Building Efficient CNN Architecture for Offline Handwritten Chinese Character Recognition

04/04/2018
by   Zhiyuan Li, et al.
0

Deep convolutional networks based methods have brought great breakthrough in images classification, which provides an end-to-end solution for handwritten Chinese character recognition(HCCR) problem through learning discriminative features automatically. Nevertheless, state-of-the-art CNNs appear to incur huge computation cost, and require the storage of a large number of parameters especially in fully connected layers, which is difficult to deploy such networks into alternative hardware device with the limit of computation amount. To solve the storage problem, we propose a novel technique called Global Weighted Arverage Pooling for reducing the parameters in fully connected layer without loss in accuracy. Besides, we implement a cascaded model in single CNN by adding mid output layer to complete recognition as early as possible, which reduces average inference time significantly. Experiments were performed on the ICDAR-2013 offline HCCR dataset, and it is found that the proposed approach only needs 6.9ms for classfying a chracter image on average, and achieves the state-of-the-art accuracy of 97.1

READ FULL TEXT
research
12/30/2018

A High-Performance CNN Method for Offline Handwritten Chinese Character Recognition and Visualization

Recent researches introduced fast, compact and efficient convolutional n...
research
02/26/2017

Building Fast and Compact Convolutional Neural Networks for Offline Handwritten Chinese Character Recognition

Like other problems in computer vision, offline handwritten Chinese char...
research
05/15/2017

Design of a Very Compact CNN Classifier for Online Handwritten Chinese Character Recognition Using DropWeight and Global Pooling

Currently, owing to the ubiquity of mobile devices, online handwritten C...
research
01/15/2021

Convolutional Neural Network with Pruning Method for Handwritten Digit Recognition

CNN model is a popular method for imagery analysis, so it could be utili...
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
12/17/2019

Joint Architecture and Knowledge Distillation in Convolutional Neural Network for Offline Handwritten Chinese Text Recognition

The technique of distillation helps transform cumbersome neural network ...
research
12/31/2015

Exploiting Local Structures with the Kronecker Layer in Convolutional Networks

In this paper, we propose and study a technique to reduce the number of ...

Please sign up or login with your details

Forgot password? Click here to reset