Ant clustering based text detection in natural scene images

P. Tomer, Ajay Goyal
{"title":"Ant clustering based text detection in natural scene images","authors":"P. Tomer, Ajay Goyal","doi":"10.1109/ICCCNT.2013.6726747","DOIUrl":null,"url":null,"abstract":"Text pictures in natural scene are necessary clues for several image-based applications like scene understanding, content-based image retrieval, helpful navigation, and automatic geocoding. However, locating text from a fancy atmosphere with multiple colors may be a difficult task. Although there are various techniques implemented for the detection of the text in natural scenes. The work implemented in paper(Text string detection from natural scenes by structural based partition and grouping) is based on Gradient based Partition and Color based Partition but the techniques implemented here provides less efficiency and the chances of error rate is more hence have less accuracy. But the technique implemented in this paper for the detection of texts in natural scenes is based on Ant based clustering. By using Ant clustering the performance of the technique for the detection of text has been increased.","PeriodicalId":6330,"journal":{"name":"2013 Fourth International Conference on Computing, Communications and Networking Technologies (ICCCNT)","volume":"16 1","pages":"1-7"},"PeriodicalIF":0.0000,"publicationDate":"2013-07-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2013 Fourth International Conference on Computing, Communications and Networking Technologies (ICCCNT)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICCCNT.2013.6726747","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 2

Abstract

Text pictures in natural scene are necessary clues for several image-based applications like scene understanding, content-based image retrieval, helpful navigation, and automatic geocoding. However, locating text from a fancy atmosphere with multiple colors may be a difficult task. Although there are various techniques implemented for the detection of the text in natural scenes. The work implemented in paper(Text string detection from natural scenes by structural based partition and grouping) is based on Gradient based Partition and Color based Partition but the techniques implemented here provides less efficiency and the chances of error rate is more hence have less accuracy. But the technique implemented in this paper for the detection of texts in natural scenes is based on Ant based clustering. By using Ant clustering the performance of the technique for the detection of text has been increased.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
基于蚂蚁聚类的自然场景图像文本检测
自然场景中的文本图片是场景理解、基于内容的图像检索、辅助导航和自动地理编码等基于图像的应用的必要线索。然而,从具有多种颜色的花哨环境中定位文本可能是一项艰巨的任务。尽管在自然场景中有各种各样的技术用于文本的检测。本文实现的工作(基于结构的分割和分组从自然场景中检测文本字符串)是基于基于梯度的分割和基于颜色的分割,但这里实现的技术效率较低,错误率更高,因此准确性较低。而本文实现的自然场景文本检测技术是基于Ant聚类的。通过使用Ant聚类,提高了文本检测技术的性能。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
“Multi-tenant SaaS cloud” Reduced order linear functional observers for large scale linear discrete-time control systems Multi pattern matching technique on fragmented and out-of-order packet streams for intrusion detection system Detection and tracking of moving objects by fuzzy textures Evacuation map generation using maze routing
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1