Log In Sign Up

Handwritten Chinese Character Recognition by Convolutional Neural Network and Similarity Ranking

by   Junyi Zou, et al.

Convolution Neural Networks (CNN) have recently achieved state-of-the art performance on handwritten Chinese character recognition (HCCR). However, most of CNN models employ the SoftMax activation function and minimize cross entropy loss, which may cause loss of inter-class information. To cope with this problem, we propose to combine cross entropy with similarity ranking function and use it as loss function. The experiments results show that the combination loss functions produce higher accuracy in HCCR. This report briefly reviews cross entropy loss function, a typical similarity ranking function: Euclidean distance, and also propose a new similarity ranking function: Average variance similarity. Experiments are done to compare the performances of a CNN model with three different loss functions. In the end, SoftMax cross entropy with Average variance similarity produce the highest accuracy on handwritten Chinese characters recognition.


page 1

page 2

page 3

page 4


Template-Instance Loss for Offline Handwritten Chinese Character Recognition

The long-standing challenges for offline handwritten Chinese character r...

What's in a Loss Function for Image Classification?

It is common to use the softmax cross-entropy loss to train neural netwo...

σ^2R Loss: a Weighted Loss by Multiplicative Factors using Sigmoidal Functions

In neural networks, the loss function represents the core of the learnin...

Maximum Entropy Regularization and Chinese Text Recognition

Chinese text recognition is more challenging than Latin text due to the ...

Steganalysis of Image with Adaptively Parametric Activation

Steganalysis as a method to detect whether image contains se-cret messag...

Multiscale Softmax Cross Entropy for Fovea Localization on Color Fundus Photography

Fovea localization is one of the most popular tasks in ophthalmic medica...

Chi-square Loss for Softmax: an Echo of Neural Network Structure

Softmax working with cross-entropy is widely used in classification, whi...