Combining Multi-Frame Images for Enhancement Using Self-Delaying Dynamic Networks

Abstract— This paper presents the use of a newly created network structure known as a Self-Delaying Dynamic Network (SDN). The SDNs were created to process data which varies with time. They feature an inbuilt timing structure which allows them to pass different items of data at different rates. This allows the network to store data from one time period until it can be used with related data in a later time period. These SDNs are non-recurrent temporal neural networks which store input data and they feature dynamic logic based connections between layers. An application is shown to create a high resolution image from a set of time stepped input frames. Several low resolution images and one high resolution image of a number of scenes were presented to the SDN during training by a Genetic Algorithm (GA). The trained SDN was then used to enhance a number of unseen noisy image sets. The images formed by the SDN are superior in several ways to the images produced using bi-cubic interpolatio...

• Type: Conference
• Year: 2006
• Where: IJCNN
• Authors: Lewis Eric Hibell, Honghai Liu, David J. Brown
• Keywords: IJCNN 2006, Inbuilt Timing Structure, Self-Delaying Dynamic Network, Time Period