PSF Recovery from Examples for Blind Super-Resolution

Author

Bégin, Isabelle ; Ferrie, Frank P.

Volume

5

fYear

2007

fDate

Sept. 16 2007-Oct. 19 2007

Abstract

This paper addresses the problem of super-resolving a single image and recovering the characteristics of the sensor using a learning-based approach. In particular, the point spread function (PSF) of the camera is sought by minimizing the mean Euclidean distance function between patches from the input frame and from degraded versions of high-resolution training images. Once an estimate of the PSF is obtained, a supervised learning algorithm can then be used as is. Results are compared with another method for blind super-resolution by using a series of quality measures.

Keywords

estimation theory; image resolution; image sensors; learning (artificial intelligence); blind super image resolution; camera; image sensor; mean Euclidean distance function; point spread function estimation; supervised learning algorithm; Belief propagation; Cameras; Degradation; Euclidean distance; Image databases; Image quality; Image resolution; Markov random fields; Signal resolution; Supervised learning; Image Quality; Learning; Markov Random Fields; Point Spread Function; Super-Resolution;

fLanguage

English

Publisher

ieee

Conference_Titel

Image Processing, 2007. ICIP 2007. IEEE International Conference on

Conference_Location

San Antonio, TX

ISSN

1522-4880

Print_ISBN

978-1-4244-1437-6

Electronic_ISBN

1522-4880

Type

conf

DOI

10.1109/ICIP.2007.4379855

Filename

4379855