Hallucinating Faces: Global Linear Modal Based Super-Resolution and Position Based Residue Compensation

详细信息    查看全文

• 作者：Xiang Ma ; Junping Zhang ; Chun Qi
• 关键词：Face hallucination ; Super ; resolution ; Residue compensation
• 刊名：Lecture Notes in Computer Science
• 出版年：2009
• 出版时间：2009
• 年：2009
• 卷：5716
• 期：1
• 页码：835-843
• 全文大小：411.3 KB

文摘

A learning-based face hallucination method is proposed in this paper for the reconstruction of a high-resolution face image from a low-resolution observation based on a set of high- and low-resolution training image pairs. The proposed global linear modal based super-resolution estimates the optimal weights of all the low-resolution training images and a high-resolution image is obtained by applying the estimated weights to the high-resolution space. Then, we propose a position based local residue compensation algorithm to better recover subtle details of face. Experiments demonstrate that our method has advantage over some established methods.