Face Hallucination Based On Sample Selection Bias Correction
Tao Lü, Ruimin Hu, Zhen Han, Junjun Jiang, Jun Chang · International Journal of Advancements in Computing Technology · 2012
In some learning approach problems, the learning algorithm receives training and test samples drawn according to the same distribution. However, this assumption is not available in practice. In face super-resolution, when the training sample available is biased, it may affect quality of the construction face. In this paper, we proposed a novel method to correct the bias of sample selection in training dataset. First, Active Shape Model is used to get the face shape vectors which contain some information about face contour. Then all faces from Chinese face dataset are classified into certain categories based on Hausdorff Distance by k-means clustering. We correct the sample bias by selecting the most similar faces due to the face shape similarity between samples and test images. Last, the global face reconstruction method based on eigenface is used to achieve satisfied image quality with selected train dataset. Experiments show that the face super-resolution algorithm based on sample selection bias correction can improve the subjective and objective quality of the input low resolution face images compared to traditional eigenface algorithm.