A Discriminative Cascade CNN Model for Offline Handwritten Digit Recognition

被引：0

作者：

Pan, Shulan ^{[1
]}

Wang, Yanwei

Liu, Changsong

Ding, Xiaoqing

机构：

[1] Tsinghua Univ, Dept Elect Engn, State Key Lab Intelligent Technol, Beijing, Peoples R China

来源：

2015 14TH IAPR INTERNATIONAL CONFERENCE ON MACHINE VISION APPLICATIONS (MVA) | 2015年

关键词：

D O I：

暂无

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

This paper presents a high-performance two-stage cascade CNN model. The main idea behind the cascade CNN model is complementary classification objectives between Stage I and Stage II. Discriminative learning is introduced to train Stage II by feeding back poorly recognized training samples. Experiments have been conducted on the competitive MNIST handwritten digit database. The cascade model achieved the best state-of-the-art performance with an error rate of 0.18%.

引用

页码：501 / 504

页数：4

共 50 条

[1] FPGA Implementation of CNN for Handwritten Digit Recognition
Xiao, Rui
Shi, Junsheng
Zhang, Chao
[J]. PROCEEDINGS OF 2020 IEEE 4TH INFORMATION TECHNOLOGY, NETWORKING, ELECTRONIC AND AUTOMATION CONTROL CONFERENCE (ITNEC 2020), 2020, : 1128 - 1133
[2] Discriminative Bernoulli Mixture Models for Handwritten Digit Recognition
Gimenez, Adria
Andres-Ferrer, J.
Juan, Alfons
Serrano, Nicolas
[J]. 11TH INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION (ICDAR 2011), 2011, : 558 - 562
[3] Feature Map Reduction in CNN for Handwritten Digit Recognition
Chakraborty, Sinjan
Paul, Sayantan
Sarkar, Ram
Nasipuri, Mita
[J]. RECENT DEVELOPMENTS IN MACHINE LEARNING AND DATA ANALYTICS, 2019, 740 : 143 - 148
[4] A SS-CNN on an FPGA for Handwritten Digit Recognition
Si, Jiong
Yfantis, Evangelos
Harris, Sarah L.
[J]. 2019 IEEE 10TH ANNUAL UBIQUITOUS COMPUTING, ELECTRONICS & MOBILE COMMUNICATION CONFERENCE (UEMCON), 2019, : 88 - 93
[5] Hybrid CNN-GRU Model for High Efficient Handwritten Digit Recognition
Vantruong Nguyen
Cai, Jueping
Chu, Jie
[J]. 2019 2ND INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND PATTERN RECOGNITION (AIPR 2019), 2019, : 66 - 71
[6] An MQDF-CNN Hybrid Model for Offline Handwritten Chinese Character Recognition
Wang, Yanwei
Li, Xin
Liu, Changsong
Ding, Xiaoqing
Chen, Youxin
[J]. 2014 14TH INTERNATIONAL CONFERENCE ON FRONTIERS IN HANDWRITING RECOGNITION (ICFHR), 2014, : 246 - 249
[7] Offline handwritten character recognition based on discriminative training of orthogonal gaussian mixture model
Zhang, R
Ding, XQ
Zhang, JY
[J]. SIXTH INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION, PROCEEDINGS, 2001, : 221 - 225
[8] Hybrid CNN-SVM Classifier for Handwritten Digit Recognition
Ahlawat, Savita
Choudhary, Amit
[J]. INTERNATIONAL CONFERENCE ON COMPUTATIONAL INTELLIGENCE AND DATA SCIENCE, 2020, 167 : 2554 - 2560
[9] Multiclass Recognition of Offline Handwritten Devanagari Characters using CNN
Bisht, Mamta
Gupta, Richa
[J]. INTERNATIONAL JOURNAL OF MATHEMATICAL ENGINEERING AND MANAGEMENT SCIENCES, 2020, 5 (06) : 1429 - 1439
[10] An Improved Feature Extraction Method for Individual Offline Handwritten Digit Recognition
Wang Qinghui
Yang Aiping
Dai Wenzhan
[J]. 2010 8TH WORLD CONGRESS ON INTELLIGENT CONTROL AND AUTOMATION (WCICA), 2010, : 6327 - 6330

← 1 2 3 4 5 →