SCUT-EPT: New Dataset and Benchmark for Offline Chinese Text Recognition in Examination Paper
Authors:
Open Access
- 6 December 2018
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 7, 370-382
Abstract
Most Existing researches and public datasets for handwritten Chinese text recognition base on the regular documents with clean and blank background, lacking research reports for handwritten text recognition on challenging areas such as educational documents and financial bills. In this paper, we focus on examination paper text recognition and construct a challenging dataset named Examination Paper Text (SCUT-EPT) dataset which contains 50,000 text line images (40,000 for training and 10,000 for testing) selected from examination papers of 2,986 volunteers. The proposed SCUT-EPT dataset presents numerous novel challenges, including character erasure, text line supplement, character/phrase switching, noised background, nonuniform word size and unbalanced text length. In our experiments, the current advanced text recognition methods such as convolutional recurrent neural network (CRNN [1]) exhibits poor performance on the proposed SCUT-EPT dataset, proving the challenge and significance of the dataset. Nevertheless, through visualizing and error analysis, we observe that humans can avoid vast majority of the error predictions, which reveals the limitations and drawbacks of current methods for HCTR. Finally, three popular sequence transcription methods: connectionist temporal classification (CTC), attention mechanism, and cascaded attention-CTC are investigated for HCTR problem. It is interesting to observe that although the attention mechanism has been proved to be very effective in English scene text recognition, its performance is far inferior to the CTC method in the case of HCTR with large-scale character set.Keywords
Funding Information
- National Key Research and Development Program of China (2016YFB1001405, GD-NSF 2017A030312006)
- National Natural Science Foundation of China (61673182, 61771199)
- GDSTP (2017A010101027, GZSTP 201607010227)
This publication has 37 references indexed in Scilit:
- Segmentation-free handwritten Chinese text recognition with LSTM-RNN2015
- Fully convolutional networks for semantic segmentation2015
- Minimum-risk training for semi-Markov conditional random fields with application to handwritten Chinese/Japanese text recognitionPattern Recognition, 2014
- Handwritten Chinese/Japanese Text Recognition Using Semi-Markov Conditional Random FieldsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2013
- SCUT-COUCH2009—a comprehensive online unconstrained Chinese handwriting database and benchmark evaluationInternational Journal on Document Analysis and Recognition (IJDAR), 2010
- Chinese character recognition: history, status and prospectsFrontiers of Computer Science in China, 2007
- Connectionist temporal classification2006
- Baseline estimation for Arabic handwritten words2003
- The IAM-database: an English sentence database for offline handwriting recognitionInternational Journal on Document Analysis and Recognition (IJDAR), 2002
- Long Short-Term MemoryNeural Computation, 1997