Filters








58,107 Hits in 5.6 sec

MTAP special issue on methods and tools for ground truth collection in multimedia applications

Concetto Spampinato, Bastiaan J. Boom, Jiyin He
2014 Multimedia tools and applications  
Nevertheless, the creation of a common and large scale ground truth data to train, test and evaluate algorithms for multimedia processing is still a major concern.  ...  In fact, tools for ground truth annotation must be user-oriented, providing visual interfaces and methods that are able to guide and speed-up the process of ground truth creation.  ...  The special issue specifically addresses the development of multimedia processing methods for supporting automatic ground truth generation, methods and tools for combining and comparing ground truth labeled  ... 
doi:10.1007/s11042-014-1853-1 fatcat:unfnafnuh5gexpyw74hxxrqegi

A general framework for the evaluation of symbol recognition methods

E. Valveny, P. Dosch, Adam Winstanley, Yu Zhou, Su Yang, Luo Yan, Liu Wenyin, Dave Elliman, Mathieu Delalandre, Eric Trupin, Sébastien Adam, Jean-Marc Ogier
2006 International Journal on Document Analysis and Recognition  
The discussion is centered on three key elements in performance evaluation: test data, evaluation metrics and protocols of evaluation.  ...  Performance evaluation is receiving increasing interest in graphics recognition.  ...  Acknowledgments The contest organizers would like to acknowledge all participants of the first contest of performance evaluation of symbol recognition methods, as well as the organizers of the GREC workshop  ... 
doi:10.1007/s10032-006-0033-x fatcat:pl5j2htrcvgg7hbrkuixjpo3oi

Performance Evaluation of Symbol Recognition [chapter]

Ernest Valveny, Philippe Dosch
2004 Lecture Notes in Computer Science  
These issues were the starting point of the organization of the contest on symbol recognition held during the last Workshop on Graphics Recognition (GREC'03).  ...  Thus, standard evaluation datasets and protocols have to be built up in order to be able to evaluate the performance of all these methods.  ...  The ground-truth is also easier to build and recognition methods can use both formats. Segmentation is another important issue concerning the evaluation of symbol recognition.  ... 
doi:10.1007/978-3-540-28640-0_34 fatcat:qonp5bikezdoler3vbnjixuwii

ACM SIGMM the first workshop on web-scale multimedia corpus (WSMC09)

Benoit Huet, Jinhui Tang, Alex Hauptmann
2009 Proceedings of the seventeen ACM international conference on Multimedia - MM '09  
of such resources in terms of ground truth, features, algorithms and tools etc.  ...  The Workshop will provide a forum to consolidate key factors related to research on very large scale multimedia dataset such as the construction of dataset, creation of ground truth, sharing and extension  ...  We hope that you enjoy and benefit from this program,  ... 
doi:10.1145/1631272.1631551 dblp:conf/mm/HuetTH09 fatcat:kwufdtgghnhi7jqbfs5mtepkce

Abramowitz and Stegun – A Resource for Mathematical Document Analysis [chapter]

Alan P. Sexton
2012 Lecture Notes in Computer Science  
on and cross evaluation of different algorithms, tools and systems.  ...  full tool chain themselves.  ...  Acknowledgements We thank Bruce Miller of the National Institute of Standards and Technology, for providing a clean new copy of A&S for scanning.  ... 
doi:10.1007/978-3-642-31374-5_11 fatcat:dp7bfbsdqrhjdiq57z25wi4hba

A new data science research program: evaluation, metrology, standards, and community outreach

Bonnie J. Dorr, Craig S. Greenberg, Peter Fontana, Mark Przybocki, Marion Le Bras, Cathryn Ploehn, Oleg Aulov, Martial Michel, E. Jim Golden, Wo Chang
2016 International Journal of Data Science and Analytics  
The DSE series aims to address logistical and evaluation design challenges while providing rigorous measurement methods and an emphasis on generalizability rather than domain-and application-specific approaches  ...  The evaluations are intended to facilitate research efforts and collaboration, leverage shared infrastructure, and effectively address crosscutting challenges faced by diverse data science communities.  ...  Another potential approach is to use simulated data as a proxy for ground truth. Within the DSRP, these and other approaches for addressing issues concerning ground truth metadata will be explored.  ... 
doi:10.1007/s41060-016-0016-z dblp:journals/ijdsa/DorrGFPBPAMGC16 fatcat:ngrq7wupyfbs5ozna4sgthcjma

Landscape Analysis for the Specimen Data Refinery

Stephanie Walton, Laurence Livermore, Olaf Bánki, Robert Cubey, Robyn Drinkwater, Markus Englund, Carole Goble, Quentin Groom, Christopher Kermorvant, Isabel Rey, Celia Santos, Ben Scott (+2 others)
2020 Research Ideas and Outcomes  
We consider the potential for repurposing existing tools, including workflow management systems; and areas where more development is required.  ...  This report reviews the current state-of-the-art applied approaches on automated tools, services and workflows for extracting information from images of natural history specimens and their labels.  ...  diagram and discussions on service implementation; comments and proof reading by the report contributors and by Helen Hardy; review feedback from Mark Hereld and Rebecca Dikow.  ... 
doi:10.3897/rio.6.e57602 fatcat:qwgfilzc6vebbmhgrr2rp3xcni

Document image recognition and retrieval: where are we?

Michael D. Garris, Daniel P. Lopresti, Jiangying Zhou
1999 Document Recognition and Retrieval VI  
This paper discusses survey data collected as a result of planning a project to evaluate document recognition and information retrieval technologies.  ...  In the process of establishing the project, a Request for Comment (RFC) was widely distributed throughout the document recognition and information retrieval research and development (R&D) communities,  ...  The aim of the project was to study and evaluate the automated production and usability of large-scale, on-line collections of digital documents.  ... 
doi:10.1117/12.335811 dblp:conf/drr/Garris99 fatcat:m6vk7licqnda3gyt3dz2hgzbru

Graphics Recognition—What Else? [chapter]

Karl Tombre
2010 Lecture Notes in Computer Science  
A number of points raised two years ago remain very much valid, but we also try to identify some new grand challenges for the field of graphics recognition.  ...  Large-Scale Applications A lot of discussions addressed the specific challenges of building large-scale applications, i.e. scaling from an academic problem to a really useful system.  ...  inria-00497723, version 1 -5 Jul 2010 -Ad hoc tasks such as identification and recognition of tables are addressed more easily than full-fledged, large-scale applications.  ... 
doi:10.1007/978-3-642-13728-0_25 fatcat:6nlqbdiaw5dghkdjufelz5ni3i

Benchmarking Strategy for Arabic Screen-Rendered Word Recognition [chapter]

Fouad Slimane, Slim Kanoun, Jean Hennebert, Rolf Ingold, Adel M. Alimi
2012 Guide to OCR for Arabic Scripts  
This database is a large-scale benchmarking of open-vocabulary, multi-font, multi-size and multi-style word recognition systems in Arabic.  ...  The challenges that are addressed by the database are in the variability of the sizes, fonts and styles used to generate the images.  ...  Acknowledgements The authors would like to thank all ICDAR'2011-Arabic Recognition Competition: Multi-Font Multi-Size Digitally Represented Text participants and the anonymous reviewers for their comments  ... 
doi:10.1007/978-1-4471-4072-6_18 fatcat:zzzsq2vlurfpxlvdcjekrjeo2y

Performance Evaluation of Symbol Recognition and Spotting Systems: An Overview

Mathieu Delalandre, Ernest Valveny, Josep Lladós
2008 2008 The Eighth IAPR International Workshop on Document Analysis Systems  
This paper deals with the topic of performance evaluation of the symbol recognition & spotting systems.  ...  The paper starts by giving a general view of symbol recognition & spotting and performance evaluation.  ...  Rusinol, Philippe Dosch, Rashid Qureshi and Tony Pridmore.  ... 
doi:10.1109/das.2008.63 dblp:conf/das/DelalandreVL08 fatcat:xithkg5vcbgs5fm4w5zwalnge4

An analysis of binarization ground truthing

Elisa H. Barney Smith
2010 Proceedings of the 8th IAPR International Workshop on Document Analysis Systems - DAS '10  
Evaluating binarization on real images is preferred. The ground truthing between and among different operators is compared. Four direct metrics were used.  ...  The accuracy of a binarization algorithm is often calculated relative to a ground truth image. Except for synthetically generated images, no ground truth image exists.  ...  The restarting issue was found to be largely a timing issue making students either work a long concentrated period, or have to leave their machine on, avoiding other applications and locked when not in  ... 
doi:10.1145/1815330.1815334 dblp:conf/das/Smith10 fatcat:npw3rvc24fg33gslxhdagvvbhu

Evaluation of Prompted Annotation of Activity Data Recorded from a Smart Phone

Ian Cleland, Manhyung Han, Chris Nugent, Hosung Lee, Sally McClean, Shuai Zhang, Sungyoung Lee
2014 Sensors  
In this paper we discuss the design and evaluation of a mobile based tool to collect activity data on a large scale.  ...  Further work will examine data segmentation and personalization issues in order to refine the system.  ...  Acknowledgments The authors wish to acknowledge partial support from the EPSRC through the MATCH program (EP/F063822/1 and EP/G012393/1). This research was supported by the MSIP (  ... 
doi:10.3390/s140915861 pmid:25166500 pmcid:PMC4208150 fatcat:6tbwayj7qzak5oiu4w7yaougye

An open approach towards the benchmarking of table structure recognition systems

Asif Shahab, Faisal Shafait, Thomas Kieninger, Andreas Dengel
2010 Proceedings of the 8th IAPR International Workshop on Document Analysis Systems - DAS '10  
We provide free access to the ground truthing tool and evaluation mechanism described in this paper, describe the ideas behind and we also provide ground truth for the 547 documents of the UNLV and UW-  ...  Today, quite a large number of different approaches facing these tasks have been described in literature or are available as part of commercial OCR systems that claim to deal with tables on the scanned  ...  Acknowledgments This work was partially funded by the BMBF (German Federal Ministry of Education and Research), project PaREn (01 IW 07001).  ... 
doi:10.1145/1815330.1815345 dblp:conf/das/ShahabSKD10 fatcat:qpcvffglbzasnhhmd7gmw6cshi

High-Accuracy Facial Depth Models derived from 3D Synthetic Data [article]

Faisal Khan, Shubhajit Basak, Hossein Javidnia, Michael Schukat, Peter Corcoran
2020 arXiv   pre-print
Potential fields of application include 3D reconstruction, driver monitoring systems, robotic vision systems, and advanced scene understanding.  ...  The synthetic data is used to train a CNN based facial depth estimation system which is validated on both synthetic and real images.  ...  Very limited work is done on synthetic facial models to explore the field with the available 3D tools and other commercially available software.  ... 
arXiv:2003.06211v2 fatcat:fpx2z4dq6vh5lh6eao6h6dxxfa
« Previous Showing results 1 — 15 out of 58,107 results