No description available.

No description available.

Visual recognition (e.g., object, scene and action recognition) is an active area of research in computer vision due to its increasing number of real-world applications such as video (image) indexing and search, intelligent surveillance, human-machine interaction, robot navigation, etc. Effective modeling of the objects, scenes and actions is critical for visual recognition. Recently, bag of visual words (BoVW) representation, in which the image patches or video cuboids are quantized into visual words (i.e., mid-level features) based on their appearance similarity using clustering, has been widely and successfully explored. The advantages of this representation are: no explicit detection of objects or object parts and their tracking are required; the representation is somewhat tolerant to within-class deformations, and it is efficient for matching. However, the performance of the BoVW is sensitive to the size of the visual vocabulary. Therefore, computationally expensive cross-validation is needed to find the appropriate quantization granularity. This limitation is partially due to the fact that the visual words are not semantically meaningful. This limits the effectiveness and compactness of the representation. To overcome these shortcomings, in this thesis we present principled approach to learn a semantic vocabulary (i.e. high-level features) from a large amount of visual words (mid-level features). In this context, the thesis makes two major contributions. First, we have developed an algorithm to discover a compact yet discriminative semantic vocabulary. This vocabulary is obtained by grouping the visual-words based on their distribution in videos (images) into visual-word clusters. The mutual information (MI) be- tween the clusters and the videos (images) depicts the discriminative power of the semantic vocabulary, while the MI between visual-words and visual-word clusters measures the compactness of the vocabulary. We apply the information bottleneck (IB) algorithm to find the optimal number of visual-word clusters by finding the good tradeoff between compactness and discriminative power. We tested our proposed approach on the state-of-the-art KTH dataset, and obtained average accuracy of 94.2%. However, this approach performs one-side clustering, because only visual words are clustered regardless of which video they appear in. In order to leverage the co-occurrence of visual words and images, we have developed the co-clustering algorithm to simultaneously group the visual words and images. We tested our approach on the publicly available fifteen scene dataset and have obtained about 4% increase in the average accuracy compared to the one side clustering approaches. Second, instead of grouping the mid-level features, we first embed the features into a low-dimensional semantic space by manifold learning, and then perform the clustering. We apply Diffusion Maps (DM) to capture the local geometric structure of the mid-level feature space. The DM embedding is able to preserve the explicitly defined diffusion distance, which reflects the semantic similarity between any two features. Furthermore, the DM provides multi-scale analysis capability by adjusting the time steps in the Markov transition matrix. The experiments on KTH dataset show that DM can perform much better (about 3% to 6% improvement in average accuracy) than other manifold learning approaches and IB method. Above methods use only single type of features. In order to combine multiple heterogeneous features for visual recognition, we further propose the Fielder Embedding to capture the complicated semantic relationships between all entities (i.e., videos, images,heterogeneous features). The discovered relationships are then employed to further increase the recognition rate. We tested our approach on Weizmann dataset, and achieved about 17% 21% improvements in the average accuracy.

The biggest change in the facial recognition community since the completion of the FacE REcognition Technology (FERET) program has been the introduction of facial recognition products to the commercial market. Open market competitiveness has driven numerous technological advances in automated face recognition since the FERET program and significantly lowered system costs. Today there are dozens of facial recognition systems available that have the potential to meet performance requirements for numerous applications. But which of these systems best meet the performance requirements for given applications? Repeated inquiries from numerous government agencies on the current state of facial recognition technology prompted the DoD Counterdrug Technology Development Program Office to establish a new set of evaluations. The Facial Recognition Vendor Test 2000 (FRVT 2000), was co-sponsored by the DoD Counterdrug Technology Development Program Office, the National Institute of Justice, and the Defense Advanced Research Projects Agency, and was administered in May-June 2000. The sponsors of the FRVT 2000 had two major goals for the evaluation. The first was a technical assessment of the capabilities of commercially available facial recognition systems. The sponsors wanted to know the strengths and weaknesses of each individual system, as well as obtain an understanding of the current state of the art for facial recognition. The second goal of the evaluation was to educate the biometrics community and the general public on how to present and analyze results. The sponsors have seen vendors and would-be customers quoting outstanding performance specifications without understanding that these specifications are virtually useless without first knowing the details of the test that was used to produce the quoted results. The Facial Recognition Vendor Test 2000 was a worthwhile endeavor. It will help numerous readers evaluate facial recognition systems for their own uses and will serve as a benchmark for all future evaluations of biometric technologies. The FRVT 2000 evaluations were not designed, and the FRVT 2000 Evaluation Report was not written, to be a buyer's guide for facial recognition. No one will be able to open the report to a specific page to determine which facial recognition system is best because there is not one system for all applications. The only way to determine the best facial recognition system for any application is to follow the three-step evaluation methodology described in the FRVT 2000 Evaluation Report and analyze the data as it pertains to each individual application. This thesis explains the design and implementation of the FRVT 2000 evaluations, and discusses how the FRVT 2000 Evaluation Report met the author's objectives for the evaluation. / Master of Science

Own Group Recognition Bias (OGRB) is a robust phenomenon defined by being better able to recognize individuals from one's own ethnic group compared to other groups. A number of researchers agree that this bias is a function of perceptual and social contact. The aim of this thesis was to investigate the role of contact in the OGRB, particularly in its social dimension, and to understand more broadly how a set of social and cognitive components can act on face recognition. This work was based on two main approaches. The first was to assess the effects of social and cognitive components on the ability of European observers to recognize European and North-African faces. Specifically, I investigated contact patterns, prejudice, interaction anxiety and visual strategies in the context of the OGRB. To this end, I first created and tested scales to measure aspects of social contact, and prejudice towards North-African individuals. The social contact investigation was of three major sub-components of contact, including contact avoidance. The prejudice scale contained two attitudinal components, with items assessing ethnic prejudice and affective states. Then, I set up an experimental protocol using an eye-tracker and physiological measures to assess the impact of different components such as contact, intergroup anxiety, visual strategies and prejudice on face recognition. The main objective of this first part of the thesis was to determine the multiple interdependent effects between cognitive and social elements on intergroup face recognition abilities. The results of the experimental protocol confirmed the existence of an OGRB in European participants towards North-African individuals; however, the impact of social variables on face recognition was not conclusive. The study of visual strategies, however, showed clearer results. In a second part of my thesis, I addressed the notion of within-group variability and how this component can be integrated with the different elements mentioned above. First, I conducted a systematic review of the notion of 'phenotypicality bias', which is defined as the activation of prejudice based on perceived typicality of an ethnicity. This review highlighted an underdeveloped body of work that challenges the conception of the ethnic group as a homogeneous entity. In a second phase, I tested a set of protocols on the representation and perception of within-group variability for stimuli from African, European and North-African groups. This work allowed me to highlight elements perceived as typical of a given group and to create and validate standardised photographic material with different levels of perceived ethnic typicality. Finally, I manipulated this ethnic typicality in a final experimental face recognition protocol in order to assess its impact on the OGRB. The results of this last study also confirm an OGRB for African and North-African stimuli in a European population. The impact of within-group variability on recognition was relatively clear, especially for ethnic other-group faces.

Own Group Recognition Bias (OGRB) is a robust phenomenon defined by being better able to recognize individuals from one's own ethnic group compared to other groups. A number of researchers agree that this bias is a function of perceptual and social contact. The aim of this thesis was to investigate the role of contact in the OGRB, particularly in its social dimension, and to understand more broadly how a set of social and cognitive components can act on face recognition. This work was based on two main approaches. The first was to assess the effects of social and cognitive components on the ability of European observers to recognize European and North-African faces. Specifically, I investigated contact patterns, prejudice, interaction anxiety and visual strategies in the context of the OGRB. To this end, I first created and tested scales to measure aspects of social contact, and prejudice towards North-African individuals. The social contact investigation was of three major sub-components of contact, including contact avoidance. The prejudice scale contained two attitudinal components, with items assessing ethnic prejudice and affective states. Then, I set up an experimental protocol using an eye-tracker and physiological measures to assess the impact of different components such as contact, intergroup anxiety, visual strategies and prejudice on face recognition. The main objective of this first part of the thesis was to determine the multiple interdependent effects between cognitive and social elements on intergroup face recognition abilities. The results of the experimental protocol confirmed the existence of an OGRB in European participants towards North-African individuals; however, the impact of social variables on face recognition was not conclusive. The study of visual strategies, however, showed clearer results. In a second part of my thesis, I addressed the notion of within-group variability and how this component can be integrated with the different elements mentioned above. First, I conducted a systematic review of the notion of 'phenotypicality bias', which is defined as the activation of prejudice based on perceived typicality of an ethnicity. This review highlighted an underdeveloped body of work that challenges the conception of the ethnic group as a homogeneous entity. In a second phase, I tested a set of protocols on the representation and perception of within-group variability for stimuli from African, European and North-African groups. This work allowed me to highlight elements perceived as typical of a given group and to create and validate standardised photographic material with different levels of perceived ethnic typicality. Finally, I manipulated this ethnic typicality in a final experimental face recognition protocol in order to assess its impact on the OGRB. The results of this last study also confirm an OGRB for African and North-African stimuli in a European population. The impact of within-group variability on recognition was relatively clear, especially for ethnic other-group faces.

No description available.

Spoken language processing is one of the oldest and most natural modes of information exchange between humans beings. For centuries, people have tried to develop machines that can understand and produce speech the way humans do so naturally. The biggest problem in our inability to model speech with computer programs and mathematics results from the fact that language is instinctive, whereas, the vocabulary and dialect used in communication are learned. Human beings are genetically equipped with the ability to learn languages, and culture imprints the vocabulary and dialect on each member of society. This thesis examines the role of pattern classification in the recognition of human speech, i.e., machine learning techniques that are currently being applied to the spoken language processing problem. The primary objective of this thesis is to create a network training paradigm that allows for direct training of multi-path models and alleviates the need for complicated systems and training recipes. A traditional trainer uses an expectation maximization (EM)based supervised training framework to estimate the parameters of a spoken language processing system. EM-based parameter estimation for speech recognition is performed using several complicated stages of iterative reestimation. These stages typically are prone to human error. The network training paradigm reduces the complexity of the training process while retaining the robustness of the EM-based supervised training framework. The hypothesis of this thesis is that the network training paradigm can achieve comparable recognition performance to a traditional trainer while alleviating the need for complicated systems and training recipes for spoken language processing systems.

In this work, nonlinear acoustic information is combined with traditional linear acoustic information in order to produce a noise-robust set of features for speech recognition. Classical acoustic modeling techniques for speech recognition have relied on a standard assumption of linear acoustics where signal processing is primarily performed in the signal's frequency domain. While these conventional techniques have demonstrated good performance under controlled conditions, the performance of these systems suffers significant degradations when the acoustic data is contaminated with previously unseen noise. The objective of this thesis was to determine whether nonlinear dynamic invariants are able to boost speech recognition performance when combined with traditional acoustic features. Several sets of experiments are used to evaluate both clean and noisy speech data. The invariants resulted in a maximum relative increase of 11.1% for the clean evaluation set. However, an average relative decrease of 7.6% was observed for the noise-contaminated evaluation sets. The fact that recognition performance decreased with the use of dynamic invariants suggests that additional research is required for robust filtering of phase spaces constructed from noisy time series.

No description available.