High quality images are
demanded in a wide variety of applications, including surveillance
systems, medical imaging, and high-definition TV (HDTV) displays. It is
possible to increase the spatial resolution and reduce the noise by
combining overlapping multiple images. This process is known as
super-resolution image reconstruction. We have developed several
algorithms handling compression, using learning-based priors, modeling
Bayer sampling, and handling photometric variations.
Superresolution under
photometric diversity of images,
Murat Gevrekci and Bahadir K. Gunturk,
EURASIP Journal on Advances in Signal
Processing, Special Issue: Super-Resolution Enhancement of Digital
Video, 2007. [pdf]
Restoration of bayer-sampled image
sequences, Murat Gevrekci, Bahadir K. Gunturk, and Yucel Altunbasak,
Oxford University Press,
Computer Journal, 2007. [pdf]
Super-resolution reconstruction of compressed video using
transform-domain statistics, Bahadir K. Gunturk, Yucel Altunbasak, and Russell M. Mersereau,
IEEE Trans. Image Processing, vol.
13, no. 1, pp. 33-43, January 2004. [pdf]
Eigenface-domain super-resolution
for face recognition, Bahadir K. Gunturk, Aziz U. Batur, Yucel Altunbasak, Monson H.
Hayes III, and Russell M. Mersereau, IEEE Trans. Image Processing, vol. 12, no.
5, pp. 597-606, May 2003. [pdf]
Multi-frame resolution enhancement methods for compressed video, Bahadir K. Gunturk, Yucel Altunbasak, and Russell M. Mersereau,
IEEE
Signal Processing Letters, vol. 9, no. 6, pp. 170-174, June
2002. [pdf]
