Share Email Print
cover

Proceedings Paper

Neural-network-based image resolution enhancement from a multiple of low-resolution images
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

A neural network based image enhancement method is introduced to improve the image resolution from a sequence of low resolution image frames. Most of the existing methods reconstruct a high-resolution image from a multiple of low-resolution image frames by minimizing some established cost function using a mathematical technique. This method, however, uses an integrated recurrent neural network (IRNN) that is particularly designed to be capable of learning an optimal mapping from a multiple of low-resolution image frames to a high-resolution image through training. The IRNN consists of four feed-forward sub-networks working collectively with the ability of having a feedback of information from its output to input. As such, it is capable of both learning and searching the optimal solution in the solution space leading to high resolution images. Simulation results demonstrate that the proposed IRNN has good potential in solving image resolution enhancement problem, as it can adapt itself to the various conditions of the reconstruction problem by learning.

Paper Details

Date Published: 25 March 2003
PDF: 9 pages
Proc. SPIE 5015, Applications of Artificial Neural Networks in Image Processing VIII, (25 March 2003); doi: 10.1117/12.477396
Show Author Affiliations
Ezzatollah Salari, Univ. of Toledo (United States)
Shuangteng Zhang, Eastern Kentucky Univ. (United States)


Published in SPIE Proceedings Vol. 5015:
Applications of Artificial Neural Networks in Image Processing VIII
Nasser M. Nasrabadi; Aggelos K. Katsaggelos, Editor(s)

© SPIE. Terms of Use
Back to Top