CASIA Online and Offline Chinese Handwriting Databases

By Chenglin Liu, Fei Yin, Da-Han Wang, Qiu-Feng Wang. IEEE International Conference on Document Analysis and Recognition, 2011

521 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/4d242380d4b7a29b07afdf0df1402297e76b2af4

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Benjamin Graham
2. L. V. D. van der Maaten
3. Yoshua Bengio
4. Jun Du
5. Trevor Darrell
6. Quoc V. Le
7. Li Fei-Fei
8. Dacheng Tao

In Computer Vision and Pattern Recognition

1. Luc Van Gool
2. Dacheng Tao
3. Xiaogang Wang
4. Yoshua Bengio
5. Trevor Darrell
6. Jitendra Malik
7. Ming-Hsuan Yang
8. Andrew Zisserman

Citations in the corpus

• A CNN-Assisted Enhanced Audio Signal Processing for Speech Emotion Recognition (2019, methodology): “[20] proposed a method for SER using a Chinese speech dataset [21] (CASIA), to select hidden emotional features based on correlation and using an extreme learning machine (ELM)-based decision tree for classification.”
• Sparse 3D convolutional neural networks (2015, background): “1 database contains online handwriting samples of the 3755 GBK level-1 Chinese characters [9].”
• Robust Classification with Convolutional Prototype Learning (2018, background): “Online handwriting database (OLHWDB [24]) is a large scale Chinese handwriting dataset.”
• Becoming the expert - interactive multi-class machine teaching (2015, unknown): “Chinese 3 237-240 [26] Butterflies 5 300 Seabed 4 100 Leaves 4 102-150 [24]”
• Continuous Learning of Context-dependent Processing in Neural Networks (2018, methodology): “The offline Chinese handwriting database CASIA-HWDB [59] Large-scale CelebFaces Attributes (CelebA) [37] contains 202599 celebrity face images of 10177 identities, covering a wide range of attitude and background clutter.”
• Spatially-sparse convolutional neural networks (2014, background): “1[11] database contains online handwriting samples of the 3755 GBK level-1 Chinese characters.”
• Submanifold Sparse Convolutional Networks (2017, methodology): “The CASIA dataset [7] contains samples of 3755 GBK level-1 characters with approximately 240 train and 60 test images per class.”
• Fractional Max-Pooling (2014, background): “1 database contains online handwriting samples of the 3755 isolated GBK level-1 Chinese characters (Liu et al., 2011).”
• Teaching Categories to Human Learners with Visual Explanations (2018, methodology): “Chinese Characters Finally, we use a dataset of three different Chinese characters extracted from [22], that was also used in [17].”
• Joint architecture and knowledge distillation in CNN for Chinese text recognition (2019, methodology): “The proposed distillation algorithm is mainly validated on of-fline handwritten Chinese text recognition (HCTR) using the CA-SIA database [21,22] .”
• Online and offline handwritten Chinese character recognition: Benchmarking on new databases (2013, methodology): “The online handwriting database CASIA-OLHWDB (OLHWDB in brief) and the offline database CASIA-HWDB (HWDB in brief), produced by 1020 writers, were released recently for free use in academic research [6].”
• Drawing and Recognizing Chinese Characters with Recurrent Neural Network (2016, methodology): “To train the generative RNN model, we still use the database of CASIA [44] including OLHWDB1.”
• Language-Agnostic Visual Embeddings for Cross-Script Handwriting Retrieval (2026, unknown): “0 [ Liu et al. , 2011 ] .”