Search For:

Displaying 1-16 out of 16 total
Understanding Document Analysis and Understanding (through Modeling)
Found in: Document Analysis and Recognition, International Conference on
By Bertin Klein, Stefan Agne, Andrew D. Bagdanov
Issue Date:August 2003
pp. 1218
We turn to the viewpoint of users of a DAU system. Out of the view of users we sketch a picture of
 
Granulometric Analysis of Document Images
Found in: Pattern Recognition, International Conference on
By Andrew D. Bagdanov, Marcel Worring
Issue Date:August 2002
pp. 10468
We report on new form of multivariate granulometries based on rectangles of varying size and aspect ratio. These granulometries are used for describing visual similarity between document images. Rectangular granulometries are used to probe the layout struc...
 
Fine-Grained Document Genre Classification Using First Order Random Graphs
Found in: Document Analysis and Recognition, International Conference on
By Andrew D. Bagdanov,Marcel Worring
Issue Date:September 2001
pp. 0079
Abstract: We approach the general problem of classifying machine-printed documents into genres. Layout is a crit-cal factor in recognizing fine-grained genres, as document content features are similar. Document genre is determined from the layout structure...
 
Posterity Logging of Face Imagery for Video Surveillance
Found in: IEEE MultiMedia
By Andrew D. Bagdanov,Alberto Del Bimbo,Fabrizio Dini,Giuseppe Lisanti,Iacopo Masi
Issue Date:October 2012
pp. 48-59
A real-time posterity logging system detects and tracks multiple targets in video streams, grabbing face images and retaining only the best quality for each detected target.
 
Finite State Machine-Based Optimization of Data Parallel Regular Domain Problems Applied in Low-Level Image Processing
Found in: IEEE Transactions on Parallel and Distributed Systems
By Frank J. Seinstra, Dennis Koelma, Andrew D. Bagdanov
Issue Date:October 2004
pp. 865-877
<p><b>Abstract</b>—A popular approach to providing nonexperts in parallel computing with an easy-to-use programming model is to design a software library consisting of a set of preparallelized routines, and hide the intricacies of paralle...
 
Document Classification and Page Stream Segmentation for Digital Mailroom Applications
Found in: 2013 12th International Conference on Document Analysis and Recognition (ICDAR)
By Albert Gordo,Marcal Rusinol,Dimosthenis Karatzas,Andrew D. Bagdanov
Issue Date:August 2013
pp. 621-625
In this paper we present a method for the segmentation of continuous page streams into multipage documents and the simultaneous classification of the resulting documents. We first present an approach to combine the multiple pages of a document into a singl...
 
Adaptive Video Compression for Video Surveillance Applications
Found in: Multimedia, International Symposium on
By Andrew D. Bagdanov,Marco Bertini,Alberto Del Bimbo,Lorenzo Seidenari
Issue Date:December 2011
pp. 190-197
This article describes an approach to adaptive video coding for video surveillance applications. Using a combination of low-level features with low computational cost, we show how it is possible to control the quality of video compression so that semantica...
 
Reactive Object Tracking with a Single PTZ Camera
Found in: Pattern Recognition, International Conference on
By Murad Al Haj, Andrew D. Bagdanov, Jordi Gonzàlez, F. Xavier Roca
Issue Date:August 2010
pp. 1690-1693
In this paper we describe a novel approach to reactive tracking of moving targets with a pan-tilt-zoom camera. The approach uses an extended Kalman filter to jointly track the object position in the real world, its velocity in 3D and the camera intrinsics,...
 
Harmony potentials for joint classification and segmentation
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Josep M. Gonfaus, Xavier Boix, Joost van de Weijer, Andrew D. Bagdanov, Joan Serrat, Jordi Gonzalez
Issue Date:June 2010
pp. 3280-3287
Hierarchical conditional random fields have been successfully applied to object segmentation. One reason is their ability to incorporate contextual information at different scales. However, these models do not allow multiple labels to be assigned to a sing...
 
Adaptive uncertainty estimation for particle filter-based trackers
Found in: Image Analysis and Processing, International Conference on
By Andrew D. Bagdanov, Alberto Del Bimbo, Fabrizio Dini, Walter Nunziati
Issue Date:September 2007
pp. 331-336
In particle filter.based visual trackers, dynamic velocity components are typically incorporated into the state update equations. In these cases, there is a risk that the uncertainty in the model update stage can become amplified in unexpected and undesira...
 
Improving the robustness of particle filter-based visual trackers using online parameter adaptation
Found in: Advanced Video and Signal Based Surveillance, IEEE Conference on
By Andrew D. Bagdanov, Alberto Del Bimbo, Fabrizio Dini, Walter Nunziati
Issue Date:September 2007
pp. 218-223
In particle filter-based visual trackers, dynamic velocity components are typically incorporated into the state update equations. In these cases, there is a risk that the uncertainty in the model update stage can become amplified in unexpected and undesira...
 
Semantic annotation and retrieval of video events using multimedia ontologies
Found in: International Conference on Semantic Computing
By Andrew D. Bagdanov, Marco Bertini, Alberto Del Bimbo, Giuseppe Serra, Carlo Torniai
Issue Date:September 2007
pp. 713-720
Effective usage of multimedia digital libraries has to deal with the problem of building efficient content annotation and retrieval tools. In this paper Multimedia Ontologies, that include both linguistic and dynamic visual ontologies, are presented and th...
 
Learning Foveal Sensing Strategies in Unconstrained Surveillance Environments
Found in: Advanced Video and Signal Based Surveillance, IEEE Conference on
By Andrew D. Bagdanov, Alberto Del Bimbo, Walter Nunziati, Federico Pernici
Issue Date:November 2006
pp. 40
In this paper we report on techniques for automatically learning foveal sensing strategies for an active pan-tiltzoom camera. The approach uses reinforcement learning to discover foveal actions maximizing the performance of visual detectors, that are in tu...
 
Improving evidential quality of surveillance imagery through active face tracking
Found in: Pattern Recognition, International Conference on
By Andrew D. Bagdanov, Alberto del Bimbo, Walter Nunziati
Issue Date:August 2006
pp. 1200-1203
We report on a system for automatically obtaining high-resolution images of surveillance targets. The system, beginning from a framed target, uses the presence of faces as a cue to initiate a real-time active face tracking process. Using a single pan-tilt-...
 
The florence 2D/3D hybrid face dataset
Found in: Proceedings of the 2011 joint ACM workshop on Human gesture and behavior understanding (J-HGBU '11)
By Alberto Del Bimbo, Andrew D. Bagdanov, Iacopo Masi
Issue Date:December 2011
pp. 79-80
This article describes a new dataset under construction at the Media Integration and Communication Center and the University of Florence. The dataset consists of high-resolution 3D scans of human faces along with several video sequences of varying resoluti...
     
A reinforcement learning approach to active camera foveation
Found in: Proceedings of the 4th ACM international workshop on Video surveillance and sensor networks (VSSN '06)
By Alberto del Bimbo, Andrew D. Bagdanov, Federico Pernici, Walter Nunziati
Issue Date:October 2006
pp. 179-186
In this paper we report on techniques for automatically learning foveal sensing strategies for an active pan-tilt-zoom camera. The approach uses reinforcement learning to discover foveal actions maximizing the performance of visual detectors, that are in t...
     
 1