2016
DOI: 10.1016/j.patcog.2015.07.007
|View full text |Cite
|
Sign up to set email alerts
|

Discriminative quadratic feature learning for handwritten Chinese character recognition

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

0
20
0

Year Published

2016
2016
2023
2023

Publication Types

Select...
6
2
1

Relationship

1
8

Authors

Journals

citations
Cited by 31 publications
(20 citation statements)
references
References 35 publications
0
20
0
Order By: Relevance
“…In [14], a character boundaries preserved filter was used for noise removal, which is a stroke's width information based anisotropic diffusion filter, and can preserved characters structure well. Because of effects on de-noising, features of Chinese characters are widely employed in Chinese character recognition [19], Chinese character categorization [13] and Chinese character segmentation [11].…”
Section: Related Workmentioning
confidence: 99%
“…In [14], a character boundaries preserved filter was used for noise removal, which is a stroke's width information based anisotropic diffusion filter, and can preserved characters structure well. Because of effects on de-noising, features of Chinese characters are widely employed in Chinese character recognition [19], Chinese character categorization [13] and Chinese character segmentation [11].…”
Section: Related Workmentioning
confidence: 99%
“…The traditional works of Chinese character recognition follow the basic pipeline of shape normalisation [146,147], feature extraction, dimension reduction, and classification [148]. The authors in [148] utilise gradient direction histograms as original features. The quadratic feature expansion combined with discriminative dimensionality reduction makes the original features non-linear and discriminative.…”
Section: Comparison With Other Languagesmentioning
confidence: 99%
“…To improve the HCR accuracy, traditional methods including the modified quadratic discriminant function (MQDF) [31] and the graphical lasso quadratic discriminant function (GLQDF) [32] have successfully been used to improve recognition accuracy. Graham used DeepCNet [33] based on DCNNs with good effect at ICDAR 2013 [34], which is the premier competition for document analysis and recognition, and is a Chinese handwritten character recognition competition.…”
Section: Related Workmentioning
confidence: 99%