A hybrid MLP-PNN architecture for fast image superresolution

03/22/2005
by   Carlos Miravet, et al.
0

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.

READ FULL TEXT

page 4

page 7

research
10/03/2005

Accurate and robust image superresolution by neural processing of local image representations

Image superresolution involves the processing of an image sequence to ge...
research
02/28/2011

A novel super resolution reconstruction of low reoslution images progressively using dct and zonal filter based denoising

Due to the factors like processing power limitations and channel capabil...
research
03/24/2009

Gradient-based adaptive interpolation in super-resolution image restoration

This paper presents a super-resolution method based on gradient-based ad...
research
03/10/2023

Handheld Burst Super-Resolution Meets Multi-Exposure Satellite Imagery

Image resolution is an important criterion for many applications based o...
research
07/27/2018

Gated Fusion Network for Joint Image Deblurring and Super-Resolution

Single-image super-resolution is a fundamental task for vision applicati...
research
11/29/2019

Learning from Irregularly Sampled Data for Endomicroscopy Super-resolution: A Comparative Study of Sparse and Dense Approaches

Purpose: Probe-based Confocal Laser Endomicroscopy (pCLE) enables perfor...
research
03/20/2020

Across-scale Process Similarity based Interpolation for Image Super-Resolution

A pivotal step in image super-resolution techniques is interpolation, wh...

Please sign up or login with your details

Forgot password? Click here to reset