基于改进型卷积神经网络和行特征的文本检测

方承志; 樊梦雅

Chinese

您当前的位置：

首页 >

文章列表页 >

基于改进型卷积神经网络和行特征的文本检测

更新时间：2026-09-04

- 基于改进型卷积神经网络和行特征的文本检测
- Text detection based on improved convolutional neural network and the feature of text lines
- 微电子学与计算机 2019年36卷第8期页码：77-82
- 作者机构：
  
  南京邮电大学电子与光学工程学院,江苏,南京,210023
- 作者简介：
- 基金信息：
  
  国家自然科学基金面上资助项目 61271334国家自然科学基金面上资助项目 61073115
- DOI：
  中图分类号：
- 纸质出版：2019
- 稿件说明：
移动端阅览
方承志, 樊梦雅. 基于改进型卷积神经网络和行特征的文本检测[J]. 微电子学与计算机, 2019, 36(8): 77-82.

FANG Cheng-zhi, FAN Meng-ya. Text detection based on improved convolutional neural network and the feature of text lines[J]. 2019, 36(8): 77-82.
方承志, 樊梦雅. 基于改进型卷积神经网络和行特征的文本检测[J]. 微电子学与计算机, 2019, 36(8): 77-82. DOI：

FANG Cheng-zhi, FAN Meng-ya. Text detection based on improved convolutional neural network and the feature of text lines[J]. 2019, 36(8): 77-82. DOI：

摘要

针对现有的自然场景文本检测算法准确率尚未理想的问题

提出了一种基于改进型卷积神经网络和行特征的文本检测方法.首先

采用增强的最大稳定极值区域(MSER)提取图像的连通分量

并应用剪枝方法来获取孤立的连通区域; 其次

应用改进型卷积神经网络(CNN)对非字符区域进行消除

获得候选字符区域; 然后

提出基于行特征构建多方向候选文本行的算法

用于检测任意定向和弯曲的场景文本; 最后

应用C4.5决策树算法对候选文本行进行分类.该算法在ICDAR2013、ICDAR2015和MSER-TD500数据集上进行实验

实验结果表明

该算法能显著提高自然场景文本检测的准确率和召回率

且适用于任意方向、语言和字体的文本.

Abstract

In order to solve the problem of low precision in existing natural scene text detection algorithm

a text detection algorithm based on improved convolutional neural network and the feature of text lines was proposed. Firstly

the enhanced maximally stable extreme region (MSER) was used to extract connected components of the image and isolated connected regions were obtained by pruning method. Secondly

an improved convolutional neural network (CNN) was used to eliminate non-character regions and obtain candidate character regions. Thirdly

an algorithm based on the feature of text lines for constructing multi-oriented candidate text lines was proposed to detect arbitrary oriented and curved scene text. Finally

C4.5 decision tree algorithm was applied to classify candidate text lines. Experiments were carried out on ICDAR2013

ICDAR2015 and MSRA-TD500 datasets. Experimental results show that the algorithm can significantly improve the precision and recall of text detection in natural scenes

and is suitable for text in any direction

language and font.

关键词

Keywords

references

CHEN X, YUILLE A L. Detecting and reading text in natural scenes[C]// IEEE Computer Society Conference on Computer Vision and Pattern Recognition. IEEE Computer Society, 2004: 366-373.

ZHAO Y, LU T, LIAO W. A Robust Color-Independent Text Detection Method from Complex Videos[C]// International Conference on Document Analysis and Recognition. IEEE Computer Society, 2011: 374-378.

方承志, 黄梅玲.自然场景中多方向文本的检测[J].计算机工程与设计, 2018, 39(5):1377-1381. DOI: 1377

LEE J J, LEE P H, LEE S W, et al. AdaBoost for Text Detection in Natural Scene[C]// International Conference on Document Analysis and Recognition. IEEE, 2011: 429-434.

范一华, 邓德祥, 颜佳.基于色彩空间的最大稳定极值区域的自然场景文本检测[J].计算机应用, 2018, 38(1):264-269. DOI: 264

田彪.自然场景图像中的文字检测关键算法研究[D].南京: 南京邮电大学, 2016.

EPSHTEIN B, OFEK E, WEXLER Y. Detecting text in natural scenes with stroke width transform[C]// Computer Vision and Pattern Recognition. IEEE, 2010: 2963-2970.

BAI B, YIN F, LIU C L. A Fast Stroke-Based Method for Text Detection in Video[C]// Iapr International Workshop on Document Analysis Systems. IEEE, 2012: 69-73.

KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet classification with deep convolutional neural networks[C]// International Conference on Neural Information Processing Systems. Curran Associates Inc. 2012: 1097-1105.

WANG K, BELONGIE S. Word Spotting in the Wild[C]// European Conference on Computer Vision. Springer-Verlag, 2010: 591-604.

方承志, 田彪.结合连通分量规则度与Adaboost的文本定位算法[J].电视技术, 2015, 39(21):1-4. DOI: 1

LIU X, WANG W. Robustly Extracting Captions in Videos Based on Stroke-Like Edges and Spatio-Temporal Analysis[M]. IEEE Press, 2012.

REN X, CHEN K, YANG X, et al. A novel scene text detection algorithm based on convolutional neural network[C]// Visual Communications and Image Processing (VCIP), 2016. IEEE, 2016: 1-4.

MATAS J, CHUM O, URBAN M, et al. Robust wide-baseline stereo from maximally stable extremal regions[J]. Image % Vision Computing, 2004, 22(10):761-767. DOI: 761

REN S, HE K, GIRSHICK R, et al. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks[J]. IEEE Transactions on Pattern Analysis % Machine Intelligence, 2017, 39(6):1137-1149. DOI: 1137

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

一种基于特征上下文理解与切片分析的肺结核检测算法

基于改进RT-DETR的航拍小目标检测算法

基于反向体偏置的高增益稳定性高温运放设计

注意力机制与改进密集卷积引导的信息隐藏模型

基于MSS-YOLO-MPHands融合架构的装配手部动作识别研究