Template-Instance Loss for Offline Handwritten Chinese Character Recognition

10/12/2019
by   Yao Xiao, et al.
0

The long-standing challenges for offline handwritten Chinese character recognition (HCCR) are twofold: Chinese characters can be very diverse and complicated while similarly looking, and cursive handwriting (due to increased writing speed and infrequent pen lifting) makes strokes and even characters connected together in a flowing manner. In this paper, we propose the template and instance loss functions for the relevant machine learning tasks in offline handwritten Chinese character recognition. First, the character template is designed to deal with the intrinsic similarities among Chinese characters. Second, the instance loss can reduce category variance according to classification difficulty, giving a large penalty to the outlier instance of handwritten Chinese character. Trained with the new loss functions using our deep network architecture HCCR14Layer model consisting of simple layers, our extensive experiments show that it yields state-of-the-art performance and beyond for offline HCCR.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/10/2014

Handwritten Character Recognition In Malayalam Scripts- A Review

Handwritten character recognition is one of the most challenging and ong...
research
09/01/2013

Multi-Column Deep Neural Networks for Offline Handwritten Chinese Character Classification

Our Multi-Column Deep Neural Networks achieve best known recognition rat...
research
11/15/2018

Deep Template Matching for Offline Handwritten Chinese Character Recognition

Just like its remarkable achievements in many computer vision tasks, the...
research
08/30/2019

Handwritten Chinese Character Recognition by Convolutional Neural Network and Similarity Ranking

Convolution Neural Networks (CNN) have recently achieved state-of-the ar...
research
04/13/2020

Embedded Large-Scale Handwritten Chinese Character Recognition

As handwriting input becomes more prevalent, the large symbol inventory ...
research
12/24/2018

Writer-Aware CNN for Parsimonious HMM-Based Offline Handwritten Chinese Text Recognition

Recently, the hybrid convolutional neural network hidden Markov model (C...
research
09/21/2018

Zero-calibration cVEP BCI using word prediction: a proof of concept

Brain Computer Interfaces (BCIs) based on visual evoked potentials (VEP)...

Please sign up or login with your details

Forgot password? Click here to reset