基于MCA与判别字典学习的场景图文字检测方法

刘舒萍; 汤宏颖

doi:10.13873/j.1000-9787(2017)07-0045-05

Chinese

您当前的位置：

首页 >

文章列表页 >

基于MCA与判别字典学习的场景图文字检测方法

研究与探讨 | 更新时间：2025-09-11

- 基于MCA与判别字典学习的场景图文字检测方法
- Text detection from natural-scene images using MCA and discriminative dictionary learning
- 传感器与微系统 2017年36卷第7期页码：45-49
- 作者机构：
  
  昆明理工大学信息工程与自动化学院
- 作者简介：
- 基金信息：
  
  国家自然科学基金应急管理项目（NSFC61540042）;云南省教育厅科学研究基金重点资助项目（2015Z045）
- DOI：10.13873/j.1000-9787(2017)07-0045-05
  中图分类号： TP391.41
- 纸质出版：2017
- 稿件说明：
移动端阅览
[1]刘舒萍,汤宏颖.基于MCA与判别字典学习的场景图文字检测方法[J].传感器与微系统,2017,36(07):45-49.

LIU Shu-ping, TANG Hong-ying. Text detection from natural-scene images using MCA and discriminative dictionary learning[J]. 2017, 36(7): 45-49.
[1]刘舒萍,汤宏颖.基于MCA与判别字典学习的场景图文字检测方法[J].传感器与微系统,2017,36(07):45-49. DOI： 10.13873/j.1000-9787(2017)07-0045-05.

LIU Shu-ping, TANG Hong-ying. Text detection from natural-scene images using MCA and discriminative dictionary learning[J]. 2017, 36(7): 45-49. DOI： 10.13873/j.1000-9787(2017)07-0045-05.

摘要

传统的文字检测方法在场景图像复杂背景、噪声污染和文字的多种形态特征的干扰下

检测的准确率很低

漏检、误检非常严重。针对这些问题

提出了基于形态成分分析（MCA）与判别字典学习的场景图像文字检测的方法。通过学习过完备字典将文字检测问题转化成稀疏和鲁棒表示的问题。利用MCA与改进的Fisher判别准则学习一个过完备字典

求解待检测图像文字部分的稀疏系数

重建待检测图像中的文字图像

进行文字检测。通过在ICDAR2003/2005/2011和MSRA-TD500数据库中的大量的实验证明了与其他文字检测方法相比

该方法能有效提高检测准确率。

Abstract

It is very difficult to locate and recognize text in natural-scene images by interference of complex background

noise pollution and multiple morphological of text using traditional text detection method. Propose a novel method for detecting text in natural-scene images using MCA and discriminative dictionary learning method.Text-detection problems are converted to sparse and robust representations by learning redundant dictionary. An over-complete dictionary is learned using MCA and an improved version of Fisher’s discriminant law

the sparserepresentation coefficients of text components in the query image are obtained using the learned dictionary. Text image is reconstructed in image to be test

and text test is carried not. The proposed method is extensively evaluated using International Conference on Document Analysis and Recognition（ ICDAR） 2003/2005/2011 datasets and MSRA-TD500 datasets

and it can effectively improve accurary of detection.

关键词

Keywords

references

无线传感器网络中基于压缩感知的分簇数据收集算法 [J]. 王冲,张霞,李鸥. 传感器与微系统 . 2016(01)

一种新的人脸图像去噪算法 [J]. 沈千里,陈晓,支亚京,蔡婷婷. 传感器与微系统 . 2015(11)

基于贪婪重建的射频传感器网络稀疏目标跟踪 [J]. 宋和平,王国利. 传感器与微系统 . 2013(11)

A new Histogram Oriented Moments descriptor for multi-oriented moving text detection in video [J] . Vijeta Khare,Palaiahnakote Shivakumara,Paramesran Raveendran. Expert Systems With Applications . 2015 (21)

Text string detection for loosely constructed characters with arbitrary orientations [J] . Yong Zhang,Jianhuang Lai,Pong C. Yuen. Neurocomputing . 2015

Discriminative dictionary learning via Fisher discrimination K-SVD algorithm [J] . Hao Zheng,Dapeng Tao. Neurocomputing . 2015

Performance improvement of character recognition in industrial applications using prior knowledge for more reliable segmentation [J] . Martin Grafmüller,Jürgen Beyerer. Expert Systems With Applications . 2013 (17)

Chinese text location under complex background using Gabor filter and SVM [J] . Jianqiang Yan,Jie Li,Xinbo Gao. Neurocomputing . 2011 (17)

Orthogonal least squares methods and their application to non-linear system identification [J] . S. Chen,S. A. Billings,W. Luo. International Journal of Control . 1989 (5)

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

基于改进K-SVD算法在牛脸识别上的应用

基于多任务结构稀疏表示的跟踪算法

基于改进HOG特征和稀疏表示的手指静脉识别

压缩感知中块结构字典学习方法改进

基于协作低秩分层稀疏和LC-KSVD的人脸表情识别