Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

Most automatic expression analysis systems attempt to recognize a small set of prototypic expressions, such as happiness, anger, surprise, and fear. Such prototypic expressions, however, occur rather infrequently. Human emotions and intentions are more often communicated by changes in one or a few discrete facial features. In this paper, we develop an automatic face analysis (AFA) system to analyze facial expressions based on both permanent facial features (brows, eyes, mouth) and transient facial features (deepening of facial furrows) in a nearly frontal-view face image sequence. The AFA system recognizes fine-grained changes in facial expression into action units (AU) of the Facial Action Coding System (FACS), instead of a few prototypic expressions. Multistate face and facial component models are proposed for tracking and modeling the various facial features, including lips, eyes, brows, cheeks, and furrows. During tracking, detailed parametric descriptions of the facial features are extracted. With these parameters as the inputs, a group of action units (neutral expression, six upper face AU and 10 lower face AU) are recognized whether they occur alone or in combinations. The system has achieved average recognition rates of 96.4 percent (95.4 percent if neutral expressions are excluded) for upper face AU and 96.7 percent (95.6 percent with neutral expressions excluded) for lower face AU. The generalizability of the system has been tested by using independent image databases collected and FACS-coded for ground-truth by different research teams.

/pdf/recognizing-action-units-for-facial-expression-analysis-30323i9nup.pdf

Recognizing action units for facial expression analysis

We prove that the set of all Lambertian reflectance functions (the mapping from surface normals to intensities) obtained with arbitrary distant light sources lies close to a 9D linear subspace. This implies that, in general, the set of images of a convex Lambertian object obtained under a wide variety of lighting conditions can be approximated accurately by a low-dimensional linear subspace, explaining prior empirical results. We also provide a simple analytic characterization of this linear space. We obtain these results by representing lighting using spherical harmonics and describing the effects of Lambertian materials as the analog of a convolution. These results allow us to construct algorithms for object recognition based on linear methods as well as algorithms that use convex optimization to enforce nonnegative lighting functions. We also show a simple way to enforce nonnegative lighting when the images of an object lie near a 4D linear space. We apply these algorithms to perform face recognition by finding the 3D model that best matches a 2D query image.

/pdf/lambertian-reflectance-and-linear-subspaces-k79c4cysdg.pdf

Lambertian reflectance and linear subspaces

A method of maintaining digital medical records, comprising a step of receiving a medical transaction record (102), encrypted with a key in accordance with a patient-file association. Also comprising a step of accessing the encrypted medical transaction record according to a patient association with the record (111). And further comprising a step of re-encryption of the encrypted accessed medical transaction record with a key associated with an intended recipient of the medical record. The system and method according to the present invention presents a new business model for creation, maintenance, transmission, and use of medical records. The invention also allows financial burdens to be reallocated optimally and equitably, resulting in decreased overall societal cost and providing a successful business model for a database proprietor. Secure entrusted medical records are held in trust by an independent third party on behalf of the patient (113), and serve the medical community at large. Separately encrypted record elements may be aggregated as an information polymer.

Information record infrastructure, system and method

Recognizing faces in unconstrained videos is a task of mounting importance. While obviously related to face recognition in still images, it has its own unique characteristics and algorithmic requirements. Over the years several methods have been suggested for this problem, and a few benchmark data sets have been assembled to facilitate its study. However, there is a sizable gap between the actual application needs and the current state of the art. In this paper we make the following contributions. (a) We present a comprehensive database of labeled videos of faces in challenging, uncontrolled conditions (i.e., ‘in the wild’), the ‘YouTube Faces’ database, along with benchmark, pair-matching tests1. (b) We employ our benchmark to survey and compare the performance of a large variety of existing video face recognition techniques. Finally, (c) we describe a novel set-to-set similarity measure, the Matched Background Similarity (MBGS). This similarity is shown to considerably improve performance on the benchmark tests.

/pdf/face-recognition-in-unconstrained-videos-with-matched-3tbbtju4in.pdf

Face recognition in unconstrained videos with matched background similarity

We present a face recognition method using image sequence. As input we utilize plural face images rather than a "single-shot", so that the input reflects variation of facial expression and face direction. For the identification of the face, we essentially form a subspace with the image sequence and apply the Mutual Subspace Method in which the similarity is defined by the angle between the subspace of input and those of references. We demonstrate the effectiveness of the proposed method through several experimental results.

Face recognition using temporal image sequence

This paper introduces a novel approach for face recognition using multiple face patterns obtained in various views for robot vision. A face pattern may change dramatically due to changes in the relation between the positions of a robot, a subject and light sources. As a robot is not generally able to ascertain such changes by itself, face recognition in robot vision must be robust against variations caused by the changes. Conventional methods using a single face pattern are not capable of dealing with the variations of face pattern. In order to overcome the problem, we have developed a face recognition method based on the constrained mutual subspace method (CMSM) using multi-viewpoint face patterns attributable to the movement of a robot or a subject. The effectiveness of our method for robot vision is demonstrated by means of a preliminary experiment.

/pdf/face-recognition-using-multi-viewpoint-patterns-for-robot-2kc5a83if8.pdf

Face Recognition Using Multi-viewpoint Patterns for Robot Vision

In this paper, we propose a new image feature based on spatial co-occurrence among micropatterns, where each micropattern is represented by a Local Binary Pattern (LBP). In conventional LBP-based features such as LBP histograms, all the LBPs of micropatterns in the image are packed into a single histogram. Doing so discards important information concerning spatial relations among the LBPs, even though they may contain information about the image's global structure. To consider such spatial relations, we measure their co-occurrence among multiple LBPs. The proposed feature is robust against variations in illumination, a feature inherited from the original LBP, and simultaneously retains more detail of image. The significant advantage of the proposed method versus conventional LBP-based features is demonstrated through experimental results of face and texture recognition using public databases.

/pdf/feature-extraction-based-on-co-occurrence-of-adjacent-local-1hv31uqqmr.pdf

Feature extraction based on co-occurrence of adjacent local binary patterns

An input unit for controlling a device. The input unit first determines whether a user is actively operating the device. If such a detection is made, the input unit then determines whether the user performs an act that corresponds to a command. User attention may be indicated by a user observing the device, approaching the device, facing the device, or speaking. An input command may be indicated by touch, gesture, speech, or line of sight.

Apparatus and method for controlling an electronic device with user action

In a person identification apparatus, a normalized face image is used to identify a person. When the face image of the person is input, a face area extraction section extracts the face area from the face image. A feature point extraction section extracts a plurality of candidates of feature points from the face area using a separation filter. A feature point set selection section selects sets of the candidates from the plurality of candidates of feature points according to face structure information. A feature point decision section extracts neighboring patterns of each candidate from the face area for the set of candidates, calculates a similarity value between the neighboring patterns of each candidate and the template pattern, and selects a subset of the candidates having the highest similarity values. A normalization section generates a normalized face image of the face area according to the selected subset of the candidates. A recognition section compares the normalized face image with the registered image to identify the person.

Kazuhiro Fukui

Papers

Face recognition using temporal image sequence

Face Recognition Using Multi-viewpoint Patterns for Robot Vision

Feature extraction based on co-occurrence of adjacent local binary patterns

Apparatus and method for controlling an electronic device with user action

Person identification apparatus and method using concentric templates and feature point candidates