Title

Single-Frame Super-Resolution By A Cortex Based Mechanism Using High Level Visual Features In Natural Images

Keywords

Biological system modeling; Computer science; Environmental factors; Image edge detection; Image generation; Image resolution; Interpolation; Pixel; Polynomials; Spatial resolution

Abstract

Super-resolution is the creation of higher resolution views of pixel-based images through interpolating the original pixels. Natural images are highly redundant on a pixel-by-pixel scale due to local dependencies among pixels, such as lines and textures. Greater super-resolution can be achieved by taking advantage of these local features inherent in natural images. In order to discover and learn these statistically significant features, we used SINBAD method (Set of INteracting BAckpropagating Dendrites), which is a biologically inspired cortical model for perception. SINBAD method allowed us to infer missing pixel values better than standard backprop networks and polynomial interpolation techniques, which are insensitive to the lines or textures in the images. To further test which method preserves edges more accurately, we used Sobel edge detection. SINBAD cells picked local lines and edges as the easiest orderly features in un-preprocessed natural images. Thus, the SINBAD approach appears to follow the same route taken by the brain's processing of visual information.

Publication Date

1-1-2002

Publication Title

Proceedings of IEEE Workshop on Applications of Computer Vision

Volume

2002-January

Number of Pages

112-117

Document Type

Article; Proceedings Paper

Personal Identifier

scopus

DOI Link

https://doi.org/10.1109/ACV.2002.1182167

Socpus ID

84948735385 (Scopus)

Source API URL

https://api.elsevier.com/content/abstract/scopus_id/84948735385

This document is currently not available here.

Share

COinS