[1]郭 闯,邱晓晖.基于 BLSTM 网络的改进 EAST 文本检测算法[J].计算机技术与发展,2020,30(07):21-24.[doi:10. 3969 / j. issn. 1673-629X. 2020. 07. 005]
　GUO Chuang,QIU Xiao-hui.Improved EAST Natural Scene Text Location Algorithm Based on BLSTM Network[J].COMPUTER TECHNOLOGY AND DEVELOPMENT,2020,30(07):21-24.[doi:10. 3969 / j. issn. 1673-629X. 2020. 07. 005]
点击复制

基于 BLSTM 网络的改进 EAST 文本检测算法()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
30
期数:
2020年07期
页码:
21-24
栏目:
智能、算法、系统工程
出版日期:
2020-07-10

文章信息/Info

Title:
Improved EAST Natural Scene Text Location Algorithm Based on BLSTM Network
文章编号:
1673-629X(2020)07-0021-04
作者:
郭 闯; 邱晓晖
南京邮电大学 通信与信息工程学院,江苏 南京 210003
Author(s):
GUO Chuang; QIU Xiao-hui
School of Communication and Information Engineering,Nanjing University of Posts and Telecommunications,Nanjing 210003,China
关键词:
文本定位; EAST; BLSTM; 感受野; 自然场景
Keywords:
text location; EAST; BLSTM; receptive fields; natural scene
分类号:
TP301. 6
DOI:
10. 3969 / j. issn. 1673-629X. 2020. 07. 005
摘要:
尽管前人在文本检测和文本识别方面已经取得了显著的研究进展,但是在场景文本检测方面仍然存在着较大的不足。 即使是深度学习模型,也不会达到很好的性能。 因为整体性能取决于流程中的多个阶段和组件的相互作用。 基于深度学习神经网络模型的 EAST 算法可以在进行场景文本检测时避免传统文本检测方法不必要的中间步骤(例如候选区域和字分区域) ,从而得到了快速准确的检测效果,准确率和召回率都有大幅度的提高。 然而由于其感受野范围较短,对长文本的检测效果仍存在问题,因此文中对 EAST 算法进行改进,在 EAST 算法的基础上,引入 BLSTM 网络,提高其感受野,增强文本定位的效果。 实验结果表明,该算法在 ICDAR2015 文本定位任务的召回率为 78.07% ,准确率为 85.10% ,F-score 为 81.64% ,优于经典 EAST 算法。
Abstract:
Although the predecessors have made remarkable research progress in text detection and text recognition,there are still some deficiencies in scene text detection. Even the deep learning model will not achieve ideal performance. Because the overall performance depends on  the interaction of multiple stages and components in the process. EAST algorithm based on deep learning neural network model can avoid unnecessary intermediate steps in traditional text detection methods (such as candidate regions and word sub-regions) when performing scene text detection,so as to obtain rapid and accurate detection effect,with a significant improvement in accuracy and recall rate. However,due to the short range of receptive fields, there are still problems in the detection of long text. Therefore, we improve the EAST algorithm, based on which BLSTM network is introduced to improve its sensing field and enhance the effect of text location. The experiment shows that the recall rate,accuracy and F-score of the proposed algorithm are 78.07% ,85.10% and 81.64% respectively,which are better than the classical EAST algorithm.

相似文献/References:

[1]王景中,朱其猛.基于汉字笔画特征的文本图像倒置判断算法[J].计算机技术与发展,2014,24(05):129.
　WANG Jing-zhong,ZHU Qi-meng.A Judgment Algorithm for Inverted Chinese Text Image Based on Characteristics of Stroke[J].COMPUTER TECHNOLOGY AND DEVELOPMENT,2014,24(07):129.
[2]王晓琼[],舒双宝[],甘开福[],等. EAST红外CCD诊断系统的图像采集与处理[J].计算机技术与发展,2015,25(08):179.
　WANG Xiao-qiong[],SHU Shuang-bao[],GAN Kai-fu[],et al. Image Collecting and Processing of Infrared CCD Diagnosis System in EAST[J].COMPUTER TECHNOLOGY AND DEVELOPMENT,2015,25(07):179.

更新日期/Last Update: 2020-07-10