Deep template matching for offline handwritten Chinese character recognition

Just like its remarkable achievements in many computer vision tasks, the convolutional neural networks provide an end-to-end solution in handwritten Chinese character recognition (HCCR) with great success. However, the process of learning discriminative features for image recognition is difficult in...

Celý popis

Uložené v:

Podrobná bibliografia
Vydané v:	Journal of engineering (Stevenage, England) Ročník 2020; číslo 4; s. 120 - 124
Hlavní autori:	Li, Zhiyuan, Xiao, Yi, Wu, Qi, Jin, Min, Lu, Huaxiang
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	The Institution of Engineering and Technology 01.04.2020 Wiley
Predmet:	computer vision computer vision tasks convolutional neural nets convolutional neural networks deep template feature extraction handwritten character recognition ICDAR‐2013 offline HCCR datasets image classification image recognition learning (artificial intelligence) offline handwritten Chinese character recognition powerful discriminative features predictive power remarkable achievements Research Article Siamese neural network simple binary classification problem template images training process training set ICDAR-2013 offline HCCR datasets training set handwritten character recognition image classification offline handwritten Chinese character recognition deep template template images computer vision tasks training process predictive power Siamese neural network feature extraction simple binary classification problem computer vision remarkable achievements convolutional neural nets convolutional neural networks learning (artificial intelligence) image recognition powerful discriminative features
ISSN:	2051-3305, 2051-3305
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!

Popis
Shrnutí:	Just like its remarkable achievements in many computer vision tasks, the convolutional neural networks provide an end-to-end solution in handwritten Chinese character recognition (HCCR) with great success. However, the process of learning discriminative features for image recognition is difficult in cases where little data is available. In this study, the authors propose a novel method for learning siamese neural network which employs a special structure to predict the similarity between handwritten Chinese characters and template images. The optimisation of siamese neural network can be treated as a simple binary classification problem. When the training process finished, the powerful discriminative features will help to generalise the predictive power not just to new data, but to entirely new classes that never appear in the training set. Experiments performed on the ICDAR-2013 offline HCCR datasets have shown that the proposed method has a very promising generalisation ability for new classes that never appear in the training set.
ISSN:	2051-3305 2051-3305
DOI:	10.1049/joe.2019.0895