Title | ||
---|---|---|
A Comparison Of Compressed Sensing And Dnn Based Reconstruction For Ghost Motion Imaging |
Abstract | ||
---|---|---|
Ghost imaging is a technique that enables producing object's images without a multi-pixel detector. In a recently demonstrated technique called ghost motion imaging (GMI), images of objects under motion across an optical structure are encoded into corresponding signals observed by a single-pixel detector, and the object images can be reconstructed from the signals. GMI has been shown to be applicable to high-throughput cell morphometry. Image reconstruction for GMI was previously implemented by mean of a two-step iterative shrinkage/thresholding (TwIST) algorithm in the compressed sensing framework. In this work, we propose a learning-based image reconstruction from the GMI signals by using a deep neural network (DNN). We found that our DNN-based method is more accurate in image reconstruction with a shorter signal measurement than the TwIST-based one. |
Year | DOI | Venue |
---|---|---|
2020 | 10.1109/ICIP40778.2020.9190671 | 2020 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP) |
Keywords | DocType | ISSN |
Ghost Imaging, Ghost Motion Imaging, Image Reconstruction, Compressed Sensing, Deep Learning | Conference | 1522-4880 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Mantaro Yamada | 1 | 0 | 0.34 |
Hiroaki Adachi | 2 | 0 | 0.68 |
Ryoichi Horisaki | 3 | 0 | 0.68 |
Issei Sato | 4 | 331 | 41.59 |