Deep template matching for offline handwritten Chinese character recognition

Abstract

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.

Keywords

• learning (artificial intelligence)
• handwritten character recognition
• image classification
• feature extraction
• computer vision
• convolutional neural nets
• offline handwritten chinese character recognition
• deep template
• icdar-2013 offline hccr datasets
• training set
• predictive power
• powerful discriminative features
• training process
• simple binary classification problem
• template images
• siamese neural network
• image recognition
• convolutional neural networks
• computer vision tasks
• remarkable achievements