primary goals. The first is to improve recognition performance from frontal and off angle still face images taken under uncontrolled indoor and outdoor lighting. The second is to improve recognition performance on still frontal face images that have been resized and compressed, as is required for electronic passports. In the Video Challenge Problem, the goal is to recognize people from video in unconstrained environments. The video is unconstrained in pose, illumination, and camera angle. All three challenge problems include a large data set, experiment descriptions, ground truth, and scoring code.

An introduction to the good, the bad, & the ugly face recognition challenge problem

The Good, the Bad, & the Ugly Face Challenge Problem was created to encourage the development of algorithms that are robust to recognition across changes that occur in still frontal faces. The Good, the Bad, & the Ugly consists of three partitions. The Good partition contains pairs of images that are considered easy to recognize. On the Good partition, the base verification rate (VR) is 0.98 at a false accept rate (FAR) of 0.001. The Bad partition contains pairs of images of average difficulty to recognize. For the Bad partition, the VR is 0.80 at a FAR of 0.001. The Ugly partition contains pairs of images considered difficult to recognize, with a VR of 0.15 at a FAR of 0.001. The base performance is from fusing the output of three of the top performers in the FRVT 2006. The design of the Good, the Bad, & the Ugly controls for pose variation, subject aging, and subject “recognizability.” Subject recognizability is controlled by having the same number of images of each subject in every partition. This implies that the differences in performance among the partitions are result of how a face is presented in each image.

Action classification on product manifolds

Videos can be naturally represented as multidimensional arrays known as tensors. However, the geometry of the tensor space is often ignored. In this paper, we argue that the underlying geometry of the tensor space is an important property for action classification. We characterize a tensor as a point on a product manifold and perform classification on this space. First, we factorize a tensor relating to each order using a modified High Order Singular Value Decomposition (HOSVD). We recognize each factorized space as a Grassmann manifold. Consequently, a tensor is mapped to a point on a product manifold and the geodesic distance on a product manifold is computed for tensor classification. We assess the proposed method using two public video databases, namely Cambridge-Gesture gesture and KTH human action data sets. Experimental results reveal that the proposed method performs very well on these data sets. In addition, our method is generic in the sense that no prior training is needed.

The challenge of face recognition from digital point-and-shoot cameras

Inexpensive “point-and-shoot” camera technology has combined with social network technology to give the general population a motivation to use face recognition technology. Users expect a lot; they want to snap pictures, shoot videos, upload, and have their friends, family and acquaintances more-or-less automatically recognized. Despite the apparent simplicity of the problem, face recognition in this context is hard. Roughly speaking, failure rates in the 4 to 8 out of 10 range are common. In contrast, error rates drop to roughly 1 in 1,000 for well controlled imagery. To spur advancement in face and person recognition this paper introduces the Point-and-Shoot Face Recognition Challenge (PaSC). The challenge includes 9,376 still images of 293 people balanced with respect to distance to the camera, alternative sensors, frontal versus not-frontal views, and varying location. There are also 2,802 videos for 265 people: a subset of the 293. Verification results are presented for public baseline algorithms and a commercial algorithm for three cases: comparing still images to still images, videos to videos, and still images to videos.

Advances in matrix manifolds for computer vision

The attention paid to matrix manifolds has grown considerably in the computer vision community in recent years. There are a wide range of important applications including face recognition, action recognition, clustering, visual tracking, and motion grouping and segmentation. The increased popularity of matrix manifolds is due partly to the need to characterize image features in non-Euclidean spaces. Matrix manifolds provide rigorous formulations allowing patterns to be naturally expressed and classified in a particular parameter space. This paper gives an overview of common matrix manifolds employed in computer vision and presents a summary of related applications. Researchers in computer vision should find this survey beneficial due to the overview of matrix manifolds, the discussion as well as the collective references.

Grassmann Registration Manifolds for Face Recognition

Motivated by image perturbation and the geometry of manifolds, we present a novel method combining these two elements. First, we form a tangent space from a set of perturbed images and observe that the tangent space admits a vector space structure. Second, we embed the approximated tangent spaces on a Grassmann manifold and employ a chordal distance as the means for comparing subspaces. The matching process is accelerated using a coarse to fine strategy. Experiments on the FERET database suggest that the proposed method yields excellent results using both holistic and local features. Specifically, on the FERET Dup2 data set, our proposed method achieves 83.8% rank 1 recognition: to our knowledge the currently the best result among all non-trained methods. Evidence is also presented that peak recognition performance is achieved using roughly 100 distinct perturbed images.

A meta-analysis of face recognition covariates

This paper presents a meta-analysis for covariates that affect performance of face recognition algorithms. Our review of the literature found six covariates for which multiple studies reported effects on face recognition performance. These are: age of the person, elapsed time between images, gender of the person, the persons expression, the resolution of the face images, and the race of the person. The results presented are drawn from 25 studies conducted over the past 12 years. There is near complete agreement between all of the studies that older people are easier to recognize than younger people, and recognition performance begins to degrade when images are taken more than a year apart. While individual studies find men or women easier to recognize, there is no consistent gender effect. There is universal agreement that changing expression hurts recognition performance. If forced to compare different expressions, there is still insufficient evidence to conclude that any particular expression is better than another. Higher resolution images improve performance for many modern algorithms. Finally, given the studies summarized here, no clear conclusions can be drawn about whether one racial group is harder or easier to recognize than another.

Focus on quality, predicting FRVT 2006 performance

This paper summarizes a study carried out on data from the Face Recognition Vendor Test 2006 (FRVT 2006). The finding of greatest practical importance is the discovery of a strong connection between a relatively simple measure of image quality and performance of state-of-the-art vendor algorithms in FRVT 2006. The image quality measure quantifies edge density and likely relates to focus. This effect is part of a larger four-way interaction observed between edge density, face size and whether images are acquired indoors our outdoors. This finding illustrates the broader potential for statistical modeling of empirical data to play an important role in finding and codifying biometric quality measures.

Tangent bundle for human action recognition

Common human actions are instantly recognizable by people and increasingly machines need to understand this language if they are to engage smoothly with people. Here we introduce a new method for automated human action recognition. The proposed method represents videos as a tangent bundle on a Grassmann manifold. Videos are expressed as third order tensors and factorized to a set of tangent spaces. Tangent vectors are then computed between elements on a Grassmann manifold and exploited for action classification. In particular, logarithmic mapping is applied to map a point from the manifold to tangent vectors centered at a given element. The canonical metric is used to induce the intrinsic distance for a set of tangent spaces. Empirical results show that our method is effective on both uniform and non-uniform backgrounds for action classification. We achieve recognition rates of 91% on the Cambridge gesture dataset, 88% on the UCF sport dataset, and 97% on the KTH human action dataset. Additionally, our method does not require prior training.