Dr. Bertrand Coüasnon Profile

Dr. Bertrand Coüasnon

at IRISA / INSA Rennes

SPIE Involvement:

Author | Editor

Proceedings Article | 24 March 2014 Paper

Handwritten text segmentation using blurred image

Aurélie Lemaitre, Jean Camillerapp, Bertrand Coüasnon

Proceedings Volume 9021, 90210D (2014) https://doi.org/10.1117/12.2035735

KEYWORDS: Image segmentation, Databases, Image analysis, Tantalum, Fermium, Frequency modulation, Data modeling, Electroluminescent displays, Image resolution, Binary data

Read Abstract +

Proceedings Article | 24 March 2014 Paper

LearnPos: a new tool for interactive learning positioning

Cérès Carton, Aurélie Lemaitre, Bertrand Coüasnon

Proceedings Volume 9021, 90210H (2014) https://doi.org/10.1117/12.2042379

KEYWORDS: Neodymium, Data modeling, Databases, Fuzzy logic, Error analysis, Image segmentation, Image analysis, Ytterbium, Analytical research, Cobalt

Read Abstract +

Proceedings Article | 24 March 2014 Paper

Boosting bonsai trees for handwritten/printed text discrimination

Yann Ricquebourg, Christian Raymond, Baptiste Poirriez, Aurélie Lemaitre, Bertrand Coüasnon

Proceedings Volume 9021, 902105 (2014) https://doi.org/10.1117/12.2042418

KEYWORDS: Image segmentation, Binary data, Image processing, Feature extraction, Data processing, Data modeling, Optical character recognition, Feature selection, Visualization, Neural networks

Read Abstract +

Proceedings Article | 4 February 2013 Paper

Evaluation of lexicon size variations on a verification and rejection system based on SVM, for accurate and robust recognition of handwritten words

Yann Ricquebourg, Bertrand Coüasnon, Laurent Guichard

Proceedings Volume 8658, 86580A (2013) https://doi.org/10.1117/12.2006985

KEYWORDS: Image segmentation, Detection and tracking algorithms, Databases, Curium, Error analysis, Silicon, Picosecond phenomena, Computer programming, Image processing, Feature extraction

Read Abstract +

The transcription of handwritten words remains a still challenging and difficult task. When processing full pages, approaches are limited by the trade-off between automatic recognition errors and the tedious aspect of human user verification. In this article, we present our investigations to improve the capabilities of an automatic recognizer, so as to be able to reject unknown words (not to take wrong decisions) while correctly rejecting (i.e. to recognize as much as possible from the lexicon of known words). This is the active research topic of developing a verification system that optimize the trade-off between performance and reliability. To minimize the recognition errors, a verification system is usually used to accept or reject the hypotheses produced by an existing recognition system. Thus, we re-use our novel verification architecture1 here: the recognition hypotheses are re-scored by a set of support vector machines, and validated by a verification mechanism based on multiple rejection thresholds. In order to tune these (class-dependent) rejection thresholds, an algorithm based on dynamic programming has been proposed which focus on maximizing the recognition rate for a given error rate. Experiments have been carried out on the RIMES database in three steps. The first two showed that this approach results in a performance superior or equal to other state-of-the-art rejection methods. We focus here on the third one showing that this verification system also greatly improves results of keywords extraction in a set of handwritten words, with a strong robustness to lexicon size variations (21 lexicons have been tested from 167 entries up to 5,600 entries) which is particularly relevant to our application context cooperating with humans, and only made possible thanks to the rejection ability of this proposed system. The proposed verification system, compared to a HMM with simple rejection, improves on average the recognition rate by 57% (resp. 33% and 21%) for a given error rate of 1% (resp. 5% and 10%).

Proceedings Article | 24 January 2012 Paper

Iterative analysis of document collections enables efficient human-initiated interaction

Joseph Chazalon, Bertrand Coüasnon

Proceedings Volume 8297, 82970L (2012) https://doi.org/10.1117/12.911995

KEYWORDS: Error analysis, Visualization, Monochromatic aberrations, Image processing, Visual analytics, Systems modeling, Human-machine interfaces, Computer architecture, Telecommunications, Image segmentation

Read Abstract +

Proceedings Article | 24 January 2011 Paper

A perceptive method for handwritten text segmentation

Aurélie Lemaitre, Jean Camillerapp, Bertrand Coüasnon

Proceedings Volume 7874, 78740C (2011) https://doi.org/10.1117/12.873037

KEYWORDS: Image segmentation, Image resolution, Databases, Fermium, Frequency modulation, Monochromatic aberrations, Feature extraction, Electronic imaging, Current controlled current source, Data mining

Read Abstract +

Proceedings Article | 24 January 2011 Paper

Introduction of statistical information in a syntactic analyzer for document image recognition

André Maroneze, Bertrand Coüasnon, Aurélie Lemaitre

Proceedings Volume 7874, 787404 (2011) https://doi.org/10.1117/12.873393

KEYWORDS: Image analysis, Statistical analysis, Stochastic processes, Electronic imaging, Current controlled current source, Information fusion, Feedback loops

Read Abstract +

Proceedings Article | 18 February 2010 Paper

Interest of perceptive vision for document structure analysis

Aurélie Lemaitre, Jean Camillerapp, Bertrand Coüasnon

Proceedings Volume 7527, 752714 (2010) https://doi.org/10.1117/12.838453

KEYWORDS: Visualization, Visual process modeling, Image segmentation, Human vision and color perception, Retina, Image resolution, Document image analysis, Feature extraction, Chemical elements, Cobalt

Read Abstract +

Proceedings Article | 18 January 2010 Paper

Using definite clause grammars to build a global system for analyzing collections of documents

Joseph Chazalon, Bertrand Coüasnon

Proceedings Volume 7534, 75340R (2010) https://doi.org/10.1117/12.840436

KEYWORDS: Image processing, Silver, Image analysis, Image segmentation, Statistical analysis, Computer programming, Associative arrays, Head, Process modeling, Computer programming languages

Read Abstract +

Proceedings Article | 28 January 2008 Paper

A generic method for structure recognition of handwritten mail documents

Aurélie Lemaitre, Jean Camillerapp, Bertrand Coüasnon

Proceedings Volume 6815, 68150W (2008) https://doi.org/10.1117/12.766477

KEYWORDS: Image segmentation, Image resolution, Silicon, Optical character recognition, Image analysis, Feature extraction, Binary data, Electronic imaging, Astatine, Digital filtering

Read Abstract +

Showing 5 of 10 publications

SPIE Conference Volume | 2 February 2014

Document Recognition and Retrieval XXI

SPIE Conference Volume | 21 January 2013

Document Recognition and Retrieval XX

Conference Committee Involvement (4)

Document Recognition and Retrieval XXII

11 February 2015 | San Francisco, California, United States

Document Recognition and Retrieval XXI

5 February 2014 | San Francisco, California, United States

Document Recognition and Retrieval XX

5 February 2013 | Burlingame, California, United States

Document Recognition and Retrieval XIX

25 January 2012 | Burlingame, California, United States

Keywords/Phrases

Search In:

Publication Years