Very low resolution face reconstruction based on multi-output regression
Zhihui Li, Yingkun Hou, Haibo Liu, Xiang Li · 2014
According to the reconstruction in the existing systems whose model is big and reconstruct speed is slow as the actual situation, this paper proposes a piece-division multiple output regression algorithm based on the Bayesian multiple adaptive regression splines ( MARS )model to make the regression of very low resolution(VLR) face data. This paper studies the low resolution(LR) face image reconstruction, which has less data, using the regression method to reconstruction is the most appropriate way with small model, fast reconstruction speed and accurate results as its advantages. The experiments prove the reconstruction accuracy from error and identification accuracy two aspects in this paper.