Title | ||
---|---|---|
Improving Imaging Quality of Real-time Fourier Single-pixel Imaging via Deep Learning. |
Abstract | ||
---|---|---|
Fourier single pixel imaging (FSPI) is well known for reconstructing high quality images but only at the cost of long imaging time. For real-time applications, FSPI relies on under-sampled reconstructions, failing to provide high quality images. In order to improve imaging quality of real-time FSPI, a fast image reconstruction framework based on deep learning (DL) is proposed. More specifically, a deep convolutional autoencoder network with symmetric skip connection architecture for real time 96 x 96 imaging at very low sampling rates (5-8%) is employed. The network is trained on a large image set and is able to reconstruct diverse images unseen during training. The promising experimental results show that the proposed FSPI coupled with DL (termed DL-FSPI) outperforms conventional FSPI in terms of image quality at very low sampling rates. |
Year | DOI | Venue |
---|---|---|
2019 | 10.3390/s19194190 | SENSORS |
Keywords | Field | DocType |
computational imaging,Fourier single-pixel imaging,deep learning | Iterative reconstruction,Computer vision,Autoencoder,Computational photography,Image quality,Fourier transform,Electronic engineering,Artificial intelligence,Sampling (statistics),Pixel,Engineering,Deep learning | Journal |
Volume | Issue | ISSN |
19 | 19.0 | 1424-8220 |
Citations | PageRank | References |
1 | 0.37 | 0 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Saad Rizvi | 1 | 1 | 0.70 |
Jie Cao | 2 | 4 | 5.28 |
Kaiyu Zhang | 3 | 3 | 1.15 |
Qun Hao | 4 | 65 | 16.54 |