High Performance Offline Handwritten Chinese Text Recognition with a New Data Preprocessing and Augmentation Pipeline

Xie, Canyu; Lai, Songxuan; Liao, Qianying; Jin, Lianwen

doi:10.1007/978-3-030-57058-3_4

Cited by 18 publications

(19 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the experiment, we compared our method against four well know offline handwriting text recognition methods [8,9,11,12,14,17]. These methods involve text recognition technologies such as traditional character over-segmentation, CNN and CNN-LSTM, and they have all shown their advantages in their respective aspects.…”

Section: A Experimental Preparationmentioning

confidence: 99%

“…Levenstein edit distance [41] is used to measure the performance of the model on character level, and through the length of the label sequence to achieve normalization, which is commonly known as Character Error Rate (CER). In this paper, based on the literature [7,9,12,14], the accurate rate (AR) and correct rate (CR) are employed to evaluate our model. Their formal expressions are as follows:…”

Section: A Experimental Preparationmentioning

confidence: 99%

“…One recent approach utilized recurrent neural networks(RNN) for the recognition of handwritten English languages with small number of character categories. The RNN approach is quite flexible and it avoids explicit segmentation which is largely due to the connectionist temporal classification(CTC) [12]. Suryani et al [13] employed a CNN and LSTM under the HMM frame work to obtain a significant improvement over the traditional LSTM-HMM model.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Residual-Attention Offline Handwritten Chinese Text Recognition Based on Fully Convolutional Neural Networks

Wang¹,

Yang

Ding

et al. 2021

IEEE Access

View full text Add to dashboard Cite

Offline handwritten Chinese text recognition is one of the most challenging tasks in that it involves various writing styles, complex character-touching, and large number of character categories. In this paper, we propose a residual-attention offline handwritten Chinese text recognition based on fully convolutional neural networks, which is segmentation-free handwritten recognition that avoids the impact of incorrect character segmentation. By designing a smart residual attention gate block, our model can help to extract important features, and effectively implement the training of deep convolutional neural networks. Furthermore, we deploy an expansion factor to indicate the trade-off between computing resources for model training and the ability of a gradient to propagate across multiple layers, and make our model training adapt to different computing platforms. Experiments on the CASIA-HWDB and ICDAR-2013 competition dataset show that our method achieves a competitive performance on offline handwritten Chinese text recognition. On the CASIA-HWDB test set, the character-level accurate rate and correct rate achieve 97.32% and 97.90% respectively. INDEX TERMSOffline handwritten recognition, Convolutional neural networks, Connectionist temporal classification, Residual attention.

show abstract

Section: A Experimental Preparationmentioning

confidence: 99%

Section: A Experimental Preparationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Residual-Attention Offline Handwritten Chinese Text Recognition Based on Fully Convolutional Neural Networks

Wang¹,

Yang

Ding

et al. 2021

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Handwritten Chinese text recognition (HCTR) has been studied for decades (Graves et al, 2009;Wang et al, 2012;Zhou et al, 2013;Keysers et al, 2017;Zhang et al, 2018). However, most previous studies (Yin et al, 2013;Wang et al, 2012Wang et al, , 2016Peng et al, 2019;Su et al, 2009;Du et al, 2016;Wang et al, 2018Wang et al, , 2020aMessina and Louradour, 2015;Xie et al, 2020;Xiu et al, 2019;Xie et al, 2019b;Wang et al, 2020b;Zhu et al, 2020;Luo et al, 2021;Rodriguez-Serrano et al, 2015;Jaderberg et al, 2016) assume that text line detection is provided by annotations and only focus on the recognition of cropped text line images. Although the accuracy of these line-level methods seems to be sufficient when combined with language models, they are limited to the one-dimensional distribution of characters and are significantly affected by the accuracy of text line detection in real-world applications.…”

Section: Introductionmentioning

confidence: 99%

PageNet: Towards End-to-End Weakly Supervised Page-Level Handwritten Chinese Text Recognition

et al. 2022

Self Cite

View full text Add to dashboard Cite

Handwritten Chinese text recognition (HCTR) has been an active research topic for decades. However, most previous studies solely focus on the recognition of cropped text line images, ignoring the error caused by text line detection in real-world applications. Although some approaches aimed at page-level text recognition have been proposed in recent years, they either are limited to simple layouts or require very detailed annotations including expensive line-level and even character-level bounding boxes. To this end, we propose PageNet for end-to-end weakly supervised page-level HCTR. PageNet detects and recognizes characters and predicts the reading order between them, which is more robust and flexible when dealing with complex layouts including multidirectional and curved text lines. Utilizing the proposed weakly supervised learning framework, PageNet requires only transcripts to be annotated for real data; however, it can still output detection and recognition results at both the character and line levels, avoiding the labor and cost of labeling bounding boxes of characters and text lines. Extensive experiments conducted on five datasets demonstrate the superiority of PageNet over existing weakly supervised and fully supervised page-level methods. These experimental results may spark further research beyond the realms of existing methods based on connectionist temporal classification or attention. The source code is available at https://github.com/shannanyinxiang/PageNet.

show abstract

“…Messina et al [3] proposed multidimensional long-short term memory recurrent neural networks (MDLSTM-RNN) using Connectionist Temporal Classifier [4](CTC) as loss function for end-to-end text line recognition. Xie et al [5] proposed a CNN-ResLSTM model with a data preprocessing and augmentation pipeline to rectify the text pictures to optimize recognition. Xiao et al [6] proposed a deep network with Pixel-Level Rectification to integrate pixel-level rectification into CNN and RNN-based recognizers.…”

Section: Introductionmentioning

confidence: 99%

Robust End-to-End Offline Chinese Handwriting Text Page Spotter with Text Kernel

Wang¹,

Yu²,

Wang³

et al. 2021

Preprint

View full text Add to dashboard Cite

Offline Chinese handwriting text recognition is a long-standing research topic in the field of pattern recognition. In previous studies, text detection and recognition are separated, which leads to the fact that text recognition is highly dependent on the detection results. In this paper, we propose a robust end-to-end Chinese text page spotter framework. It unifies text detection and text recognition with text kernel that integrates global text feature information to optimize the recognition from multiple scales, which reduces the dependence of detection and improves the robustness of the system. Our method achieves state-of-the-art results on the CASIA-HWDB2.0-2.2 dataset and ICDAR-2013 competition dataset. Without any language model, the correct rates are 99.12% and 94.27% for line-level recognition, and 99.03% and 94.20% for page-level recognition, respectively. Code will be available at GitHub.

show abstract

High Performance Offline Handwritten Chinese Text Recognition with a New Data Preprocessing and Augmentation Pipeline

Cited by 18 publications

References 23 publications

A Residual-Attention Offline Handwritten Chinese Text Recognition Based on Fully Convolutional Neural Networks

A Residual-Attention Offline Handwritten Chinese Text Recognition Based on Fully Convolutional Neural Networks

PageNet: Towards End-to-End Weakly Supervised Page-Level Handwritten Chinese Text Recognition

Robust End-to-End Offline Chinese Handwriting Text Page Spotter with Text Kernel

Contact Info

Product

Resources

About