激光与光电子学进展, 2019, 56 (7): 072001, 网络出版: 2019-07-30 复制并引用该论文  本文已被引 7 次  被引通知

图 & 表

图 1. 101种符号类别分布图

Fig. 1. Class distribution of 101 symbols

下载图片 查看原文

图 2. 原始图像通过弹性失真模型后随机生成的图像。(a)原始图像;(b)第一次随机生成的图像;(c)第二次随机生成的图像

Fig. 2. Images randomly generated after original images passing through elastic distortion model. (a) Original images; (b) images randomly generated for first time; (c) images randomly generated for second time

下载图片 查看原文

图 3. DenseNet-SE网络结构图

Fig. 3. Structural diagram of DenseNet-SE network

下载图片 查看原文

图 4. 稠密残差块模块构造图

Fig. 4. Structural diagram of residual-dense block module

下载图片 查看原文

图 5. DenseNet和DenseNet-SE准确率的比较

Fig. 5. Validation accuracy comparison of DenseNet and DenseNet-SE

下载图片 查看原文

图 6. DenseNet-SE测试集和验证集的准确率比较

Fig. 6. Accuracy comparison of DenseNet-SE test set and validation set

下载图片 查看原文

图 7. CROHME2016测试集中误判类型的符号

Fig. 7. Symbols of misjudgment types in CROHME2016 test set

下载图片 查看原文

表 1CROHME实验数据集的分布

Table1. Distribution of CROHME experimental datasets

Dividing dataset Dataset category Image size /(cm×cm) Scale Previous quantity Twisted quantity Train CROHME2016 train 48×48 85802 321301 Validation CROHME2013 test 48×48 6082 — Test CROHME2016 test 48×48 10019 — CROHME2014 test 48×48 10061 —

查看原文

表 2测试一个epoch所需的时间和准确率

Table2. Time consumption and accuracy for each epoch test

Model Traintime /s Trainbatch /s Validationaccuracy /% DenseNet 307 0.112 91.08 DenseNet-SE 406 0.123 95.31

查看原文

表 3所提方法与不同种类系统的比较

Table3. Comparison between proposed method and different types of systems

System CROHME2014 testaccuracy /% CROHME2016 testaccuracy /% Featureused Ref. [6] 91.04 92.81 Online+offline Ref. [5] 91.28 92.27 Online+offline Ref. [3] 91.24 - Online+offline Ref. [4] 88.66 88.85 Online+offline Ref. [8] 87.72 - Offline Ref. [7] 91.82 92.42 Offline Proposed 93.38 92.93 Offline

查看原文

表 4CROHME2016 中排行前10的符号错误判别类型

Table4. Symbols of TOP-10 error discrimination types in CROHME2016

No. Symbollabel Totalsymbols Percentage ofnumber ofmisclassifiedsymbols /% 1 o 11 100 2 ρrime 11 100 3 C 31 96.77 4 τimes 72 88.89 5 Y 13 76.92 6 COMMA 82 76.83 7 s 21 71.43 8 . 21 71.43 9 ιn 3 66.67 10 r 40 65.00

查看原文

方定邦, 冯桂, 曹海燕, 杨恒杰, 韩雪, 易银城. 基于多特征卷积神经网络的手写公式符号识别[J]. 激光与光电子学进展, 2019, 56(7): 072001. Dingbang Fang, Gui Feng, Haiyan Cao, Hengjie Yang, Xue Han, Yincheng Yi. Handwritten Formula Symbol Recognition Based on Multi-Feature Convolutional Neural Network[J]. Laser & Optoelectronics Progress, 2019, 56(7): 072001.