Super-Resolution of Face Images Using Kernel PCA-Based Prior
| Title | Super-Resolution of Face Images Using Kernel PCA-Based Prior |
| Publication Type | Journal Articles |
| Year of Publication | 2007 |
| Authors | Chakrabarti A, Rajagopalan AN, Chellappa R |
| Journal | Multimedia, IEEE Transactions on |
| Volume | 9 |
| Issue | 4 |
| Pagination | 888 - 892 |
| Date Published | 2007/06// |
| ISBN Number | 1520-9210 |
| Keywords | analysis;learning-based, analysis;probability;, component, Face, image, method;prior, model;face, principal, probability, recognition;image, reconstruction;image, reconstruction;kernel, resolution;principal, super-resolution;high-resolution |
| Abstract | We present a learning-based method to super-resolve face images using a kernel principal component analysis-based prior model. A prior probability is formulated based on the energy lying outside the span of principal components identified in a higher-dimensional feature space. This is used to regularize the reconstruction of the high-resolution image. We demonstrate with experiments that including higher-order correlations results in significant improvements |
| DOI | 10.1109/TMM.2007.893346 |