Segmentation-free handwritten Chinese text recognition with LSTM-RNN
| Autor: | Ronaldo Messina, Jérôme Louradour |
|---|---|
| Rok vydání: | 2015 |
| Předmět: |
Noisy text analytics
Computer science business.industry Speech recognition Text recognition computer.software_genre Image (mathematics) Task (project management) Recurrent neural network ComputingMethodologies_DOCUMENTANDTEXTPROCESSING Segmentation Artificial intelligence business computer Natural language processing |
| Zdroj: | ICDAR |
| DOI: | 10.1109/icdar.2015.7333746 |
| Popis: | We present initial results on the use of Multi-Dimensional Long-Short Term Memory Recurrent Neural Networks (MDLSTM-RNN) in recognizing lines of handwritten Chinese text without explicit segmentation of the characters. In fact, most of Chinese text recognizers in the literature perform a pre-segmentation of text image into characters. This can be a drawback, as explicit segmentation is an extra step before recognizing the text, and the errors made at this stage have direct impact on the performance of the whole system. MDLSTM-RNN is now a state-of-the-art technology that provides the best performance on languages with Latin and Arabic characters, hence we propose to apply RNN on Chinese text recognition. Our results on the data from the Task 4 in ICDAR 2013 competition for handwritten Chinese recognition are comparable in performance with the best reported systems. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|