• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>Optoelectronic imaging and multimedia technology IV >Single face image reconstruction for super resolution using support vector regression
【24h】

Single face image reconstruction for super resolution using support vector regression

机译：使用支持向量回归的超高分辨率单面图像重建

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

In recent years, we have witnessed the prosperity of the face image super-resolution (SR) reconstruction, especially the learning-based technology. In this paper, a novel super-resolution face reconstruction framework based on support vector regression (SVR) about a single image is presented. Given some input data, SVR can precisely predict output class labels. We regard the SR problem as the estimation of pixel labels in its high resolution version. It's effective to put local binary pattern (LBP) codes and partial pixels into input vectors during training models in our work, and models are learnt from a set of high and low resolution face image. By optimizing vector pairs which are used for learning model, the final reconstructed results were advanced. Especially to deserve to be mentioned, we can get more high frequency information by exploiting the cyclical scan actions in the process of both training and prediction. A large number of experimental data and visual observation have shown that our method outperforms bicubic interpolation and some state-of-the-art super-resolution algorithms.
机译：近年来，我们见证了人脸图像超分辨率（SR）重建的繁荣，尤其是基于学习的技术。本文提出了一种基于支持向量回归（SVR）的单图像超分辨率人脸重建框架。给定一些输入数据，SVR可以精确预测输出类别标签。我们将SR问题视为其高分辨率版本中像素标签的估计。在我们的训练模型中，将局部二进制模式（LBP）代码和部分像素放入输入向量中非常有效，并且可以从一组高分辨率和低分辨率的人脸图像中学习模型。通过优化用于学习模型的向量对，可以改善最终的重构结果。特别值得一提的是，在训练和预测过程中，我们都可以通过利用周期性扫描动作来获得更多的高频信息。大量的实验数据和视觉观察表明，我们的方法优于双三次插值法和一些最新的超分辨率算法。

著录项

  • 来源
    《Optoelectronic imaging and multimedia technology IV》|2016年|100201d.1-100201d.8|共8页
  • 会议地点 Beijing(CN)
  • 作者

    Haijie Lin; Qiping Yuan; Zhihong Chen; Xiaoping Yang;

  • 作者单位

    School of Electronics Information Engineering, Tianjin Key Laboratory of Film Electronic and Communication Devices, Tianjin University of Technology, 391 West Binshui Road, Tianjin, China 300384;

    School of Electronics Information Engineering, Tianjin Key Laboratory of Film Electronic and Communication Devices, Tianjin University of Technology, 391 West Binshui Road, Tianjin, China 300384;

    School of Electronics Information Engineering, Tianjin Key Laboratory of Film Electronic and Communication Devices, Tianjin University of Technology, 391 West Binshui Road, Tianjin, China 300384;

    School of Electronics Information Engineering, Tianjin Key Laboratory of Film Electronic and Communication Devices, Tianjin University of Technology, 391 West Binshui Road, Tianjin, China 300384;

  • 会议组织
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

    Super-resolution; support vector regression; local binary pattern; cyclical-scan;

    机译：超分辨率；支持向量回归本地二进制模式；循环扫描;

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