Pose-Invariant Face Recognition Using Real and Virtual Views

The problem of automatic face recognition is to visually identify a person in an input image. This task is performed by matching the input face against the faces of known people in a database of faces. Most existing work in face recognition has limited the scope of the problem, however, by dealing primarily with frontal views, neutral expressions, and fixed lighting conditions. To help generalize existing face recognition systems, we look at the problem of recognizing faces under a range of viewpoints. In particular, we consider two cases of this problem: (i) many example views are available of each person, and (ii) only one view is available per person, perhaps a driver's license or passport photograph. Ideally, we would like to address these two cases using a simple view-based approach, where a person is represented in the database by using a number of views on the viewing sphere. While the view-based approach is consistent with case (i), for case (ii) we need to augment the single real view of each person with synthetic views from other viewpoints, views we call 'virtual views'. Virtual views are generated using prior knowledge of face rotation, knowledge that is 'learned' from images of prototype faces. This prior knowledge is used to effectively rotate in depth the single real view available of each person. In this thesis, I present the view-based face recognizer, techniques for synthesizing virtual views, and experimental results using real and virtual views in the recognizer.

Fast Learning VIEWNET Architectures for Recognizing 3-D Objects from Multiple 2-D Views

The recognition of 3-D objects from sequences of their 2-D views is modeled by a family of self-organizing neural architectures, called VIEWNET, that use View Information Encoded With NETworks. VIEWNET incorporates a preprocessor that generates a compressed but 2-D invariant representation of an image, a supervised incremental learning system that classifies the preprocessed representations into 2-D view categories whose outputs arc combined into 3-D invariant object categories, and a working memory that makes a 3-D object prediction by accumulating evidence from 3-D object category nodes as multiple 2-D views are experienced. The simplest VIEWNET achieves high recognition scores without the need to explicitly code the temporal order of 2-D views in working memory. Working memories are also discussed that save memory resources by implicitly coding temporal order in terms of the relative activity of 2-D view category nodes, rather than as explicit 2-D view transitions. Variants of the VIEWNET architecture may also be used for scene understanding by using a preprocessor and classifier that can determine both What objects are in a scene and Where they are located. The present VIEWNET preprocessor includes the CORT-X 2 filter, which discounts the illuminant, regularizes and completes figural boundaries, and suppresses image noise. This boundary segmentation is rendered invariant under 2-D translation, rotation, and dilation by use of a log-polar transform. The invariant spectra undergo Gaussian coarse coding to further reduce noise and 3-D foreshortening effects, and to increase generalization. These compressed codes are input into the classifier, a supervised learning system based on the fuzzy ARTMAP algorithm. Fuzzy ARTMAP learns 2-D view categories that are invariant under 2-D image translation, rotation, and dilation as well as 3-D image transformations that do not cause a predictive error. Evidence from sequence of 2-D view categories converges at 3-D object nodes that generate a response invariant under changes of 2-D view. These 3-D object nodes input to a working memory that accumulates evidence over time to improve object recognition. ln the simplest working memory, each occurrence (nonoccurrence) of a 2-D view category increases (decreases) the corresponding node's activity in working memory. The maximally active node is used to predict the 3-D object. Recognition is studied with noisy and clean image using slow and fast learning. Slow learning at the fuzzy ARTMAP map field is adapted to learn the conditional probability of the 3-D object given the selected 2-D view category. VIEWNET is demonstrated on an MIT Lincoln Laboratory database of l28x128 2-D views of aircraft with and without additive noise. A recognition rate of up to 90% is achieved with one 2-D view and of up to 98.5% correct with three 2-D views. The properties of 2-D view and 3-D object category nodes are compared with those of cells in monkey inferotemporal cortex.

View-Based Strategies for 3D Object Recognition

A persistent issue of debate in the area of 3D object recognition concerns the nature of the experientially acquired object models in the primate visual system. One prominent proposal in this regard has expounded the use of object centered models, such as representations of the objects' 3D structures in a coordinate frame independent of the viewing parameters [Marr and Nishihara, 1978]. In contrast to this is another proposal which suggests that the viewing parameters encountered during the learning phase might be inextricably linked to subsequent performance on a recognition task [Tarr and Pinker, 1989; Poggio and Edelman, 1990]. The 'object model', according to this idea, is simply a collection of the sample views encountered during training. Given that object centered recognition strategies have the attractive feature of leading to viewpoint independence, they have garnered much of the research effort in the field of computational vision. Furthermore, since human recognition performance seems remarkably robust in the face of imaging variations [Ellis et al., 1989], it has often been implicitly assumed that the visual system employs an object centered strategy. In the present study we examine this assumption more closely. Our experimental results with a class of novel 3D structures strongly suggest the use of a view-based strategy by the human visual system even when it has the opportunity of constructing and using object-centered models. In fact, for our chosen class of objects, the results seem to support a stronger claim: 3D object recognition is 2D view-based.

High throughput profile-profile based fold recognition for the entire human proteome

BACKGROUND: In order to maintain the most comprehensive structural annotation databases we must carry out regular updates for each proteome using the latest profile-profile fold recognition methods. The ability to carry out these updates on demand is necessary to keep pace with the regular updates of sequence and structure databases. Providing the highest quality structural models requires the most intensive profile-profile fold recognition methods running with the very latest available sequence databases and fold libraries. However, running these methods on such a regular basis for every sequenced proteome requires large amounts of processing power.In this paper we describe and benchmark the JYDE (Job Yield Distribution Environment) system, which is a meta-scheduler designed to work above cluster schedulers, such as Sun Grid Engine (SGE) or Condor. We demonstrate the ability of JYDE to distribute the load of genomic-scale fold recognition across multiple independent Grid domains. We use the most recent profile-profile version of our mGenTHREADER software in order to annotate the latest version of the Human proteome against the latest sequence and structure databases in as short a time as possible. RESULTS: We show that our JYDE system is able to scale to large numbers of intensive fold recognition jobs running across several independent computer clusters. Using our JYDE system we have been able to annotate 99.9% of the protein sequences within the Human proteome in less than 24 hours, by harnessing over 500 CPUs from 3 independent Grid domains. CONCLUSION: This study clearly demonstrates the feasibility of carrying out on demand high quality structural annotations for the proteomes of major eukaryotic organisms. Specifically, we have shown that it is now possible to provide complete regular updates of profile-profile based fold recognition models for entire eukaryotic proteomes, through the use of Grid middleware such as JYDE.

Reverberant auditory environments: the effects of multiple echoes on distraction by 'irrelevant' speech

Two experiments examine the effect on an immediate recall test of simulating a reverberant auditory environment in which auditory distracters in the form of speech are played to the participants (the 'irrelevant sound effect'). An echo-intensive environment simulated by the addition of reverberation to the speech reduced the extent of 'changes in state' in the irrelevant speech stream by smoothing the profile of the waveform. In both experiments, the reverberant auditory environment produced significantly smaller irrelevant sound distraction effects than an echo-free environment. Results are interpreted in terms of changing-state hypothesis, which states that acoustic content of irrelevant sound, rather than phonology or semantics, determines the extent of the irrelevant sound effect (ISE). Copyright (C) 2007 John Wiley & Sons, Ltd.

Our foreign relations : showing present perils from England and France, the nature and conditions of intervention by mediation, and also by recognition, the impossibility of any recognition of a new power with slavery as a corner-stone, and the wrongful concession of ocean belligerency. Speech of Hon. Charles Sumner, before the citizens of New York, at the Cooper Institute, Sept. 10, 1863.

Mode of access: Internet.

3D ellipsoid fitting for multi-view gait recognition

Gait recognition approaches continue to struggle with challenges including view-invariance, low-resolution data, robustness to unconstrained environments, and fluctuating gait patterns due to subjects carrying goods or wearing different clothes. Although computationally expensive, model based techniques offer promise over appearance based techniques for these challenges as they gather gait features and interpret gait dynamics in skeleton form. In this paper, we propose a fast 3D ellipsoidal-based gait recognition algorithm using a 3D voxel model derived from multi-view silhouette images. This approach directly solves the limitations of view dependency and self-occlusion in existing ellipse fitting model-based approaches. Voxel models are segmented into four components (left and right legs, above and below the knee), and ellipsoids are fitted to each region using eigenvalue decomposition. Features derived from the ellipsoid parameters are modeled using a Fourier representation to retain the temporal dynamic pattern for classification. We demonstrate the proposed approach using the CMU MoBo database and show that an improvement of 15-20% can be achieved over a 2D ellipse fitting baseline.

Gait energy volumes and frontal gait recognition using depth images

Gait energy images (GEIs) and its variants form the basis of many recent appearance-based gait recognition systems. The GEI combines good recognition performance with a simple implementation, though it suffers problems inherent to appearance-based approaches, such as being highly view dependent. In this paper, we extend the concept of the GEI to 3D, to create what we call the gait energy volume, or GEV. A basic GEV implementation is tested on the CMU MoBo database, showing improvements over both the GEI baseline and a fused multi-view GEI approach. We also demonstrate the efficacy of this approach on partial volume reconstructions created from frontal depth images, which can be more practically acquired, for example, in biometric portals implemented with stereo cameras, or other depth acquisition systems. Experiments on frontal depth images are evaluated on an in-house developed database captured using the Microsoft Kinect, and demonstrate the validity of the proposed approach.

Semantic context and visual feature effects in object naming : an fMRI study using arterial spin labeling

Previous behavioral studies reported a robust effect of increased naming latencies when objects to be named were blocked within semantic category, compared to items blocked between category. This semantic context effect has been attributed to various mechanisms including inhibition or excitation of lexico-semantic representations and incremental learning of associations between semantic features and names, and is hypothesized to increase demands on verbal self-monitoring during speech production. Objects within categories also share many visual structural features, introducing a potential confound when interpreting the level at which the context effect might occur. Consistent with previous findings, we report a significant increase in response latencies when naming categorically related objects within blocks, an effect associated with increased perfusion fMRI signal bilaterally in the hippocampus and in the left middle to posterior superior temporal cortex. No perfusion changes were observed in the middle section of the left middle temporal cortex, a region associated with retrieval of lexical-semantic information in previous object naming studies. Although a manipulation of visual feature similarity did not influence naming latencies, we observed perfusion increases in the perirhinal cortex for naming objects with similar visual features that interacted with the semantic context in which objects were named. These results provide support for the view that the semantic context effect in object naming occurs due to an incremental learning mechanism, and involves increased demands on verbal self-monitoring.

The activity view of inner speech

We distinguish two general approaches to inner speech (IS) the "format" and the "activity" views and defend the activity view. The format view grounds the utility of IS on features of the representational format of language, and is related to the thesis that the proper function of IS is to make conscious thinking possible. IS appears typically as a product constituted by representations of phonological features. The view also has implications for the idea that passivity phenomena in cognition may be misat-tributed IS. The activity view sees IS as a speaking activity that does not have a proper function in cognition. It simply inherits the array of functions of outer speech. We argue that it is methodologically advisable to start from this variety of uses, which suggests commonalities between internal and external activities. The format view has several problems; it has to deny "unsymbolized thinking"; it cannot easily explain how IS makes thoughts available to consciousness, and it cannot explain those uses of IS where its format features apparently play no role. The activity view not only lacks these problems but also has explanatory advantages: construing IS as an activity allows it to be integrally constituted by its content; the view is able to construe unsymbolized thinking as part of a continuum of phenomena that exploit the same mechanisms, and it offers a simple explanation for the variety of uses of IS

MCBoost: Multiple classifier boosting for perceptual co-clustering of images and visual features

We present a new co-clustering problem of images and visual features. The problem involves a set of non-object images in addition to a set of object images and features to be co-clustered. Co-clustering is performed in a way that maximises discrimination of object images from non-object images, thus emphasizing discriminative features. This provides a way of obtaining perceptual joint-clusters of object images and features. We tackle the problem by simultaneously boosting multiple strong classifiers which compete for images by their expertise. Each boosting classifier is an aggregation of weak-learners, i.e. simple visual features. The obtained classifiers are useful for object detection tasks which exhibit multimodalities, e.g. multi-category and multi-view object detection tasks. Experiments on a set of pedestrian images and a face data set demonstrate that the method yields intuitive image clusters with associated features and is much superior to conventional boosting classifiers in object detection tasks.

Expressive visual text-to-speech using active appearance models

This paper presents a complete system for expressive visual text-to-speech (VTTS), which is capable of producing expressive output, in the form of a 'talking head', given an input text and a set of continuous expression weights. The face is modeled using an active appearance model (AAM), and several extensions are proposed which make it more applicable to the task of VTTS. The model allows for normalization with respect to both pose and blink state which significantly reduces artifacts in the resulting synthesized sequences. We demonstrate quantitative improvements in terms of reconstruction error over a million frames, as well as in large-scale user studies, comparing the output of different systems. © 2013 IEEE.

Synchronization of user-generated videos through trajectory correspondence and a refinement procedure

Temporal synchronization of multiple video recordings of the same dynamic event is a critical task in many computer vision applications e.g. novel view synthesis and 3D reconstruction. Typically this information is implied through the time-stamp information embedded in the video streams. User-generated videos shot using consumer grade equipment do not contain this information; hence, there is a need to temporally synchronize signals using the visual information itself. Previous work in this area has either assumed good quality data with relatively simple dynamic content or the availability of precise camera geometry. Our first contribution is a synchronization technique which tries to establish correspondence between feature trajectories across views in a novel way, and specifically targets the kind of complex content found in consumer generated sports recordings, without assuming precise knowledge of fundamental matrices or homographies. We evaluate performance using a number of real video recordings and show that our method is able to synchronize to within 1 sec, which is significantly better than previous approaches. Our second contribution is a robust and unsupervised view-invariant activity recognition descriptor that exploits recurrence plot theory on spatial tiles. The descriptor is individually shown to better characterize the activities from different views under occlusions than state-of-the-art approaches. We combine this descriptor with our proposed synchronization method and show that it can further refine the synchronization index. © 2013 ACM.

A Self-Organizing Multiple-View Representation of 3D Objects

We explore representation of 3D objects in which several distinct 2D views are stored for each object. We demonstrate the ability of a two-layer network of thresholded summation units to support such representations. Using unsupervised Hebbian relaxation, we trained the network to recognise ten objects from different viewpoints. The training process led to the emergence of compact representations of the specific input views. When tested on novel views of the same objects, the network exhibited a substantial generalisation capability. In simulated psychophysical experiments, the network's behavior was qualitatively similar to that of human subjects.

Algebraic Functions For Recognition

In the general case, a trilinear relationship between three perspective views is shown to exist. The trilinearity result is shown to be of much practical use in visual recognition by alignment --- yielding a direct method that cuts through the computations of camera transformation, scene structure and epipolar geometry. The proof of the central result may be of further interest as it demonstrates certain regularities across homographies of the plane and introduces new view invariants. Experiments on simulated and real image data were conducted, including a comparative analysis with epipolar intersection and the linear combination methods, with results indicating a greater degree of robustness in practice and a higher level of performance in re-projection tasks.