scispace - formally typeset
Search or ask a question

Showing papers by "Ioannis Pitas published in 2002"


Proceedings ArticleDOI
13 May 2002
TL;DR: An overview of voice, fingerprint, and face authentication algorithms is provided for multi-modal authentication in signal processing.
Abstract: Biometrics is an emerging topic in the field of signal processing. While technologies (e.g. audio, video) for biometrics have mostly been studied separately, ultimately, biometric technologies could find their strongest role as interwined and complementary pieces of a multi-modal authentication system. In this paper, a short overview of voice, fingerprint, and face authentication algorithms is provided.

72 citations


Proceedings ArticleDOI
24 Jun 2002
TL;DR: The proposed shot cut detection technique relies on the mutual information and the joint entropy between frames and can detect cuts, fade-ins and fade-outs very effectively.
Abstract: A new method for detecting shot boundaries in video sequences using metrics based on information theory is proposed. The method relies on the mutual information and the joint entropy between frames and can detect cuts, fade-ins and fade-outs. The detection technique was tested on TV video sequences having different types of shots and significant object and camera motion inside the shots. It was favorably compared to other recently proposed shot cut detection techniques. The method is proven to detect both fades and abrupt cuts very effectively.

71 citations


Journal ArticleDOI
TL;DR: An interpolation algorithm using a mathematical morphology morphing approach to reconstruct the n-dimensional object from a group of (n-1)-dimensional sets representing sections of that object, and proves the convergence of the morphological morphing.
Abstract: In this paper, we propose an interpolation algorithm using a mathematical morphology morphing approach. The aim of this algorithm is to reconstruct the n-dimensional object from a group of (n-1)-dimensional sets representing sections of that object. The morphing transformation modifies pairs of consecutive sets such that they approach in shape and size. The interpolated set is achieved when the two consecutive sets are made idempotent by the morphing transformation. We prove the convergence of the morphological morphing. The entire object is modeled by successively interpolating a certain number of intermediary sets between each two consecutive given sets. We apply the interpolation algorithm for three-dimensional tooth reconstruction.

59 citations


Journal ArticleDOI
TL;DR: This paper examines the suitability of support vector machines for visual speech recognition by modeling the temporal character of speech as a temporal sequence of visemes corresponding to the different phones realized in a Viterbi lattice.
Abstract: Visual speech recognition is an emerging research field. In this paper, we examine the suitability of support vector machines for visual speech recognition. Each word is modeled as a temporal sequence of visemes corresponding to the different phones realized. One support vector machine is trained to recognize each viseme and its output is converted to a posterior probability through a sigmoidal mapping. To model the temporal character of speech, the support vector machines are integrated as nodes into a Viterbi lattice. We test the performance of the proposed approach on a small visual speech recognition task, namely the recognition of the first four digits in English. The word recognition rate obtained is at the level of the previous best reported rates.

47 citations


Journal ArticleDOI
TL;DR: Internal root resorption is a rare remodeling process that can be studied using different experimental methods and is shown as a uniform radiolucency.
Abstract: – Aim and methology: Two cases of internal tooth resorption were examined. A mandibular premolar and a mandibular canine were studied after they were extracted using radiographs, a stereomicroscope (SM) and a scanning electron microscope (SEM). Lastly, 3D images of the sectioned teeth were obtained(3D). Results: Radiographically, internal root resorption was shown as a uniform radiolucency. By SM examination, an extensive destruction of dentin was seen, while, by SEM examination, a disappearance of dentinal tubules was clear. The 3D reconstructive method revealed a circumscribed, oval-shaped defect that did not perforate the cemental layer. Conclusions: Internal root resorption is a rare remodeling process that can be studied using different experimental methods.

43 citations


Proceedings ArticleDOI
07 Nov 2002
TL;DR: This paper will focus on detection/decoding performance evaluation and try to summarize its basic principles and a methodology for deriving the corresponding performance metrics will also be provided.
Abstract: Benchmarking of watermarking algorithms is a complicated task that requires examination of a set of mutually dependent performance factors (algorithm complexity, decoding/detection performance, and perceptual quality). This paper will focus on detection/decoding performance evaluation and try to summarize its basic principles. A methodology for deriving the corresponding performance metrics will also be provided.

32 citations


Proceedings ArticleDOI
10 Dec 2002
TL;DR: Experiments conducted on a small visual speech recognition task using very simple features demonstrate a word recognition rate on the level of the best rates previously reported even without training the state transition probabilities in the Viterbi lattices, proving the suitability of support vector machines for visualspeech recognition.
Abstract: In this paper we propose a visual speech recognition network based on support vector machines. Each word of the dictionary is modeled by a set of temporal sequences of visemes. Each viseme is described by a support vector machine, and the temporal character of speech is modeled by integrating the support vector machines as nodes into a Viterbi decoding lattice. Experiments conducted on a small visual speech recognition task using very simple features demonstrate a word recognition rate on the level of the best rates previously reported even without training the state transition probabilities in the Viterbi lattices. This proves the suitability of support vector machines for visual speech recognition.

31 citations


Proceedings ArticleDOI
07 Nov 2002
TL;DR: A blind watermarking method for the copyright protection of sets of polygonal lines in vector graphics images and GIS data (elevation contour maps) is presented.
Abstract: A blind watermarking method for the copyright protection of sets of polygonal lines in vector graphics images and GIS data (elevation contour maps) is presented. The paper focuses mainly on the use of simple fusion rules for combining the detector outputs from each polygonal line in order to come up with a global detection result. Experimental comparison of the various fusion methods using both synthetic and real data (elevation maps) is provided.

31 citations


Journal ArticleDOI
TL;DR: Three-dimensional volume representations from each tooth were achieved in this project to produce the final three-dimensional teeth models, on which virtual accesses of pulp cavities have been performed.

30 citations


Journal ArticleDOI
TL;DR: A novel method for frontal face verification based on the morphological signal decomposition, a procedure that is used to model a facial image region as a sum of components, yielding a very low equal error rate.

25 citations


Proceedings ArticleDOI
24 Apr 2002
TL;DR: The method for shot cut detection relies on the mutual information and the joint entropy between the frames and it is demonstrated that the method detects both fades and abrupt cuts with high accuracy.
Abstract: New methods for detecting shot boundaries in video sequences and for extracting key frames using metrics based on information theory are proposed. The method for shot cut detection relies on the mutual information and the joint entropy between the frames. It can detect cuts, fade-ins and fade-outs. The detection technique was tested on TV video sequences having different types of shots and containing significant object and camera motion inside the shots. It is demonstrated that the method detects both fades and abrupt cuts with high accuracy. The method for key frame extraction is using the mutual information. We show that it captures satisfactorily the visual content of the shot.

Proceedings ArticleDOI
07 Nov 2002
TL;DR: Experiments conducted on a small visual speech recognition task show a word recognition rate on the level of the best rates previously reported, even without training the state transition probabilities in the Viterbi lattice and using very simple features.
Abstract: In this paper we propose a visual speech recognition network based on support vector machines. Each word of the dictionary is described as a temporal sequence of visemes. Each viseme is described by a support vector machine, and the temporal character of speech is modeled by integrating the support vector machines as nodes into a Viterbi decoding lattice. Experiments conducted on a small visual speech recognition task show a word recognition rate on the level of the best rates previously reported, even without training the state transition probabilities in the Viterbi lattice and using very simple features. This proves the suitability of support vector machines for visual speech recognition.

Book ChapterDOI
11 Apr 2002
TL;DR: A new system for the recognition of visual speech based on support vector machines which proved to be powerful classifiers in other visual tasks is proposed, which offers the advantage of an easy generalization to large vocabulary recognition tasks due to the use of viseme models, as opposed to entire word models.
Abstract: Speech recognition based on visual information is an emerging research field We propose here a new system for the recognition of visual speech based on support vector machines which proved to be powerful classifiers in other visual tasks We use support vector machines to recognize the mouth shape corresponding to different phones produced To model the temporal character of the speech we employ the Viterbi decoding in a network of support vector machines The recognition rate obtained is higher than those reported earlier when the same features were used The proposed solution offers the advantage of an easy generalization to large vocabulary recognition tasks due to the use of viseme models, as opposed to entire word models

Proceedings ArticleDOI
13 May 2002
TL;DR: A novel blind method for 3D image watermarking robust against geometric distortions and lossy compression up to a certain compression ratio is proposed and experiments indicate the superiority of the proposed method.
Abstract: A novel blind method for 3D image watermarking robust against geometric distortions is proposed. A ternary watermark is embedded in a grayscale or a color 3D volume. Construction of watermarks having appropriate structure enables fast and robust watermark detection even after several geometric distortions of the watermarked volume. Simulation results indicate the ability of the proposed method to deal with the aforementioned attacks. The proposed method is also robust against lossy compression up to a certain compression ratio. Experiments conducted indicate the superiority of the proposed method.

Proceedings ArticleDOI
10 Dec 2002
TL;DR: An analysis indicates whether bagging, a method for generating multiple versions of a classifier from bootstrap samples of a training set, and combining their outcomes by majority voting, is expected to improve the accuracy of the classifier.
Abstract: In this paper we study the stability of support vector machines in face detection by decomposing their average prediction error into the bias, variance, and aggregation effect terms. Such an analysis indicates whether bagging, a method for generating multiple versions of a classifier from bootstrap samples of a training set, and combining their outcomes by majority voting, is expected to improve the accuracy of the classifier. We estimate the bias, variance, and aggregation effect by using bootstrap smoothing techniques when support vector machines are applied to face detection in the AT & T face database and we demonstrate that support vector machines are stable classifiers. Accordingly, bagging is not expected to improve their face detection accuracy.

Proceedings ArticleDOI
07 Nov 2002
TL;DR: A novel blind method for 3D image watermarking, robust against geometric distortions, and robust against lossy compression up to a certain compression ratio is proposed.
Abstract: A novel blind method for 3D image watermarking, robust against geometric distortions, is proposed. A ternary watermark is embedded in a grayscale or a color 3D volume. Construction of watermarks having appropriate structure enables fast and robust watermark detection even after several geometric distortions of the watermarked volume. Simulation results indicate the ability of the proposed method to deal with the aforementioned attacks. The proposed method is also robust against lossy compression up to a certain compression ratio.

Book ChapterDOI
11 Apr 2002
TL;DR: An accurate, computationally efficient and fully-automated algorithm for the alignment of 2D serially acquired sections forming a 3D volume is presented and the experimental results demonstrated the method's accuracy as reconstruction errors are less than 1 degree in rotation and more than 1 pixel in translation.
Abstract: An accurate, computationally efficient and fully-automated algorithm for the alignment of 2D serially acquired sections forming a 3D volume is presented. The method accounts for the main shortcomings of 3D image alignment: corrupted data (cuts and tears), dissimilarities or discontinuities between slices, missing slices. 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 3D 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 CT scanned 3D data) and the experimental results demonstrated the method's accuracy as reconstruction errors are less than 1 degree in rotation and less than 1 pixel in translation.

Proceedings ArticleDOI
10 Dec 2002
TL;DR: Variations of the proposed metrics can be used as a quantitative estimate of changes in the tracking region, caused by occlusion, sudden movement or the deformation of the tracked object.
Abstract: Metrics based on mutual information and not resorting to ground truth data are proposed in this paper in order to measure tracking reliability under occlusion., The variations of the proposed metrics can be used as a quantitative estimate of changes in the tracking region, caused by occlusion, sudden movement or the deformation of the tracked object. The proposed metric was tested on an object tracking scheme using multiple feature point correspondences. Experimental results have shown that mutual information can effectively characterize object appearance and reappearance in many computer vision applications.

Proceedings ArticleDOI
10 Dec 2002
TL;DR: Experimental results prove the superiority of the proposed detector over the correlator, which can be applied in the case of additive watermarking in the DCT or DWT domain.
Abstract: Most of the watermarking schemes that have been proposed until now employ a correlator in the detection stage. The current paper proposes a new detector scheme that can be applied in the case of additive watermarking in the DCT or DWT domain. Certain properties of the probability density function of the coefficients in these domains are exploited in order to construct an asymptotically optimal detector based on well known results of the detection theory. Detection is performed without the use of the original image, as in methods employing different detectors. Experimental results prove the superiority of the proposed detector over the correlator.

Journal ArticleDOI
TL;DR: This paper builds on the L/sub p/ comparators for which efficient analog implementations exist that employ operational amplifiers and proposes a proper approach to compensate for the estimation errors.
Abstract: Digital implementations of sorting networks that rely on a digital signal processor core are not as efficient as their analog counterparts. This paper builds on the L/sub p/ comparators for which efficient analog implementations exist that employ operational amplifiers. From a statistical point of view, L/sub p/ comparators are based on nonlinear means. Their probability density function and the first- and second-order moments are derived for independent uniformly distributed inputs. L/sub p/ comparators provide estimates of the minimum and maximum of their inputs. A proper approach to compensate for the estimation errors is proposed. Applications of the L/sub p/ comparators in odd-even transposition networks, median approximation networks, and min/max networks are presented.

Proceedings ArticleDOI
11 Apr 2002
TL;DR: It is demonstrated that trained support vector machines with a Radial Basis Function kernel segment satisfactorily (unseen) ultrasound B-mode images as well as clinical ultrasonic images.
Abstract: Support Vector Machines are a general algorithm based on guaranteed risk bounds of statistical learning theory. They have found numerous applications, such as in classification of brain PET images, optical character recognition, object detection, face verification, text categorization and so on. In this paper we propose the use of support vector machines to segment lesions in ultrasound images and we assess thoroughly their lesion detection ability. We demonstrate that trained support vector machines with a Radial Basis Function kernel segment satisfactorily (unseen) ultrasound B-mode images as well as clinical ultrasonic images.

Proceedings ArticleDOI
10 Dec 2002
TL;DR: A joint probabilistic face detection and tracking algorithm for combining a likelihood estimation and a prior probability estimation based on the fusion of an information theoretic tracking cue and a Gaussian temporal model is proposed.
Abstract: A joint probabilistic face detection and tracking algorithm for combining a likelihood estimation and a prior probability is proposed. Face tracking is achieved by a Bayesian framework. The likelihood estimation scheme is based on statistical training of sets of automatically generated feature points, while the prior probability estimation is based on the fusion of an information theoretic tracking cue and a Gaussian temporal model. The likelihood estimation process is the cone of a multiple face detection scheme used to initialize the tracking process. The resulting system was tested on real image sequences and is robust to significant partial occlusion and illumination changes.

Journal Article
TL;DR: In this article, a variant of the self-organizing maps algorithm is proposed for document organization and retrieval, where bigrams are used to encode the available documents and signed ranks are assigned to these bigrams according to their frequencies.
Abstract: A variant of the self-organizing maps algorithm is proposed in this paper for document organization and retrieval. Bigrams are used to encode the available documents and signed ranks are assigned to these bigrams according to their frequencies. A novel metric which is based on the Wilcoxon signed-rank test exploits these ranks in assessing the contextual similarity between documents. This metric replaces the Euclidean distance employed by the self-organizing maps algorithm in identifying the winner neuron. Experiments performed using both algorithms demonstrates a superior performance of the proposed variant against the self-organizing map algorithm regarding the average recall-precision curves.

01 Jan 2002
TL;DR: This paper built nearest neighbor classifiers based on their resulting independent components and compare their ability to detect faces to that of support vector machines.
Abstract: In this paper we explore the independent component decomposition for face detection. The minimization of the Kullback Leibler divergence and the maximization of the entropy are two methods employed to decompose an original image into its independent components. We built nearest neighbor classifiers based on their resulting independent components and compare their ability to detect faces to that of support vector machines.

Book ChapterDOI
28 Aug 2002
TL;DR: A novel metric which is based on the Wilcoxon signed-rank test exploits these ranks in assessing the contextual similarity between documents to replace the Euclidean distance employed by the self-organizing maps algorithm in identifying the winner neuron.
Abstract: A variant of the self-organizing maps algorithm is proposed in this paper for document organization and retrieval. Bigrams are used to encode the available documents and signed ranks are assigned to these bigrams according to their frequencies. A novel metric which is based on the Wilcoxon signed-rank test exploits these ranks in assessing the contextual similarity between documents. This metric replaces the Euclidean distance employed by the self-organizing maps algorithm in identifying the winner neuron. Experiments performed using both algorithms demonstrates a superior performance of the proposed variant against the self-organizing map algorithm regarding the average recallprecision curves.

Proceedings ArticleDOI
07 Nov 2002
TL;DR: This paper presents an accurate, computationally efficient, fast and fully-automated algorithm for the alignment of 2D serially acquired sections forming a 3D volume based on the determination of inter-slice correspondences.
Abstract: This paper presents an accurate, computationally efficient, fast and fully-automated algorithm for the alignment of 2D serially acquired sections forming a 3D volume. The method accounts for the main shortcomings of 3D image alignment: corrupted data (cuts and tears), dissimilarities or discontinuities between slices and missing slices. The approach relies on the determination of inter-slice correspondences. The features used for correspondence are extracted by a 2D physics-based deformable model parameterizing the object shape. Correspondence affinities and global constraints render the method efficient and reliable. The method has been evaluated on real images and the experimental results demonstrate its accuracy, as reconstruction errors are smaller than 1 degree in rotation and smaller than 1 pixel in translation.