Assessing the prospects for robust sub-diffraction limited super-resolution imaging with deep neural networks

Assessing the prospects for robust sub-diffraction limited super-resolution imaging with deep neural networks

Nieuwenhuizen, R.P.J.
Bouwman, D.D.
Schutte, K.

Buller, G.S. (editor)
Hollins, R.C. (editor)
Lamb, R.A. (editor)
Mueller, M. (editor)
Lamb, R.A. (editor)

2018

High resolution images are critical for a wide variety of military detection, recognition and identification tasks. Super-resolution reconstruction algorithms aim to enhance the image resolution beyond the capability of the imaging system being used. Until recently, undersampling of the optical signal on the image sensor has been the key factor limiting the attainable resolution of visible and infrared imaging systems. Traditional SR algorithms aim to overcome this undersampling by combining data from multiple frames in a sequence. However, recent advances in manufacturing technologies have led to a steady increase in the number of pixels in an image sensor. Instead, image blur caused by optical diffraction is becoming an important limitation to the attainable image resolution. Here we investigate if image resolutions beyond the limitations posed by optical diffraction may be achieved using deep neural network based single image super-resolution algorithms. These networks learn a mapping from low resolution images to high resolution counterparts from pairs of training images. This could allow them to reconstruct high frequency information beyond the diffraction limit based on prior information about likely scene contents. We find that an average gain in image resolution of over 30% could be achieved by such networks on simulated diffraction limited imagery. In addition we investigate how robust these networks are to the presence of noise in the low resolution input imagery. We show that low noise levels can lead to poor reconstruction results with networks trained on noise free examples, but also that training on multiple noise levels can be used to mitigate this deterioration in performance. © 2018 SPIE.

Algorithms
Deep learning
Diffraction
Neural networks
Super-resolution
Algorithms
Deep learning
Deep neural networks
Deterioration
Diffraction
Image enhancement
Image sensors
Imaging systems
Military photography
Neural networks
Optical resolving power
Thermography
Diffraction-limited imagery
High resolution image
High-frequency informations
Low resolution images
Manufacturing technologies
Super resolution
Super resolution imaging
Super resolution reconstruction
Image resolution

http://resolver.tudelft.nl/uuid:d33aaf7f-193b-46d5-a401-6855ea3269bf

844193

SPIE

9781510621817

0277-786X

Proceedings of SPIE - The International Society for Optical Engineering, 10799

1079905

The Society of Photo-Optical Instrumentation Engineers

conference paper