[1]张文超,吕岳,文颖,等.几何信息与SIFT特征相结合的特定人手写关键词检测[J].智能系统学报,2014,9(05):544-550.[doi:10.3969/j.issn.1673-4785.201402032]
 ZHANG Wenchao,LYU Yue,WEN Ying,et al.Specific handwritten keyword spotting using geometric information and SIFT feature[J].CAAI Transactions on Intelligent Systems,2014,9(05):544-550.[doi:10.3969/j.issn.1673-4785.201402032]
点击复制

几何信息与SIFT特征相结合的特定人手写关键词检测(/HTML)
分享到:

《智能系统学报》[ISSN:1673-4785/CN:23-1538/TP]

卷:
第9卷
期数:
2014年05期
页码:
544-550
栏目:
出版日期:
2014-10-25

文章信息/Info

Title:
Specific handwritten keyword spotting using geometric information and SIFT feature
作者:
张文超1 吕岳1 文颖1 黄志敏2
1. 华东师范大学 计算机科学与技术系, 上海 200241;
2. 公安部第三研究所, 上海 200032
Author(s):
ZHANG Wenchao1 LYU Yue1 WEN Ying1 HUANG Zhimin2
1. Department of Computer Science and Technology, East China Normal University, Shanghai 200241, China;
2. The Third Research Institute of Ministry of Public Security, Shanghai 200032, China
关键词:
关键词检测SIFT滑动窗口最大团查找
Keywords:
keyword spottingSIFTsliding windowmaximum clique matchinggeometric information
分类号:
TP18
DOI:
10.3969/j.issn.1673-4785.201402032
摘要:
中文汉字类别繁多,书写随意性大,使得中文的手写体关键词检测具有很大的挑战性。提出一种基于文字几何信息和SIFT特征相结合的手写体关键词检测方法,通过计算文本图像特征的匹配度来检测特定书写人的手写关键词。尺度不变特征转换(scale invariance feature transform,SIFT)局部特征具有良好的稳定性和独特性,既能适应同一书写人手写汉字的差异,又能区分不同书写人的书写笔迹。结合文字的几何信息,通过滑动窗口和最大团查找方法可以有效地删除误匹配点,极大地提高关键词检测的成功率。对大量手写体文本图像的实验结果表明,该方法能够有效检测同一书写人的相同关键词,具有较高的召回率和准确率。
Abstract:
Large variety of Chinese characters and handwriting styles leads to a big challenge for keyword spotting in Chinese handwritten documents. A new method combining the character geometric information and SIFT feature is proposed for detecting handwritten keywords of specific handwritten. It is proven that SIFT is a stable and distinctive local feature, which can perform well in distinguishing different handwriting styles. Combined with character geometric information and maximum clique matching, the proposed method can effectively remove miss-matching feature points and improve the precision rate of detection. Experimental results in handwriting document images show that the method can efficiently detect keywords of particular writers and remain high recall rate and high precision rate.

参考文献/References:

[1] RATH T M, MANMATHA R. Word image matching using dynamic time warping[C]//Proceedings of Conference on Vision and Pattern Recognition. Madison, USA, 2003:521-527.
[2] LLADOS J, RUSINOL M, FORNES A, et al. On the influence of word representations for handwritten word spotting in historical documents[J]. International Journal of Pattern Recognition and Artificial Intelligence, 2012, 26(5):1-25.
[3] ZHANG H, WANG D H, LIU C L. Keyword spotting from online Chinese handwritten documents using one-vs-all trained character classifier[C]//2010 International Conference on Frontiers in Handwriting Recognition. Kolkata, India, 2010:271-276.
[4] ZHANG H, LIU C L. A lattice-based method for keyword spotting in online Chinese handwriting[C]//2011 International Conference on Document Analysis and Recognition. Beijing, Chian, 2011:1064-1068.
[5] ZHANG H, WANG D H, LIU C L. A confidence-based method for keyword spotting in online Chinese handwritten documents[C]//2012 21st International Conference on Pattern Recognition. Tsukuba, Japan, 2012:525-528.
[6] LOWE D G. Distinctive image features from scale-invariant keypoints[J]. International Journal of Computer Vision, 2004, 60(2):91-110.
[7] LINDEBERG T. Detecting salient blob-like image structures and their scales with a scale-space primal sketch:a method for focus-of-attention[J]. International Journal of Computer Vision, 1993, 11(3):283-318.
[8] RODRIGUEZ J A, PERRONNIN F. Local gradient histogram features for word spotting in unconstrained handwritten documents[C]//2008 International Conference on Frontiers in Handwriting Recognition. Montréal, Canada, 2008:18-25.
[9] 郑琪, 管海兵, 陈凯. 基于局部特征的自然场景图片中文字定位和识别方法的研究[D]. 上海:上海交通大学, 2011. ZHENG Qi, GUAN Haibing, CHEN Kai. Research on text localization and recognition in image with complex scenes using local features[D]. Shanghai:Shanghai Jiaotong University, 2011:33-45.
[10] BEIS J S, LOWE D G. Shape indexing using approximate nearest-neighbour search in high-dimensional spaces[C]//Proceedings of Conference on Computer Vision and Pattern Recognition. San Juan, Puerto Rico, 1997:1000-1006.
[11] LIU C L, YIN F, WANG D H, et al. CASIA online and offline Chinese handwriting databases[C]//2011 International Conference on Document Analysis and Recognition. Beijing, China, 2011:37-41.

相似文献/References:

[1]许可乐,唐涛,蒋咏梅.一种SAR图像稳健特征点提取方法[J].智能系统学报,2013,8(04):287.[doi:10.3969/j.issn.1673-4785.201304038]
 XU Kele,TANG Tao,JIANG Yongmei.A stable feature point extraction approach for SAR image registration[J].CAAI Transactions on Intelligent Systems,2013,8(05):287.[doi:10.3969/j.issn.1673-4785.201304038]
[2]唐坤,韩斌.一种自适应搜索范围的SIFT特征点快速匹配算法[J].智能系统学报,2014,9(06):723.[doi:10.3969/j.issn.1673-4785.201309037]
 TANG Kun,HAN Bin.A new fast algorithm of self-adaptive search scope for SIFT matching[J].CAAI Transactions on Intelligent Systems,2014,9(05):723.[doi:10.3969/j.issn.1673-4785.201309037]
[3]唐坤,韩斌.一种基于参考点距离的SIFT特征点匹配算法[J].智能系统学报,2015,10(03):376.[doi:10.3969/j.issn.1673-4785.201311020]
 TANG Kun,HAN Bin.A SIFT matching algorithm based on the distance to reference point[J].CAAI Transactions on Intelligent Systems,2015,10(05):376.[doi:10.3969/j.issn.1673-4785.201311020]

备注/Memo

备注/Memo:
收稿日期:2014-02-26。
基金项目:国家科技支撑计划资助项目(2011BAK05B04).
作者简介:吕岳, 男, 1968年生, 博士, 教授、博士生导师, 主要研究方向为模式识别、图像处理、智能系统;文颖, 女, 1975年生, 博士, 副教授, 主要研究方向为图像处理、模式识别、机器学习。
通讯作者:张文超, 男, 1988年生, 硕士研究生, 主要研究方向为图像处理与模式识别。E-mail:414306765@qq.com.
更新日期/Last Update: 1900-01-01