基于MAP准则的两步人脸图像分辨率增强算法

MAP-Based Two-Step Approach to Hallucinating Faces

如何提高人脸图像分辨率是改进视觉监视系统性能需要解决的关键问题之一 .本文提出了一种基于MAP准则的两步人脸图像分辨率增强新算法 .第一步利用PCA模型和最大后验概率 (MAP)方法计算人脸的整体图像 ,第二步利用Markov随机场模型和MAP方法计算反映真实图像与整体图像差异的残差图像 .最终的结果是第一步得到的整体图像与第二步得到的残差图像之和 .利用新算法我们分别对图像分辨率增强 1 6倍 (由 32× 2 4提高到 1 2 8× 96 )和图像分辨率增强 6 4倍 (由 1 6× 1 2提高到 1 2 8× 96 )两种情况进行了实验 ,均取得了令人满意的结果 .

Face hallucination is to synthesize a high-resolution facial image from a low-resolution input.A novel two-step approach to hallucinating faces based on the MAP criterion is presented in this paper.First,a linear relationship between high-resolution and low-resolution facial images is established by applying PCA on both of them,and the global image,which is similar to the original high-resolution image,is reconstructed based on the MAP criterion.Second,a linear model between the residual image (the difference between the original image and the global image) and the low-resolution residual image (the difference between the low-resolution input and the manually down-sampled global image) is built,and,following a MRF prior,the optimal residual image is estimated based on the MAP criterion again.Experiments demonstrate that our approach can be applied to yield 4-8 fold super-resolution with high-quality hallucinated results.