The tiny face in surveillance video is an obstacle to face recognition. Therefore, we propose a two-phase face super-resolution approach.
监控视频中人脸区域通常很小,辨识度很差,这给主观的人脸识别造成了一定的困难,为此本文提出一种基于样本学习的两阶段人脸超分辨率技术。
参考来源 - 基于内容的智能视频监控关键技术及在公共安防中的应用研究·2,447,543篇论文数据，部分数据来源于NoteExpress
Finally, the global face image and local details are combined to the final face super-resolution results.
最后，将全局脸图像和局部细节信息相结合，得到最终的人脸超分辨率结果。
Then, we propose a new learning-based super-resolution algorithm for face images.
本文着重介绍了基于学习的人脸图像超分辨率算法。
A novel region adaptive learning-based super resolution algorithm for human face images is proposed, which divides a face image into flat regions and detailed regions.
提出一种基于区域自适应学习的人脸图像超分辨率复原算法。
应用推荐