Deep neural network with attention model for scene text recognition

Deep neural network with attention model for scene text recognition
复制标题

具有注意模型的深度神经网络用于场景文本识别

DOI:
10.1049/iet-cvi.2016.0404
复制
发表时间:
2017-07
影响因子:
1.7
通讯作者:
Zhang Jun
Zhang Jun
中科院分区:
计算机科学4区
文献类型:
--
作者:
Li Shuohao;Tang Min;Guo Qiang;Lei Jun;Zhang Jun

文献摘要

参考文献

相似文献

作者提出了一种具有注意力模型的深度神经网络(DNN),用于场景文本识别。该模型不需要对输入文本图像进行任何分割。该框架的灵感来自最近提出的语音识别和图像字幕的注意力模型。在该框架中,特征提取,特征注意和序列识别集成在一个联合训练的网络。与以前的方法相比,主要做了以下贡献。(i)将注意力模型应用到DNN中进行场景文本识别,可以有效解决可变长度标签引起的序列识别问题。(ii)在许多具有挑战性的基准测试中进行了严格的实验,包括IIIT5K,SVT,ICDAR2003和ICDAR2013数据集。实验结果表明,该模型与现有方法相比具有相当或更好的性能。(iii)这个模型只包含650万个参数。与其他用于场景文本识别的DNN模型相比,该模型具有迄今为止最少的参数。
The authors present a deep neural network (DNN) with attention model for scene text recognition. The proposed model does not require any segmentation of the input text image. The framework is inspired by the attention model presented recently for speech recognition and image captioning. In the proposed framework, feature extraction, feature attention and sequence recognition are integrated in a jointly trainable network. Compared with previous approaches, the following contributions are mainly made. (i) The attention model is applied into DNN to recognise scene text, and it can effectively solve the sequence recognition problem caused by variable length labels. (ii) Rigorous experiments are performed across a number of challenging benchmarks, including IIIT5K, SVT, ICDAR2003 and ICDAR2013 datasets. Results in experiments show that the proposed model is comparable or better than the state-of-the-art methods. (iii) This model only contains 6.5 million parameters. Compared with other DNN models for scene text recognition, this model has the least number of parameters so far.
用于基于图像的序列识别的端到端可训练神经网络及其在场景文本识别中的应用
DOI: 10.1109/tpami.2016.2646371
发表时间: 2017-11-01
影响因子: 23.6
作者:
Shi, Baoguang;Bai, Xiang;Yao, Cong
通讯作者: Yao, Cong
DOI: 10.1109/cvpr.2014.515
发表时间: 2014-06
期刊: 2014 IEEE Conference on Computer Vision and Pattern Recognition
影响因子: --
作者:
C. Yao;X. Bai;Baoguang Shi;Wenyu Liu-
通讯作者: C. Yao;X. Bai;Baoguang Shi;Wenyu Liu-
DOI: --
发表时间: 2009
期刊: --
影响因子: --
作者:
通讯作者: --
DOI: 10.1109/tpami.2014.2339814
发表时间: 2014-12-01
影响因子: 23.6
作者:
Almazan, Jon;Gordo, Albert;Valveny, Ernest
通讯作者: Valveny, Ernest
DOI: 10.1109/tpami.2002.1046154
发表时间: 2002-11
期刊: IEEE Trans. Pattern Anal. Mach. Intell.
影响因子: --
作者:
L. S. Oliveira;R. Sabourin;Flávio Bortolozzi;Ching Y. Suen
通讯作者: L. S. Oliveira;R. Sabourin;Flávio Bortolozzi;Ching Y. Suen