Improving resolution by image registration
CVGIP: Graphical Models and Image Processing
Neural Networks: A Comprehensive Foundation
Neural Networks: A Comprehensive Foundation
Example-Based Super-Resolution
IEEE Computer Graphics and Applications
An iterative image registration technique with an application to stereo vision
IJCAI'81 Proceedings of the 7th international joint conference on Artificial intelligence - Volume 2
Extraction of high-resolution frames from video sequences
IEEE Transactions on Image Processing
Joint MAP registration and high-resolution image estimation using a sequence of undersampled images
IEEE Transactions on Image Processing
| Hi-index | 0.00 |
This paper presents a neural network based method to estimate a high resolution image from a sequence of low resolution image frames. In this method, a multiple of layered feed-forward neural networks is specially designed to learn an optimal mapping from a multiple of low resolution image frames to a high resolution image through training. Simulation results demonstrate that the proposed neural networks can successfully learn the mapping in the presented examples and show a good potential in solving image resolution enhancement problem, as it can adapt itself to the various changeable conditions. Furthermore, due to the inherent parallel computing structure of neural network, this method can be applied for real-time application, alleviating the computational bottlenecks associated with other methods and providing a more powerful tool for image resolution enhancement.