ABSTRACT
This paper examines the performance of a specific Long-Short Term Memory Recurrent Neural Network for cursive handwriting generation when training with small datasets. The RNN can generate complex structure sequences by predicting one data point at a time. Then, by predicting the overall writing structure, the handwriting can be synthesized. The resulting network can generate different handwriting style parameters.
- Y. Elarian , "Handwriting synthesis: classifications and techniques," Ijdar, vol. 17, (4), pp. 455-469, 2014. . DOI: 10.1007/s10032-014-0231-x.Google ScholarDigital Library
- A. Graves, "Generating Sequences With Recurrent Neural Networks," 2013.Google Scholar
- U. -. Marti and H. Bunke, "The IAM-database: an English sentence database for offline handwriting recognition," Ijdar, vol. 5, (1), pp. 39-46, 2002. . DOI: 10.1007/s100320200071.Google ScholarCross Ref
- Y. Bengio, P. Simard and P. Frasconi, "Learning long-term dependencies with gradient descent is difficult," Tnn, vol. 5, (2), pp. 157-166, 1994. . DOI: 10.1109/72.279181.Google ScholarDigital Library
- S. Hochreiter and J. Schmidhuber, "Long Short-Term Memory," Neural Comput., vol. 9, (8), pp. 1735-1780, 1997. Available: https://doi.org/10.1162/neco.1997.9.8.1735. DOI: 10.1162/neco.1997.9.8.1735.Google ScholarDigital Library
- C. M. Bishop, "Mixture density networks," 1994.Google Scholar
- (). Scribe: Generating Realistic Handwriting with TensorFlow. Available: https://greydanus.github.io/2016/08/21/handwriting/.Google Scholar
- D. Eck and J. Schmidhuber. A first look at music composition using lstm recurrent neural networks. Technical report, IDSIA USI-SUPSI Instituto Dalle Molle.Google Scholar
- N. Boulanger-Lewandowski, Y. Bengio, and P. Vincent. Modeling temporal dependencies in high-dimensional sequences: Application to polyphonic music generation and transcription. In Proceedings of the Twenty-nine International Conference on Machine Learning (ICML’12), 2012.Google Scholar
- I. Sutskever, J. Martens, and G. Hinton. Generating text with recurrent neural networks. In ICML, 2011.Google ScholarDigital Library
- A. Graves and J. Schmidhuber. Offline handwriting recognition with multidimensional recurrent neural networks. In Advances in Neural Information Processing Systems, volume 21, 2008.Google Scholar
Index Terms
- Experiment on Handwriting Generation with Recurrent Neural Networks using Small Datasets
Recommendations
Bangla online handwriting recognition using recurrent neural network architecture
ICVGIP '16: Proceedings of the Tenth Indian Conference on Computer Vision, Graphics and Image ProcessingRecognition of unconstrained handwritten texts is always a difficult problem, particularly if the style of handwriting is a mixed cursive one. Among various Indian scripts, only Bangla has this additional difficulty of tackling mixed cur-siveness of its ...
A recurrent neural network based deep learning model for text and non-text stroke classification in online handwritten Devanagari document
AbstractIt is very common for human beings to include both text and non-text data in a handwritten document. Text portion contains alphabets, digits, and mathematical symbols, whereas non-text portion includes various graphical entities like flow chart, ...
Sequence-to-sequence Bangla Sentence Generation with LSTM Recurrent Neural Networks
AbstractSequence to sequence text generation is the most efficient approach for automatically converting the script of a word from a source sequence to a target sequence. Text generation is the application of natural language generation which is useful in ...
Comments