Location

Orbital ATK Conference Center

Start Date

5-7-2018 10:55 AM

Description

Deep learning is attracting a lot of attention because of its success in many research areas. This research is concerned with how deep neural networks may be used to process or compare multiple inputs with an abstract goal. Specifically, this paper addresses the case where the identification of an overlapping region between two images is desired. The scope of this paper includes the conceptual development of different approaches and a discussion of how observing a human’s approach to the same task can lead to improved performance. Some results are presented, but a thorough analysis and comparison of the trained DNNs are not included in this paper.

Comments

Session 4

Share

COinS
 
May 7th, 10:55 AM

Deep Learning Based Image Overlap Detection

Orbital ATK Conference Center

Deep learning is attracting a lot of attention because of its success in many research areas. This research is concerned with how deep neural networks may be used to process or compare multiple inputs with an abstract goal. Specifically, this paper addresses the case where the identification of an overlapping region between two images is desired. The scope of this paper includes the conceptual development of different approaches and a discussion of how observing a human’s approach to the same task can lead to improved performance. Some results are presented, but a thorough analysis and comparison of the trained DNNs are not included in this paper.