Segmentation-Free Approaches for Handwritten Numeral String Recognition

被引：0

作者：

Hochuli, Andre G. ^{[1
]}

Oliveira, Luiz S. ^{[1
]}

Britto Jr, Alceu de Souza ^{[2
]}

Sabourin, Robert ^{[3
]}

机构：

[1] Univ Fed Parana, Dept Informat Dinf, Curitiba, Parana, Brazil

[2] Pontificia Univ Catolica Parana, PPGIA, Curitiba, Parana, Brazil

[3] Ecole Technol Super, Montreal, PQ, Canada

来源：

2018 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN) | 2018年

关键词：

SELECTION;

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper presents segmentation-free strategies for the recognition of handwritten numeral strings of unknown length. A synthetic dataset of touching numeral strings of sizes 2-, 3- and 4-digits was created to train end-to-end solutions based on Convolutional Neural Networks. A robust experimental protocol is used to show that the proposed segmentation-free methods may reach the state-of-the-art performance without suffering the heavy burden of over-segmentation based methods. In addition, they confirmed the importance of introducing contextual information in the design of end-to-end solutions, such as the proposed length classifier when recognizing numeral strings.

引用

页数：8