A hybrid MLP-PNN architecture for fast image superresolution

Details A hybrid MLP-PNN architecture for fast image superresolution A hybrid MLP-PNN architecture for fast image superresolution

2005-03-22

arxiv.org/abs/cs/0503053v1

Lect. Notes Comput. Sc. 2714 (2003) 401-408

Computer Science

Computer Vision and Pattern Recognition

8 pages with 4 figures. ICANN/ICONIP 2003

Scientific paper

Image superresolution methods process an input image sequence of a scene to obtain a still image with increased resolution. Classical approaches to this problem involve complex iterative minimization procedures, typically with high computational costs. In this paper is proposed a novel algorithm for super-resolution that enables a substantial decrease in computer load. First, a probabilistic neural network architecture is used to perform a scattered-point interpolation of the image sequence data. The network kernel function is optimally determined for this problem by a multi-layer perceptron trained on synthetic data. Network parameters dependence on sequence noise level is quantitatively analyzed. This super-sampled image is spatially filtered to correct finite pixel size effects, to yield the final high-resolution estimate. Results on a real outdoor sequence are presented, showing the quality of the proposed method.

Affiliated with

Also associated with

No associations

Rating

A hybrid MLP-PNN architecture for fast image superresolution does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with A hybrid MLP-PNN architecture for fast image superresolution, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and A hybrid MLP-PNN architecture for fast image superresolution will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-683954