Showing papers by "Ioannis Pitas published in 2003"

Asymptotically optimal detection for additive watermarking in the DCT and DWT domains

Abstract: Most of the watermarking schemes that have been proposed until now employ a correlation detector (matched filter). The current paper proposes a new detector scheme that can be applied in the case of additive watermarking in the DCT (discrete cosine transform) or DWT (discrete wavelet transform) domain. Certain properties of the probability density function of the coefficients in these domains are exploited. Thus, an asymptotically optimal detector is constructed based on well known results of the detection theory. Experimental results prove the superiority of the proposed detector over the correlation detector.

ICA and Gabor representation for facial expression recognition

Abstract: Two hybrid systems for classifying seven categories of human facial expression are proposed The first system combines independent component analysis (ICA) and support vector machines (SVMs) The original face image database is decomposed into linear combinations of several basis images, where the corresponding coefficients of these combinations are fed up into SVMs instead of an original feature vector comprised of grayscale image pixel values The classification accuracy of this system is compared against that of baseline techniques that combine ICA with either two-class cosine similarity classifiers or two-class maximum correlation classifiers, when we classify facial expressions into these seven classes We found that, ICA decomposition combined with SVMs outperforms the aforementioned baseline classifiers The second system proposed operates in two steps: first, a set of Gabor wavelets (GWs) is applied to the original face image database and, second, the new features obtained are classified by using either SVMs or cosine similarity classifiers or maximum correlation classifier The best facial expression recognition rate is achieved when Gabor wavelets are combined with SVMs

Video shot segmentation using singular value decomposition

Abstract: A new method for detecting shot boundaries in video sequences using singular value decomposition (SVD) is proposed. The method relies on performing singular value decomposition on the matrix A created from 3D histograms of single frames. We have used SVD for its capabilities to derive a low dimensional refined feature space from a high dimensional raw feature space, where pattern similarity can easily be detected. The method can detect cuts and gradual transitions, such as dissolves and fades, which cannot be detected easily by entropy measures.

Watermarking of 3D models using principal component analysis

Abstract: A novel method for 3D model watermarking, robust to geometric distortions such as rotation, translation and scaling, is proposed. A ternary watermark is embedded in the vertex topology of a 3D model. A transformation of the model to an invariant space is proposed prior to watermark embedding. Simulation results indicate the ability of the proposed method to deal with the aforementioned attacks giving very good results.

Performance analysis of correlation-based watermarking schemes employing Markov chaotic sequences

Abstract: In this paper, theoretical performance analysis of watermarking schemes based on correlation detection is undertaken, leading to a number of important observations on the watermarking system detection performance. Statistical properties of watermark sequences generated by piecewise-linear Markov maps are investigated. Correlation/spectral properties of such sequences are easily controllable, which is a fact that reflects on the watermarking system performance. A family of chaotic maps, namely the skew tent map family, is used to verify the theoretical analysis. Skew tent chaotic sequences are compared against the widely used pseudorandom sequences, indicating the superiority of the former in watermarking applications. The minimum number of samples required for reliable watermark detection is also investigated. Experiments using audio data are conducted to verify the theoretical analysis results.

Markov chaotic sequences for correlation based watermarking schemes

Abstract: In this paper, statistical analysis of watermarking schemes based on correlation detection is presented. Statistical properties of watermark sequences generated by piecewise-linear Markov maps are exploited, resulting in superior watermark detection reliability. Correlation/spectral properties of such sequences are easily controllable, a fact that affects the watermarking system performance. A family of chaotic maps, namely the skew tent map family, is proposed for use in watermarking schemes.

Reconstruction of serially acquired slices using physics-based modeling

Abstract: This paper presents an accurate, computationally efficient, fast, and fully automated algorithm for the alignment of two-dimensional (2-D) serially acquired sections forming a 3-D volume. The approach relies on the determination of interslice correspondences. The features used for correspondence are extracted by a 2-D physics-based deformable model parameterizing the object shape. Correspondence affinities and global constrains render the method efficient and reliable. The method accounts for one of the major shortcomings of 2-D slices alignment of a 3-D volume, namely variable and nonuniform thickness of the slices. Moreover, no particular alignment direction is privileged, avoiding global offsets, biases, and error propagation. The method was evaluated on real images and the experimental results demonstrated its accuracy, as reconstruction errors were smaller than I degree in rotation and smaller than 1 pixel in translation.

A global energy function for the alignment of serially acquired slices

Abstract: An accurate, computationally efficient, and fully automated algorithm for the alignment of two-dimensional (2-D) serially acquired sections forming a three-dimensional (3-D) volume is presented. The approach relies on the optimization of a global energy function, based on the object shape, measuring the similarity between a slice and its neighborhood in the 3-D volume. Slice similarity is computed using the distance transform measure in both directions. No particular direction is privileged in the method avoiding global offsets, biases in the estimation and error propagation. The method was evaluated on real images [medical, biological, and other computerized tomography (CT) scanned 3-D data] and the experimental results demonstrated its accuracy as reconstuction errors are less than one degree in rotation and less than one pixel in translation.

Robust multibit audio watermarking in the temporal domain

Abstract: In this paper, a technique for temporal embedding of a multibit watermark on an audio signal is proposed. The method is based on generating a chaotic sequence which is used for modifying the audio samples. A chaotic sequence generates the watermark, while the parameters of the embedding procedure are chosen so as to minimize the perceivable distortion of the initial signal, while preserving the power of the watermark at a detectable level. The watermark is resistant to lowpass manipulation attacks, such as filtering or compression, and cropping attacks as well.

A mutual information approach to articulated object tracking

Abstract: A mutual information based articulated object tracking scheme is proposed in this paper Articulation constraints are introduced using a kinematic model Further constraints are introduced based on the human joint anatomy and flexibility The tracking scheme is enhanced by using the tracked object texture map image The tracking history is incorporated in the tracking scheme by using a temporal model or a Kalman filtering scheme The Kalman filtering scheme greatly enhances the tracking scheme provided the suitable initial conditions are set The resulting system was tested on arm and finger tracking cases using real image sequences

Optimal detection for multiplicative watermarks embedded in DFT domain

Abstract: This paper deals with the statistical analysis of the behavior of a blind copyright protection watermarking system based on pseudorandom signals embedded in the magnitude of the Fourier transform of the host data. The host data that the watermark is embedded into is one-dimensional and nonwhite, following a specific model. The analysis performed involves theoretical evaluation of the statistics of the Fourier coefficients and an optimum detector design for multiplicative embedding. It is proved that the widely used correlator is not the optimum detector. Finally, experimental results are presented in order to show the proposed detector's efficiency versus that of the correlator detector.

Improving the detection reliability of correlation-based watermarking techniques

Abstract: The performance of watermarking schemes based on correlation detection is closely related to the frequency characteristics of the watermark sequence. In order to improve both detection reliability and robustness against attacks, embedding of watermarks with high-frequency spectrum, in the low frequencies of the DFT domain, is introduced in this paper and theoretical analysis of correlation based watermarking techniques with multiplicative embedding is performed. The proposed watermarking framework is successfully applied to audio signals, demonstrating its superiority with respect to both robustness and inaudibility. Experiments are conducted, in order to verify the validity of the theoretical analysis results.

CAML – A Universal Configuration Language for Dialogue Systems

Abstract: In this paper, a novel architecture of a universal dialogue system and its configuration language, so-called Conversational Agent Markup Language (CAML), is proposed. The dialogue system embodies a CLIPS engine in order to enable CAML to formulate procedural and heuristic knowledge. CAML supports frames, functions, and categories that enable it: (a) to process wildcards, to control the inner state through variables, and to formulate procedural knowledge in contrast to Phoenix/CAT Dialog Manager; (b) to support nested macros, to control the inner state through variables, to assign priorities and weights to states, and to interface with external databases in contrast to Dialog Management Tool Language (DMTL); (c) to implement context-free grammars, to extract semantic content from user input through frames, to allow numeric variables, and to interface with external databases as opposed to Artificial Intelligence Markup Language (AIML). The proposed system is extensible in the sense that it can be embedded in any conversational system that receives and emits XML content. Such a dialogue system can be incorporated in multimodal interfaces, such as talking head applications, conversational web interfaces, conversational database interfaces, and conversational programming interfaces.

Recognition of facial expressions in presence of partial occlusion

Abstract: Nowadays, both computer vision researchers and psychology experts show an increased interest for human facial expression analysis. Despite the huge amount of research that has been dedicated to this area, almost all of them concern data recorded in controlled laboratory conditions, which does not always reflect the real world environment in which the human face is partially occluded. Six basic facial expressions are investigated in that case, i.e.when the eyes and eyebrows or the mouth regions are left out. We are interested in finding which part of the face comprised sufficient information with respect to the entire face, in order to correctly classify these six expressions. Each image from the two databases used is convolved with a set of Gabor filters having various orientations and frequencies. The new feature vectors are classified using a maximum correlation classifier and the cosine similarity measure approaches. Overall, the method provides robustness against partial occlusion.

Partly-Specified Priority Patterns in Natural Language Parsing within Dialogue Systems

Abstract: In this paper, two essential problems that belong to language parsing and have arisen from dialogue management are discussed and solved by implementing a variant of the well-known context-free parsing algorithm [1]. The first problem is the use of partly specified patterns, i.e., the use of wildcards in the right-hand-sides of the rewriting rules of a context-free grammar. The second one is the use of priority patterns, i.e., the assignment of priority values to rewriting rules. These problems are not handled in the majority of the state-of-the-art dialogue systems. The proposed algorithm has been implemented in a dialogue system core application called CAML Core [7], that is used to implement dialogue systems in several domains like conversational and multimodal interfaces for help desk applications, and chat bots.

Fuzzy Techniques in Digital Image Processing and Shape Analysis

Abstract: In this chapter, an overview of the applications of several fuzzy operators in image processing and analysis is presented. First, the fuzzy location and scale estimators based on the extension principle, are presented. The definitions of the fuzzy nonlinear means, the fuzzy location and scale estimators based on fuzzy order statistics and other fuzzy scale estimators, e.g., fuzzy sample standard deviation, are also given. Equivalent relations that can be used to calculate the fuzzy estimators using classical arithmetic are derived. The Fuzzy Vector Median is defined as an extension of the classical Vector Median, based on a distance definition between fuzzy vectors. An application of Fuzzy Vector Median for filtering images corrupted by mixed Gaussian and impulsive noise is also given.

CAML: A universal configuration language for dialogue systems

Abstract: In this paper, a novel architecture of a universal dialogue system and its configuration language, so-called Conversational Agent Markup Language (CAML), is proposed. The dialogue system embodies a CLIPS engine in order to enable CAML to formulate procedural and heuristic knowledge. CAML supports frames, functions, and categories that enable it: (a) to process wildcards, to control the inner state through variables, and to formulate procedural knowledge in contrast to Phoenix/CAT Dialog Manager; (b) to support nested macros, to control the inner state through variables, to assign priorities and weights to states, and to interface with external databases in contrast to Dialog Management Tool Language (DMTL); (c) to implement context-free grammars, to extract semantic content from user input through frames, to allow numeric variables, and to interface with external databases as opposed to Artificial Intelligence Markup Language (AIML). The proposed system is extensible in the sense that it can be embedded in any conversational system that receives and emits XML content. Such a dialogue system can be incorporated in multimodal interfaces, such as talking head applications, conversational web interfaces, conversational database interfaces, and conversational programming interfaces.

Information theory based face tracking

Abstract: Automatic detection and tracking of human body parts (e.g. face, arms) is a challenging research topic with applications in many domains such as human computer interaction, surveillance, face recognition and human joint audio and video localization systems.