Project Description
Fourier ptychography is an imaging technique that overcomes the diffraction limit of conventional cameras with applications in microscopy and long range imaging. Diffraction blur causes resolution loss in both cases. In Fourier Ptychography, a coherent light source illuminates an object, which is then imaged from multiple viewpoints. The reconstruction of the object from these set of recordings can be obtained by an iterative phase retrieval algorithm. However, the retrieval process is slow and does not work well under certain conditions. In this paper, we propose a new reconstruction algorithm that is based on convolutional neural networks and demonstrate its advantages in terms of speed and performance.
Publications
"PTYCHNET : CNN BASED FOURIER PTYCHOGRAPHY"
Armin Kappeler, Sushobhan Ghosh, Jason Holloway, Oliver Cossairt, Aggelos Katsaggelos
IEEE Conference on Image Processing (ICIP), 2017.
[PDF]
Images
Setup for Fourier Ptychography
Coherent light diffracts through a translucent medium into the far-field. A lens samples a portion of the Fourier domain which is recorded as intensity images at the sensor
Example of image acquisition
N × N images with limited, overlapping frequency bands are captured to recover one high resolution image
IERA block diagram
An overview of the Iterative Error Reduction Algorithm (IERA).
Acknowledgements
This work was supported in part by NSF CAREER grant IIS-1453192; ONR grant N00014-15-1- 2735; DARPA REVEAL grant HR0011-16-C-0028
