Research Interests:
A novel technique is proposed for watermarking of MPEG-1 and MPEG-2 compressed video streams. The proposed scheme is applied directly in the domain of MPEG-1 system streams and MPEG-2 program streams (multiplexed streams). Perceptual... more
A novel technique is proposed for watermarking of MPEG-1 and MPEG-2 compressed video streams. The proposed scheme is applied directly in the domain of MPEG-1 system streams and MPEG-2 program streams (multiplexed streams). Perceptual models are used during the embedding process in order to avoid degradation of the video quality. The water- mark is detected without the use of the
Research Interests:
A new technique for watermarking of MPEG-1/2 compressed video streams is proposed. The watermarking scheme operates directly in the domain of MPEG-1/2 program streams. Perceptual models are used during the embedding process in order to... more
A new technique for watermarking of MPEG-1/2 compressed video streams is proposed. The watermarking scheme operates directly in the domain of MPEG-1/2 program streams. Perceptual models are used during the embedding process in order to preserve the quality of the video. The detection of the watermark is performed in the compressed domain without requiring the original video. The resulting watermarking
Research Interests:
A supervised neural network (NN)-based algorithm was used for automated detection of ischemic episodes resulting from ST segment elevation or depression. The performance of the method was measured using the European ST-T database. In... more
A supervised neural network (NN)-based algorithm was used for automated detection of ischemic episodes resulting from ST segment elevation or depression. The performance of the method was measured using the European ST-T database. In particular, the performance was measured in terms of beat-by-beat ischemia detection and in terms of the detection of ischemic episodes. The algorithm used to train the NN was an adaptive backpropagation (BP) algorithm. This algorithm drastically reduces training time (tenfold decrease in our case) when compared to the classical BP algorithm. The recall phase of the NN is then extremely fast, a fact that makes it appropriate for real-time detection of ischemic episodes. The resulting NN is capable of detecting ischemia independent of the lead used. It was found that the average ischemia episode detection sensitivity is 88.62% while the ischemia duration sensitivity is 72.22%. The results show that NN can be used in electrocardiogram (ECG) processing in cases where fast and reliable detection of ischemic episodes is desired as in the case of critical care units (CCU's).
Research Interests:
Algorithms, Biomedical Engineering, Neural Networks, Biomedical informatics, Neural Network, and 13 moreDatabases, Critical Care, Electrocardiography, Performance Analysis, Adaptive Systems, Humans, Lead, Real Time, Electrocardiogram, Backpropagation, Sensitivity and Specificity, Electrical And Electronic Engineering, and Predictive value of tests
This work provides a semi-automatic method for defining and modeling of the infarcted myocardial tissue in MRI images. A deformable contour model based on Fourier decomposition is used to define the border of the infarcted region in... more
This work provides a semi-automatic method for defining and modeling of the infarcted myocardial tissue in MRI images. A deformable contour model based on Fourier decomposition is used to define the border of the infarcted region in successive slice images. A new fast algorithm has been developed for fitting the curve to the borders of the region. The method includes
Research Interests:
Ischemie changes of the ECG have been detected using the Counterpropagation (CPN), neural network. The abnormalities it was trained to detect are T wave elevation, T wave depression, ST segment elevation and ST segment depression. Data... more
Ischemie changes of the ECG have been detected using the Counterpropagation (CPN), neural network. The abnormalities it was trained to detect are T wave elevation, T wave depression, ST segment elevation and ST segment depression. Data for the training of the neural network and for the evaluation of the results are taken from the European ST-T Database.
Research Interests:
A supervised neural network (NN) based algorithm was used to detect ischemic episodes from electrocardiograms (ECGs). The algorithm is tested on the European ST-T database. The algorithm is very fast in its recall state due to the NN, and... more
A supervised neural network (NN) based algorithm was used to detect ischemic episodes from electrocardiograms (ECGs). The algorithm is tested on the European ST-T database. The algorithm is very fast in its recall state due to the NN, and uses the minimum amount of information, since it is applied on a one-lead ECG. The adaptive training backpropagation algorithm reduces dramatically
Research Interests:
A deformable 4D model based on Fourier decomposition is presented which was successfully applied to the modeling of the cardiac endocardial and epicardial surfaces and their deformation in time. The proposed method automatically selects... more
A deformable 4D model based on Fourier decomposition is presented which was successfully applied to the modeling of the cardiac endocardial and epicardial surfaces and their deformation in time. The proposed method automatically selects boundary points on the myocardial surfaces in the 3D space, collecting a different set of points for each phase. A 4D model is then fitted to
Research Interests:
Research Interests:
In this paper, a novel color image segmentation algo- rithm and a novel approach to large-format image seg- mentation are presented, both focused on usage for image segmentation in content-based multimedia applications. The novel color... more
In this paper, a novel color image segmentation algo- rithm and a novel approach to large-format image seg- mentation are presented, both focused on usage for image segmentation in content-based multimedia applications. The novel color image segmentation algorithm uses the Discrete Wavelet Frames decomposition to extract tex- ture features and performs pixel classification using a novel initial clustering procedure and
Research Interests:
In this paper, an objective segmentation evaluation metric suitable for the evaluation of still image segmentation results is proposed. The proposed metric is based on the spatial accuracy approach, orig- inally proposed for the... more
In this paper, an objective segmentation evaluation metric suitable for the evaluation of still image segmentation results is proposed. The proposed metric is based on the spatial accuracy approach, orig- inally proposed for the evaluation of foreground/backgroung segmentation masks generated from video sequences. This approach is extended to still image segmentation evaluation, where both the estimated segmentation masks and the
Research Interests:
Research Interests:
In this paper, a novel approach to large-format image seg- mentation is presented, focused on usage in content-based multimedia applications. The proposed framework aims at facilitating the time-efficient segmentation of large-format... more
In this paper, a novel approach to large-format image seg- mentation is presented, focused on usage in content-based multimedia applications. The proposed framework aims at facilitating the time-efficient segmentation of large-format images while maintaining the high perceptual quality of the segmentation result. For this to be achieved, the employed segmentation algorithm is applied to reduced versions of the large-format images,
Research Interests:
A novel unsupervised video object segmentation al- gorithm is presented, aiming to segment a video sequence to ob- jects: spatiotemporal regions representing a meaningful part of the sequence. The proposed algorithm consists of three... more
A novel unsupervised video object segmentation al- gorithm is presented, aiming to segment a video sequence to ob- jects: spatiotemporal regions representing a meaningful part of the sequence. The proposed algorithm consists of three stages: ini- tial segmentation of the first frame using color, motion, and posi- tion information, based on a variant of the K-Means-with-connec- tivity-constraint algorithm; a temporal
Research Interests:
Information Retrieval, Video Compression, Algorithm, Image segmentation, Image Classification, and 16 moreVideo segmentation, Trajectory, Video Streaming, Segmentation, Classification, Video Object, Human Interaction, Experimental Evaluation, Merging, K Means, Indexation, Image Sequence, Rule Based, Electrical And Electronic Engineering, Region Merging, and Bayes classifier
In this paper, an image retrieval methodology suited for search in large collections of heterogeneous images is presented. The pro- posed approach employs a fully unsupervised segmentation algo- rithm to divide images into regions.... more
In this paper, an image retrieval methodology suited for search in large collections of heterogeneous images is presented. The pro- posed approach employs a fully unsupervised segmentation algo- rithm to divide images into regions. Low-level features describing the color, position, size and shape of the resulting regions are ex- tracted and are automatically mapped to appropriate intermediate- level descriptors forming
Research Interests:
In this paper, a color image segmentation al- gorithm and an approach to large-format image segmen- tation are presented, both focused on breaking down im- ages to semantic objects for object-based multimedia ap- plications. The proposed... more
In this paper, a color image segmentation al- gorithm and an approach to large-format image segmen- tation are presented, both focused on breaking down im- ages to semantic objects for object-based multimedia ap- plications. The proposed color image segmentation algo- rithm performs the segmentation in the combined intensity- texture-position feature space in order to produce con- nected regions that correspond
Research Interests:
Data quantization is an essential step before digitization, ie prior to representing real numbers by bits for further digital processing. In this paper we show how a statistically non-optimal quantizer (eg a uniform quantizer) can be... more
Data quantization is an essential step before digitization, ie prior to representing real numbers by bits for further digital processing. In this paper we show how a statistically non-optimal quantizer (eg a uniform quantizer) can be improved by a simple scaling operation before ...
Research Interests:
Research Interests:
In this paper, a graphical modeling-based approach to semantic video analysis is presented for jointly realizing modality fusion and temporal context exploitation. Overall, the examined video sequence is initially segmented into shots and... more
In this paper, a graphical modeling-based approach to semantic video analysis is presented for jointly realizing modality fusion and temporal context exploitation. Overall, the examined video sequence is initially segmented into shots and for every resulting shot appropriate color, motion and audio features are extracted. Then, Hidden Markov Models (HMMs) are employed for performing an initial association of each shot
Research Interests:
In this paper, a probabilistic approach to combining spatial context with visual and co-occurrence information for semantic image analysis is presented. Overall, the examined image is segmented and subsequently an initial classification... more
In this paper, a probabilistic approach to combining spatial context with visual and co-occurrence information for semantic image analysis is presented. Overall, the examined image is segmented and subsequently an initial classification of the resulting image regions to semantic concepts is performed based solely on visual information. Then, a Genetic Algorithm (GA) is introduced for deciding on the optimal semantic
Research Interests:
In this paper, a motion-based approach for detecting high-level se- mantic events in video sequences is presented. Its main character- istic is its generic nature, i.e. it can be directly applied to any pos- sible domain of concern... more
In this paper, a motion-based approach for detecting high-level se- mantic events in video sequences is presented. Its main character- istic is its generic nature, i.e. it can be directly applied to any pos- sible domain of concern without the need for domain-specific algo- rithmic modifications or adaptations. For realizing event detection, the examined video sequence is initially segmented into
Research Interests:
Page 1. A Statistical Learning Approach to Spatial Context Exploitation for Semantic Image Analysis ∗ G. Th. Papadopoulos 1,2 , V. Mezaris 2 , I. Kompatsiaris 2 and MG Strintzis 1,2 1 Electrical & Computer Eng.... more
Page 1. A Statistical Learning Approach to Spatial Context Exploitation for Semantic Image Analysis ∗ G. Th. Papadopoulos 1,2 , V. Mezaris 2 , I. Kompatsiaris 2 and MG Strintzis 1,2 1 Electrical & Computer Eng. Dep., Aristotle Univ. ...
Research Interests:
Flexible 3D motion estimation and tracking for multiview image sequence coding 1 1 This work was supported by the EU CEC Project ACTS PANORAMA (Package for New Autostereoscopic Multiview Systems and Applications, ACTS project 092) and the Greek Secretariat for Science and Technology Programme YPERmore
This paper describes a procedure for model-based coding of all channels of a multiview image sequence. The 3D model is initialised by accurate adaptation of a 2D wireframe model to the foreground object of one of the views. The rigid 3D... more
This paper describes a procedure for model-based coding of all channels of a multiview image sequence. The 3D model is initialised by accurate adaptation of a 2D wireframe model to the foreground object of one of the views. The rigid 3D motion is estimated for each triangle, and spatial homogeneity neighbourhood constraints are used to improve the reliability of the
Research Interests:
The ambiguities due to the purely syntactical nature of MPEG- 7 have hindered its widespread application as they lead to serious in- teroperability issues in sharing and managing multimedia metadata. Ac- knowledging these limitations, a... more
The ambiguities due to the purely syntactical nature of MPEG- 7 have hindered its widespread application as they lead to serious in- teroperability issues in sharing and managing multimedia metadata. Ac- knowledging these limitations, a number of initiatives have been reported towards attaching formal semantics to the MPEG-7 speciflcations. In this paper we examine the rationale on which the relevant
Research Interests:
... Eirini Parissi1, Yiannis Kompatsiaris1, Yiannis S. Chatzizisis2, Vassilis Koutkias3, Nicos Maglaveras3, MG Strintzis1, and George D. Giannoglou2 ... Institute, Centre for Research and Technology-Hellas, 57001, Thessaloniki, Greece... more
... Eirini Parissi1, Yiannis Kompatsiaris1, Yiannis S. Chatzizisis2, Vassilis Koutkias3, Nicos Maglaveras3, MG Strintzis1, and George D. Giannoglou2 ... Institute, Centre for Research and Technology-Hellas, 57001, Thessaloniki, Greece {parissi,ikom,strintzi}@iti.gr 2 Cardiovascular ...
Research Interests:
A supervised neural network (NN) algorithm was used for automated detection of ischemic episodes resulting from ST segment elevation or depression. The performance of the method was measured using the European ST-T database. In particular... more
A supervised neural network (NN) algorithm was used for automated detection of ischemic episodes resulting from ST segment elevation or depression. The performance of the method was measured using the European ST-T database. In particular the performance was measured in terms of beat-by-beat ischemia detection and in terms of ischemic episodes detection. Aggregate statistics for the description of the detector
Research Interests:
Efficient video content management and exploitation requires ex- traction of the underlying semantics, which is a non-trivial task in- volving the association of low-level features with high-level con- cepts. In this paper, a... more
Efficient video content management and exploitation requires ex- traction of the underlying semantics, which is a non-trivial task in- volving the association of low-level features with high-level con- cepts. In this paper, a knowledge-assisted approach for extract- ing semantic information of domain-specific video content is pre- sented. Domain knowledge considers both low-level visual fea- tures (color, motion, shape) and spatial
Research Interests:
Research Interests:
Genetic Algorithms, Content Management, Image segmentation, Genetic Algorithm, Video Analysis, and 10 moreFeature Extraction, Semantic Information, Domain Knowledge, Knowledge base, Domain Specificity, Domain Ontology, Symbolic Representation of Drugs, Visual Features, Object Localization, and Semantic Description
The aim of the SCHEMA Network of Excellence is to bring together a critical mass of universities, research centers, industrial partners and end users, in order to design a reference system for content-based semantic scene analysis,... more
The aim of the SCHEMA Network of Excellence is to bring together a critical mass of universities, research centers, industrial partners and end users, in order to design a reference system for content-based semantic scene analysis, interpretation and understanding. In this paper, recent advances in the development of the SCHEMA reference system are reported, focusing on the application of region-based