| 基于学习的模糊人脸图像重构算法研究 |
| |
| 引用本文： | 吴乐,伍麟珺.基于学习的模糊人脸图像重构算法研究[J].电子世界,2014(2):71-71. |
| |
| 作者姓名： | 吴乐 伍麟珺 |
| |
| 作者单位： | 湖南工学院电气与信息工程学院 |
| |
| 基金项目： | 湖南省高等学校科学研究项目资助（项目批准号：1100368）. |
| |
| 摘 要： | 人脸研究一直是计算机视觉、模式识别和计算机图形学领域中的热点研究问题之一。现今,通过监视器得到的人脸图像分辨率不高,以至于给人脸识别和跟踪等后续应用带来很大的难度。本文提出一种基于学习的超分辨率重构算法来得到清晰的人脸图像,采用对图像块搜索操作进行位置限制和检查图像分块间重叠区域水平兼容性的思想,降低了搜索的复杂度,提高了匹配相关性。
|
| 关 键 词： | 人脸图像识别 超分辨率重构 学习算法 |
Research On Learning-Based Fuzzy Face Image Resolution Algorithm |
| |
| WU le,WU lin.Research On Learning-Based Fuzzy Face Image Resolution Algorithm[J].Electronics World,2014(2):71-71. |
| |
| Authors: | WU le WU lin |
| |
| Affiliation: | jun ( School of electric and information engineering, Hunan institute of technology, Hengyang 421002, Hunan ) |
| |
| Abstract: | The research of face image is one of hot questions in the ifeld of the pattern recognition and computer graphics.Now adays,the human face image resolution through the monitoring device is not effective and it’s not so helpful to the human face recognition and the track and so on.We propose a novel algorithm that uses the location-restraint operation and the most compatible neighboring patches along horizontal dimension of the face to directly mosaic the high-resolution patches into the outcome.This method can reduce the complexity of search order,enhance the match relevance. |
| |
| Keywords: | Human face image recognition Super resolution Learning-based algorithm |
| 本文献已被 CNKI 维普 等数据库收录！ |
