Self-supervised writer adaptation using perceptive concepts : application to on-line text recognition

We recently designed a hand-printed text recognizer. The system is based on three set of experts respectively used to segment, classify and validate the text (with a French lexicon : 200K words). We present in this communication writer adaptation methods. The first is supervised by the user. The others are self-supervised strategies which compare classification hypothesis with lexical hypothesis and modify consequently classifier parameters. The last method increases the system accuracy and the classification speed. Experiments are presented on a large database of 90 texts (5400 words) written by 54 different writers and good recognition rates (82%) have been obtained.

[1]  G. M. Reicher.  Perceptual recognition as a function of meaninfulness of stimulus material. , 1969, Journal of experimental psychology.

[2]  R W Schvaneveldt,et al.  An activation--verification model for letter and word recognition: the word-superiority effect. , 1982, Psychological review.

[3]  Yann LeCun,et al.  Writer independent and writer adaptive neural network for on-line character recognition , 1992 .

[4]  Isabelle Guyon,et al.  UNIPEN project of on-line data exchange and recognizer benchmarks , 1994, Proceedings of the 12th IAPR International Conference on Pattern Recognition, Vol. 3 - Conference C: Signal Processing (Cat. No.94CH3440-5).

[5]  Nada Matic,et al.  A Constructive RBF Network for Writer Adaptation , 1996, NIPS.

[6]  Robert L. Stevenson,et al.  Super-resolution from image sequences-a review , 1998, 1998 Midwest Symposium on Circuits and Systems (Cat. No. 98CB36268).

[7]  Robert L. Stevenson,et al.  Simultaneous multi-frame MAP super-resolution video enhancement using spatio-temporal priors , 1999, Proceedings 1999 International Conference on Image Processing (Cat. 99CH36348).

[8]  Anil K. Jain,et al.  Writer adaptation of online handwriting models , 1999, Proceedings of the Fifth International Conference on Document Analysis and Recognition. ICDAR '99 (Cat. No.PR00318).

[9]  Takeo Kanade,et al.  Super-Resolution Optical Flow , 1999 .

[10]  Lionel Prevost,et al.  Modelizing character allographs in omni-scriptor frame: a new non-supervised clustering algorithm , 2000, Pattern Recognit. Lett..

[11]  Takeo Kanade,et al.  Comprehensive database for facial expression analysis , 2000, Proceedings Fourth IEEE International Conference on Automatic Face and Gesture Recognition (Cat. No. PR00580).

[12]  Lionel Prevost,et al.  Dynamic recognition in the omni-writer frame: Application to hand-printed text recognition , 2001, Proceedings of Sixth International Conference on Document Analysis and Recognition.

[13]  Mohan M. Trivedi,et al.  Networked omnivision arrays for intelligent environment , 2001, SPIE Optics + Photonics.

[14]  Gerhard Rigoll,et al.  Comparing adaptation techniques for on-line handwriting recognition , 2001, Proceedings of Sixth International Conference on Document Analysis and Recognition.

[15]  Shmuel Peleg,et al.  Robust super-resolution , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[16]  Andrew Zisserman,et al.  Super-resolution from multiple views using learnt image models , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[17]  Mohan M. Trivedi,et al.  Streaming face recognition using multicamera video arrays , 2002, Object recognition supported by user interaction for service robots.

[18]  Mohan M. Trivedi,et al.  Video arrays for real-time tracking of person, head, and face in an intelligent room , 2003, Machine Vision and Applications.