Conferencia

Goussies, N.A.; Ubalde, S.; Fernández, F.G.; Mejail, M.E. "Optical character recognition using transfer learning decision forests" (2014) 2014 IEEE International Conference on Image Processing, ICIP 2014:4309-4313
Estamos trabajando para incorporar este artículo al repositorio
Consulte el artículo en la página del editor

Abstract:

In this paper, we present a novel method for transfer learning which uses decision forests, and we apply it to recognize characters. We introduce two extensions into the decision forest framework in order to transfer knowledge from the source tasks to a given target task. We show that both of them are important to achieve higher recognition rates. Our experiments demonstrate improvements over traditional decision forests in the MNIST dataset. They also compare favorably against other state-of-the-art classifiers. © 2014 IEEE.

Registro:

Documento: Conferencia
Título:Optical character recognition using transfer learning decision forests
Autor:Goussies, N.A.; Ubalde, S.; Fernández, F.G.; Mejail, M.E.
Filiación:Departamento de Computacion, FCEyN, Universidad de Buenos Aires, Argentina
Palabras clave:decision forests; OCR; transfer learning; Character recognition; Image processing; Learning algorithms; Optical character recognition; Optical data processing; Decision forest; State of the art; Transfer learning; Forestry
Año:2014
Página de inicio:4309
Página de fin:4313
DOI: http://dx.doi.org/10.1109/ICIP.2014.7025875
Título revista:2014 IEEE International Conference on Image Processing, ICIP 2014
Título revista abreviado:IEEE Int. Conf. Image Process., ICIP
Registro:https://bibliotecadigital.exactas.uba.ar/collection/paper/document/paper_97814799_v_n_p4309_Goussies

Referencias:

  • Lecun, Y., Bottou, L., Bengio, Y., Haffner, P., Gradient-based learning applied to document recognition (1998) Proceedings of the IEEE, pp. 2278-2324
  • Grosicki, E., El Abed, H., Icdar 2011-french handwriting recognition competition (2011) ICDAR, pp. 1459-1463
  • Tommasi, T., Orabona, F., Caputo, B., Learning categories from few examples with multi model knowledge transfer (2013) TPAMI
  • Jialin Pan, S., Yang, Q., A survey on transfer learning (2010) IEEE Transactions on Knowledge and Data Engineering, 22 (10), pp. 1345-1359. , October
  • Breiman, L., Random forests (2001) Machine Learning
  • Criminisi, K.A.E., Shotton, J., Decision forests: A unified framework for classification, regression, density estimation, manifold learning and semi-supervised learning (2012) Foundations and Trends in Computer Graphics and Vision, 7 (2-3), pp. 81-227
  • Sharp, T., Implementing decision trees and forests on a gpu (2008) ECCV, 2008, pp. 595-608
  • Levi, K., Fink, M., Weiss, Y., Learning from a small number of training examples by exploiting object categories (2004) CVPRW, pp. 96-102
  • Sudderth, E.B., Torralba, A., Freeman, W.T., Willsky, A.S., Learning hierarchical models of scenes, objects, and parts (2005) ICCV, pp. 1331-1338
  • Torralba, A., Murphy, K.P., Freeman, W.T., Sharing visual features for multiclass and multiview object detection (2007) TPAMI, 29 (5), pp. 854-869
  • Quattoni, A., Collins, M., Darrell, T., Transfer learning for image classification with sparse prototype representations (2008) CVPR, pp. 1-8
  • Lim, J.J., Salakhutdinov, R., Torralba, A., Transfer learning by borrowing examples for multiclass object detection (2011) NIPS
  • Dai, W., Yang, Q., Xue, G., Yu, Y., Boosting for transfer learning (2007) Proceedings of the 24th International Conference on Machine Learning, pp. 193-200. , New York, NY, USA,ICML '07,ACM
  • Yao, Y., Doretto, G., Boosting for transfer learning with multiple sources (2010) CVPR, pp. 1855-1862
  • Leistner, C., Saffari, A., Santner, J., Bischof, H., Semi-supervised random forests (2009) ICCV, 2009, pp. 506-513
  • Pei, Y., Kim, T., Zha, H., Unsupervised random forest manifold alignment for lipreading (2013) ICCV
  • Won Lee, J., Giraud-Carrier, C., Transfer learning in decision trees (2007) IJCNN
  • Ross Quinlan, J., Induction of decision trees (1986) Machine Learning, 1 (1), pp. 81-106
  • Baptiste Faddoul, J., Chidlovskii, B., Gilleron, R., Torre, F., Learning multiple tasks with boosted decision trees (2012) ECML/PKDD
  • Quadrianto, N., Smola, A.J., Caetano, T., Petterson, V.J.S.V.N., Multitask learning without label correspondences (2010) NIPS

Citas:

---------- APA ----------
Goussies, N.A., Ubalde, S., Fernández, F.G. & Mejail, M.E. (2014) . Optical character recognition using transfer learning decision forests. 2014 IEEE International Conference on Image Processing, ICIP 2014, 4309-4313.
http://dx.doi.org/10.1109/ICIP.2014.7025875
---------- CHICAGO ----------
Goussies, N.A., Ubalde, S., Fernández, F.G., Mejail, M.E. "Optical character recognition using transfer learning decision forests" . 2014 IEEE International Conference on Image Processing, ICIP 2014 (2014) : 4309-4313.
http://dx.doi.org/10.1109/ICIP.2014.7025875
---------- MLA ----------
Goussies, N.A., Ubalde, S., Fernández, F.G., Mejail, M.E. "Optical character recognition using transfer learning decision forests" . 2014 IEEE International Conference on Image Processing, ICIP 2014, 2014, pp. 4309-4313.
http://dx.doi.org/10.1109/ICIP.2014.7025875
---------- VANCOUVER ----------
Goussies, N.A., Ubalde, S., Fernández, F.G., Mejail, M.E. Optical character recognition using transfer learning decision forests. IEEE Int. Conf. Image Process., ICIP. 2014:4309-4313.
http://dx.doi.org/10.1109/ICIP.2014.7025875