TY - GEN
T1 - CNN-N-Gram for HandwritingWord Recognition
AU - Poznanski, Arik
AU - Wolf, Lior
N1 - Publisher Copyright:
© 2016 IEEE.
PY - 2016/12/9
Y1 - 2016/12/9
N2 - Given an image of a handwritten word, a CNN is employed to estimate its n-gram frequency profile, which is the set of n-grams contained in the word. Frequencies for unigrams, bigrams and trigrams are estimated for the entire word and for parts of it. Canonical Correlation Analysis is then used to match the estimated profile to the true profiles of all words in a large dictionary. The CNN that is used employs several novelties such as the use of multiple fully connected branches. Applied to all commonly used handwriting recognition benchmarks, our method outperforms, by a very large margin, all existing methods.
AB - Given an image of a handwritten word, a CNN is employed to estimate its n-gram frequency profile, which is the set of n-grams contained in the word. Frequencies for unigrams, bigrams and trigrams are estimated for the entire word and for parts of it. Canonical Correlation Analysis is then used to match the estimated profile to the true profiles of all words in a large dictionary. The CNN that is used employs several novelties such as the use of multiple fully connected branches. Applied to all commonly used handwriting recognition benchmarks, our method outperforms, by a very large margin, all existing methods.
UR - http://www.scopus.com/inward/record.url?scp=84986260192&partnerID=8YFLogxK
U2 - 10.1109/CVPR.2016.253
DO - 10.1109/CVPR.2016.253
M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???
AN - SCOPUS:84986260192
T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
SP - 2305
EP - 2314
BT - Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016
PB - IEEE Computer Society
T2 - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016
Y2 - 26 June 2016 through 1 July 2016
ER -