ICDAR 2013 Chinese Handwriting Recognition Competition

By Fei Yin, Qiu-Feng Wang, Xu-Yao Zhang, Chenglin Liu. 2013

321 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

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

In Computer Vision and Pattern Recognition

Citations in the corpus

Deep learning in neural networks: An overview (2014, background): “19) with almost human performance (Ciresan and Schmidhuber, 2013); compare (Yin et al., 2013).”
Continual learning of context-dependent processing in neural networks (2018, positive): “We found that a classifier trained with the OWM could learn to recognize all 3,755 characters sequentially, with a final accuracy ∼ 92% closely approaching the results obtained in human performance when recognizing handwritten Chinese characters (∼ 96%) [28].”
Within the Lack of Chest COVID-19 X-ray Dataset: A Novel Detection Model Based on GAN and Deep Transfer Learning (2020, background): “[28,29] showed how CNNs based on Graphics Processing Unit (GPU) can enhance many vision benchmark records such as MNIST [30], Chinese characters [31], Arabic digits recognition [32], Arabic handwritten characters recognition [33], NORB (jittered, cluttered) [34], tra ﬃ c signs [35], and large-scale…”
Drawing and Recognizing Chinese Characters with Recurrent Neural Network (2016, methodology): “Regularization is important for improving the generalization performance of deep neural network.”
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] .”
Handwritten Optical Character Recognition (OCR): A Comprehensive Systematic Literature Review (SLR) (2020, methodology): “[53] proposed ICDAR 2013 competition which received 27 systems for 5 tasks – classification on extracted feature data, online/offline isolated character recognition and online/offline handwritten text recognition.”
Robust Classification with Convolutional Prototype Learning (2018, background): “Following the settings in [40] and [39], the training and test datasets include 2,697,673 and 224,590 samples respectively, which are come from 3755 classes.”
Multi-Column Deep Neural Networks for Offline Handwritten Chinese Character Classification (2013, methodology): “We use several MCDNN architectures to classify handwritten Chinese characters from the dataset used at ICDAR 2011 [8] and 2013 [9] competitions.”
Continuous Learning of Context-dependent Processing in Neural Networks (2018, background): “We found that, combined with a pre-trained feature extractor (Table 1), a classifier trained with OWM could learn to recognize all 3755 characters sequentially, resulted in the final recognition accuracy of 93% across all classes (Table 1), which was very close to human’s performance in recognizing ”
High performance offline handwritten Chinese character recognition using GoogLeNet and directional feature maps (2015, methodology): “For the testing 3755 classes of CompetitionDB, the recognition rate with AlexNet we obtained was 95.49%, whereas the recognition rate with HCCR-GoogLeNet was 96.26%.”
Sketch-a-Net: A Deep Neural Network that Beats Humans (2016, background): “While the optical character recognition (OCR) community has exploited stroke ordering with some success (Yin et al, 2013), exploiting sequential information is harder on sketches – handwriting characters have relatively fixed structural ordering; while sketches exhibit a much higher degree of…”