Error-correcting output codes are a general framework to combine binary classifiers in order to address the multi-class problem. Based on the error-correcting principles and because of its ability to correct the bias and variance errors of the base classifiers, ECOC has been successfully applied to a wide range of Pattern Recognition applications.

Members

Sergio Escalera, Petia Radeva, Oriol Pujol, Miguel Ángel Bautista

Collaborators

Jordi Vitrià, Xavier Baró

Publications

Sergio Escalera, Oriol Pujol, and Petia Radeva, Traffic Sign Recognition System with Beta-Correction, doi: 10.1007/s00138-008-0145-z, Machine Vision and Applications, vol. 21, issue 2, pp. 99-, 2010.

Miguel Ángel Bautista, Xavier Baró, Oriol Pujol, Petia Radeva, Jordi Vitrià, and Sergio Escalera, Compact Evolutive Design of Error-Correcting Output Codes, Supervised and Unsupervised Methods and their Applications (SUEMA), European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, ECML PKDD 2010.

Sergio Escalera, Oriol Pujol, and Petia Radeva, Error-Correcting Output Codes Library, Journal of Machine Learning Research, vol. 11, pp. 661-664, 2010. Open Source Library, Machine Learning Open Source Software.

Sergio Escalera, Oriol Pujol, and Petia Radeva, Re-coding ECOCs without Re-training, Pattern Recognition Letters, 2010, in press.

Sergio Escalera, Oriol Pujol, and Petia Radeva, On the Decoding Process in Ternary Error-Correcting Output Codes, Transactions in Pattern Analysis and Machine Intelligence, vol. 99, issue 1, 2009. Appendix with the set of experiment performances.

Sergio Escalera, Oriol Pujol, and Petia Radeva, Separability of Ternary Codes for Sparse Designs of Error-Correcting Output Codes, in Pattern Recognition Letters, vol. 30, issue 3, pp. 285-297, 2009.

Xavier Baró, Sergio Escalera, Jordi Vitrià, Oriol Pujol, and Petia Radeva, Traffic Sign Recognition using Evolutionary Adaboost Detection and Forest-ECOC Classification, IEEE Transactions in Intelligent Transport Systems, vol. 10, issue 1, pp. 113-126, 2009. Video sample.

Sergio Escalera, David Tax, Oriol Pujol, Petia Radeva, and Robert Duin, Subclass Problem-dependent Design of Error-Correcting Output Codes, vol. 30, issue 6, pp. 1041-1054, IEEE Transactions in Pattern Analysis and Machine Intelligence, 2008.

Oriol Pujol, Sergio Escalera, and Petia Radeva, An Incremental Node Embedding Technique for Error Correcting Output Codes, vol. 14, issue 2, pp. 713-725, Pattern Recognition, 2008.

Sergio Escalera, Oriol Pujol, Josepa Mauri, and Petia Radeva, Intravascular Ultrasound Tissue Characterization with Sub-class Error-Correcting Output Codes, Special Issue on Biomedical Imaging, Journal of Signal Processing Systems, doi: 10.1007/s11265-008-0180-z, 2008.

Sergio Escalera, Oriol Pujol, and Petia Radeva, Boosted Landmarks of Contextual Descriptors and Forest-ECOC: a novel framework to detect and classify objects in cluttered scenes, vol. 28, issue 13, pp. 1750-1768, Pattern Recognition Letters, 2007.

Sergio Escalera, Coding and Decoding Designs of ECOCs for Multi-class Pattern and Object Recognition, ISBN 978-84-935251-8-7, Computer Vision Center, Universitat Autònoma de Barcelona, 2008.

Mehdi Mirza-Mohammadi, Francesco Ciompi, Sergio Escalera, Oriol Pujol, and Petia Radeva, Ranking Error-Correcting Output Codes for Class Retrieval, 4th CVC Workshop on Research and Development: New Trends and Challenges in Computer Vision, pp. 197-203, 2009.

Sergio Escalera, Alicia Fornés, Oriol Pujol, and Petia Radeva, Multi-class Binary Symbol Classification with Circular Blurred Shape Models, International Conference on Image Analysis and Processing, pp. 1005-1014, 2009.

Sergio Escalera, Oriol Pujol, and Petia Radeva, Recoding Error-Correcting Output Codes, Multiple Classifier Systems, LNCS 5519, pp. 11-21, 2009.

Alicia Fornés, Sergio Escalera, Josep Lladós, Gemma Sánchez, and Joan Mas, Hand Drawn Symbol Recognition by Blurred Shape Model Descriptor and a Multi-class Classifier, Graphics Recognition: Recent Advances and New Opportunities, pp. 30-40, 2008.

Sergio Escalera, Oriol Pujol, and Petia Radeva, Error-Correcting Output Coding for Chagasic Patients Characterization, vol. 17, pp. 1-4, International Conference in Pattern Recognition, 2008.

Sergio Escalera, Oriol Pujol, and Petia Radeva, Separability of Ternary Error-Correcting Output Codes, pp. 1-4, International Conference in Pattern Recognition, 2008.

Sergio Escalera, Oriol Pujol, and Petia Radeva, Sub-class Error-Correcting Output Codes, pp. 494-504, International Conference on Vision Systems, 2008.

Sergio Escalera, Oriol Pujol, Josepa Mauri, and Petia Radeva, IVUS Tissue Characterization with Sub-class Error-Correcting Output Codes, pp. 1-8, Mathematical Methods for Biomedical Image Analysis, Computer Vision and Pattern Recognition, 2008.

Sergio Escalera, Oriol Pujol, and Petia Radeva, Loss-Weighted Decoding for Error-Correcting Output Coding, vol. 2, pp. 117-122, International Conference on Computer Vision Theory and Applications, 2008.

Sergio Escalera, Oriol Pujol, and Petia Radeva, Traffic Sign Classification using Error Correcting Techniques, pp. 281-285, International Conference on Computer Vision Theory and Applications, 2007.

Alicia Fornés, Sergio Escalera, Josep Lladós, Gemma Sánchez, Petia Radeva, and Oriol Pujol, Handwritten Symbol Recognition by a Boosted Blurred Shape Model with Error Correction, vol. 1, pp. 13-21, Iberian Conference on Pattern Recognition and Image Analysis (IbPRIA), 2007. Best Paper Award, PAIS Newspaper article, IEEE IAPR difusion article, UAB difusion article, Emerging Technology Trends, online Magazine.

Alicia Fornés, Sergio Escalera, Josep Lladós, and Gemma Sánchez, Symbol Recognition by Multi-class Blurred Shape Models, pp. 11-13, IAPR International Workshop on Graphics Recognition, GREC 2007.

Sergio Escalera, Alicia Fornés, Oriol Pujol, Josep Lladós, and Petia Radeva, Multi-class Binary Object Categorization using Blurred Shape Models, pp. 773-782, Iberoamerican Congress on Pattern, CIARP 2007.

Sergio Escalera, Oriol Pujol, and Petia Radeva, Weighted Startegy for Error-Correcting Output Codes, Computer Vision, Advances in Research and Development, pp. 77-82, Computer Vision Center International Workshop, 2007.

Sergio Escalera, Oriol Pujol, and Petia Radeva, Problem-dependent Designs for Error Correcting Output Codes, pp. 13-17, Computer Vision Center International Workshop, 2006.

Sergio Escalera, Oriol Pujol, and Petia Radeva, ECOC-ONE: A novel coding and decoding strategy, vol. 3, pp. 578-581, International Conference on Pattern Recognition, 2006.

Sergio Escalera, Oriol Pujol, and Petia Radeva, Forest Extension of Error Correcting Output Codes and Boosted Landmarks, vol. 4, pp. 104-107, International Conference on Pattern Recognition, 2006.

Sergio Escalera, Oriol Pujol, and Petia Radeva, Optimal Extension of Error Correcting Output Codes, pp. 28-36, Congrés Català en Intel·ligència Artificial, CCIA 2006.

Sergio Escalera, Oriol Pujol, and Petia Radeva, Decoding of Ternary Error Correcting Output Codes, pp. 753-763, Iberoamerican Congress on Pattern, CIARP 2006.

Projects

Multi-class Traffic Sign Classification using Error-Correcting Output Codes

Related topics

Multi-class strategies, large scale learning

Acknowledgements

This work was partially supported by MEC grants TIN2009-14404-C02-02 and CONSOLIDER-INGENIO 2010 (CSD2007-00018).

Advertisements