Single-Pixel Imaging Based on Deep Learning Enhanced Singular Value Decomposition.

We propose and demonstrate a single-pixel imaging method based on deep learning network enhanced singular value decomposition. The theoretical framework and the experimental implementation are elaborated and compared with the conventional methods based on Hadamard patterns or deep convolutional autoencoder network. Simulation and experimental results show that the proposed approach is capable of reconstructing images with better quality especially under a low sampling ratio down to 3.12%, or with fewer measurements or shorter acquisition time if the image quality is given. We further demonstrate that it has better anti-noise performance by introducing noises in the SPI systems, and we show that it has better generalizability by applying the systems to targets outside the training dataset. We expect that the developed method will find potential applications based on single-pixel imaging beyond the visible regime.

High-efficiency terahertz single-pixel imaging based on a physics-enhanced network.

As an alternative solution to the lack of cost-effective multipixel terahertz cameras, terahertz single-pixel imaging that is free from pixel-by-pixel mechanical scanning has been attracting increasing attention. Such a technique relies on illuminating the object with a series of spatial light patterns and recording with a single-pixel detector for each one of them. This leads to a trade-off between the acquisition time and the image quality, hindering practical applications. Here, we tackle this challenge and demonstrate high-efficiency terahertz single-pixel imaging based on physically enhanced deep learning networks for both pattern generation and image reconstruction. Simulation and experimental results show that this strategy is much more efficient than the classical terahertz single-pixel imaging methods based on Hadamard or Fourier patterns, and can reconstruct high-quality terahertz images with a significantly reduced number of measurements, corresponding to an ultra-low sampling ratio down to 1.56%. The efficiency, robustness and generalization of the developed approach are also experimentally validated using different types of objects and different image resolutions, and clear image reconstruction with a low sampling ratio of 3.12% is demonstrated. The developed method speeds up the terahertz single-pixel imaging while reserving high image quality, and advances its real-time applications in security, industry, and scientific research.

Automatic recognition of breast invasive ductal carcinoma based on terahertz spectroscopy with wavelet packet transform and machine learning.

We demonstrate an automatic recognition strategy for terahertz (THz) pulsed signals of breast invasive ductal carcinoma (IDC) based on a wavelet entropy feature extraction and a machine learning classifier. The wavelet packet transform was implemented into the complexity analysis of the transmission THz signal from a breast tissue sample. A novel index of energy to Shannon entropy ratio (ESER) was proposed to distinguish different tissues. Furthermore, the principal component analysis (PCA) method and machine learning classifier were further adopted and optimized for automatic classification of the THz signal from breast IDC sample. The areas under the receiver operating characteristic curves are all larger than 0.89 for the three adopted classifiers. The best breast IDC recognition performance is with the precision, sensitivity and specificity of 92.85%, 89.66% and 96.67%, respectively. The results demonstrate the effectiveness of the ESER index together with the machine learning classifier for automatically identifying different breast tissues.