• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>電子情報通信学会技術研究報告. 医用画像. Medical Imaging >Image enhancement of text in scenery images for degraded character recognition
【24h】

Image enhancement of text in scenery images for degraded character recognition

机译：风景图像中文本的图像增强，以降低字符识别

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

This paper proposes a method to enhance text images for a system which extracts, recognizes and translates characters in scenery images captured by a digital camera. The proposed method magnifies text images in frequency domain. It restores hi-frequency component caused by JPEG(Joint Photographic Experts Group) compression and reduces mosquito noise and block noise caused by magnification process. The obtained enhanced text images are binarized and then recognized by a commercial character recognition software. Experiments are performed for printed documents, sign boards and plates captured by a digital camera. In our experiments, texts are manually extracted from images because our goal in this paper is image enhancement. Compared with traditional approaches, the recognition ratio for our enhanced images by using a commercial character recognition software improves.
机译：本文提出了一种增强文本图像的方法，该系统用于提取，识别和翻译数码相机捕获的风景图像中的字符。所提出的方法在频域中放大文本图像。它可以恢复由JPEG（联合图像专家组）压缩引起的高频分量，并减少由放大过程引起的蚊式噪声和块状噪声。将获得的增强文本图像进行二值化，然后通过商业字符识别软件进行识别。对数码相机捕获的打印文档，标牌和标牌进行了实验。在我们的实验中，从图像中手动提取文本是因为我们的目标是图像增强。与传统方法相比，通过使用商业字符识别软件对增强图像的识别率得以提高。

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