首页> 外文会议>IEEE International Symposium on Multimedia >Visual Text Features for Image Matching
【24h】

Visual Text Features for Image Matching

机译:图像匹配的视觉文本功能

获取原文

摘要

We present a new class of visual text features that are based on text in camera phone images. A robust text detection algorithm locates individual text lines and feeds them to a recognition engine. From the recognized characters, we generate the visual text features in a way that resembles image features. We calculate their location, scale, orientation, and a descriptor that describes the character and word information. We apply visual text features to image matching. To disambiguate false matches, we developed a word-distance matching method. Our experiments with image that contain text show that the new visual text feature based image matching pipeline performs on par or better than a conventional image feature based pipeline while requiring less than 10 bits per feature. This is 4.5x smaller than state-of-the-art visual feature descriptors.
机译:我们提出了一类基于相机电话图像中的文本的新类别的视觉文本功能。强大的文本检测算法定位各个文本线并将它们馈送到识别引擎。从识别的字符中,我们以类似于图像功能的方式生成视觉文本功能。我们计算其位置,缩放,方向和描述字符和单词信息的描述符。我们将Visual Text功能应用于图像匹配。为了消除错误的匹配,我们开发了一个词距离匹配方法。我们的实验包含文本的图像显示,基于新的Visual文本特征的图像匹配流水线在PAR上执行或优于基于传统的图像特征的流水线,同时每个功能小于10位。这比最先进的视觉特征描述符小4.5倍。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号