This thesis describes a representation of gait appearance for the purpose of person identification and classification. This gait representation is based on simple localized image features such as moments extracted from orthogonal view video silhouettes of human walking motion. A suite of time-integration methods, spanning a range of coarseness of time aggregation and modeling of feature distributions, are applied to these image features to create a suite of gait sequence representations. Despite their simplicity, the resulting feature vectors contain enough information to perform well on human identification and gender classification tasks. We demonstrate the accuracy of recognition on gait video sequences collected over different days and times and under varying lighting environments. Each of the integration methods are investigated for their advantages and disadvantages. An improved gait representation is built based on our experiences with the initial set of gait representations. In addition, we show gender classification results using our gait appearance features, the effect of our heuristic feature selection method, and the significance of individual features.

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.

Poggio and Vetter (1992) showed that learning one view of a bilaterally symmetric object could be sufficient for its recognition, if this view allows the computation of a symmetric, "virtual," view. Faces are roughly bilaterally symmetric objects. Learning a side-view--which always has a symmetric view--should allow for better generalization performances than learning the frontal view. Two psychophysical experiments tested these predictions. Stimuli were views of shaded 3D models of laser-scanned faces. The first experiment tested whether a particular view of a face was canonical. The second experiment tested which single views of a face give rise to best generalization performances. The results were compatible with the symmetry hypothesis: Learning a side view allowed better generalization performances than learning the frontal view.

Thesis (Ph.D)--Stanford University, 1999. / Title from pdf t.p. (viewed May 9, 2002). "May 1999." "Adminitrivia V1/Prg/19990528"--Metadata.

Thesis (Ph. D.)--Ohio State University, 2006. / Title from first page of PDF file. Includes bibliographical references (p. 147-155).

Thesis (Ph. D.)--University of Nevada, Reno, 2005. / "August, 2005." Includes bibliographical references (leaves 61-67). Online version available on the World Wide Web. Library also has microfilm. Ann Arbor, Mich. : ProQuest Information and Learning Company, [2005]. 1 microfilm reel ; 35 mm.

This study was about disability organisations opinion concerning ICF: s importance in their work to receive the same recognition and human rights for their members as citizens. The aim has been to elucidate disability organisations awareness about and use/non use of ICF and to increase the understanding of ICF: s importance for recognition and redistribution. Three different methods have been used: literature study, questionnaire survey, both on counties' (27) - and national (26) level and interviews (5) on national level. There is also a distinct difference between the disability organisations that represents people with visible impairments, who don’t think that ICF is so useful and they that represent people with invisible impairments, who thinks that ICF is a useful tool. This difference exists both in the use of ICF and the classifications importance for recognition but not ICF: s importance for redistribution. The main conclusion of the study is that awareness about and education around ICF is needed among disability organisations. A restructuring of ICF is also needed, the language should be simplified and the codes should be faded down so that the focus will be on ICF: s intention and the mind map that the classification offers. This is also necessary so that ICF becomes accessible for everybody.

Given an unstructured collection of captioned images of cluttered scenes featuring a variety of objects, our goal is to simultaneously learn the names and appearances of the objects. Only a small fraction of local features within any given image are associated with a particular caption word, and captions may contain irrelevant words not associated with any image object. We propose a novel algorithm that uses the repetition of feature neighborhoods across training images and a measure of correspondence with caption words to learn meaningful feature configurations (representing named objects). We also introduce a graph-based appearance model that captures some of the structure of an object by encoding the spatial relationships among the local visual features. In an iterative procedure we use language (the words) to drive a perceptual grouping process that assembles an appearance model for a named object. We also exploit co-occurrences among appearance models to learn hierarchical appearance models. Results of applying our method to three data sets in a variety of conditions demonstrate that from complex, cluttered, real-world scenes with noisy captions, we can learn both the names and appearances of objects, resulting in a set of models invariant to translation, scale, orientation, occlusion, and minor changes in viewpoint or articulation. These named models, in turn, are used to automatically annotate new, uncaptioned images, thereby facilitating keyword-based image retrieval.

The current study introduced a new measure for the study of naturalistic memory, which involved the use of a homogeneous, controlled event for all participants. We tested participants’ memory for this so-called staged event with both the Autobiographical Interview (AI) and our novel receiver operating characteristic (ROC) task. Statistical analyses indicated that scores on the AI and on our new ROC measure showed time sensitivity consistent with the literature. These data were difficult to interpret, however, because of a confound of age. We will need to age-match our groups before drawing any major conclusions. That said, we found a significant positive correlation between measures of recollection on both the AI and ROC task, which was a promising finding in terms of validating the new measure against an established procedure. Overall, our results suggest that assessing recall and recognition for a staged event is a viable method for studying naturalistic memory.

The current study introduced a new measure for the study of naturalistic memory, which involved the use of a homogeneous, controlled event for all participants. We tested participants’ memory for this so-called staged event with both the Autobiographical Interview (AI) and our novel receiver operating characteristic (ROC) task. Statistical analyses indicated that scores on the AI and on our new ROC measure showed time sensitivity consistent with the literature. These data were difficult to interpret, however, because of a confound of age. We will need to age-match our groups before drawing any major conclusions. That said, we found a significant positive correlation between measures of recollection on both the AI and ROC task, which was a promising finding in terms of validating the new measure against an established procedure. Overall, our results suggest that assessing recall and recognition for a staged event is a viable method for studying naturalistic memory.