A Bayesian Estimation Approach to Super-Resolution Reconstruction for Face Images
Most previous super-resolution (SR) approaches are implemented with two individual cascade steps, image registration and image fusion, which handicaps the incorporation of the structural information of the objects of interest, e.g. human faces, into SR in a parallel way. This prior information is beneficial to either robust motion estimation or fusion with higher quality. In this paper, SR reconstruction is formulated as Bayesian state estimation of location and appearance parameters of a face model. In addition, a sequential Monte Carlo (SMC) based algorithm is proposed to achieve the probabilistic state estimation, i.e. SR reconstruction in our formulation. Image alignment and image fusion are combined into one unified framework in the proposed approach, in which the prior information from the face model is incorporated into both registration and fusion process of SR. Experiments performed on synthesized frontal face sequences show that the proposed approach gains superior performance in registration as well as reconstruction.
KeywordsFace Image Face Model Sequential Monte Carlo Facial Component Sequential Monte Carlo Method
Unable to display preview. Download preview PDF.
- 2.Torre, D.l., Yacoob, Y., et al.: A probabilistic framework for rigid and non-rigid appearance based tracking and recognition. In: Inter. Conf. Face Recognition and Gesture Analysis, Grenoble, France, pp. 491–498 (2000)Google Scholar
- 5.Capel, D.P., Zisserman, A.: Super-resolution from multiple views using learnt image models. In: IEEE Conf. on Computer Vision and Pattern Recognition, pp. 627–634 (2001)Google Scholar
- 6.Liu, C., Shum, H.Y., et al.: A two-step approach to hallucinating faces: global parametric model and local nonparametric model. In: Proc. of CVPR 2001, Hawaii, USA, pp. 192–198 (2001)Google Scholar
- 10.Sudderth, E.B., Ihler, A.T., et al.: Nonparametric Belief Propagation. In: Proc. of CVPR 2003, Madison, WI, USA, pp. 605–612 (2003)Google Scholar
- 12.Chang, C., Ansari, R., et al.: Cyclic articulated human motion tracking by sequential ancestral simulation. In: Proc. of CVPR 2004, Washington, DC, USA, pp. 45–52 (2004)Google Scholar
- 14.Khan, Z., Balch, T., et al.: A Rao-Blackwellized Particle Filter for Eigen Tracking. In: Proc. of CVPR 2004, Washington, DC, USA, pp. 980–986 (2004)Google Scholar
- 15.Martinez, A.M., Benavente, R.: The AR face database. CVC Technical Report 24 (1998)Google Scholar