The face hallucinating two-step framework using hallucinated high-resolution residual

摘要：

In video surveillance, the attention human faces are frequently of small size. Image hallucination is an imperative factor disturbing the face classification by human and computer. In this paper, we propose a two-step face hallucination framework by means of training data sets which have a small quantity of low and high resolution images. In the first step, the global face is constructed based on optimal weights of training images. In the second step, a local residual compensation method bases on position patch via residual training face image data sets. Moreover, the hallucinated high-resolution residual image which is obtained by the identical process can be subsequent for the local face. Finally, the hallucinated high-resolution residual image is appended with the input low-resolution face image which is interpolated to the high-resolution image dimension by an upsampling factor. Experiments fully demonstrate that our framework is very flexible and accomplishs good performance via small training data sets.

关键词： learning method residual compensation global face local face hallucinated residual image.

作者: H. M. M. Naleer Yao Lu Yaozu An

作者单位: Beijing Laboratory of Intelligent Information Technology, School of Computer Science and Technology, Beijing Laboratory of Intelligent Information Technology, School of Computer Science and Technology,

会议类型: 国际会议

会议名称: Third International Conference on Digital Image Processing(ICDIP 2011)(第三届数字图像处理国际会议)

会议地点: 成都

会议语种:英文

页码: 49-53

在线出版日期: 2011-04-15（万方平台首次上网日期，不代表论文的发表时间）