Spatio-Spectral Enhancement of Single-Pixel Reconstruction by a Fully Convolutional Neural Network

Spectral images (SI) contain a large amount of information, which increases the cost of their collection, storage, and processing. Compressive spectral imaging (CSI) methods allow the reconstruction of that information from a small set of random projections. However, compressed sensing with high spatial-spectral resolution requires expensive sensors. The single-pixel camera is an architecture that provides a low-cost solution for compressive SI acquisition, but with a significant limitation in image resolution. This work proposes a deep learning approach by means of a fully convolutional neural network (FCNN) with the ability to retrieve the spatio-spectral information from a single-pixel reconstruction in order to produce a spatio-spectral enhancement, suitable for applications requiring higher quality and low-cost acquisition systems. Simulations and experimental results show that the trained FCNN with a limited data set improves the quality of the single-pixel reconstruction in up to 20 dB, without requiring additional measurements. The performance of the proposed approach is compared against the traditional method of the single-pixel reconstruction.

[1]  Henry Arguello,et al.  Multi-Resolution Compressive Spectral Imaging Reconstruction From Single Pixel Measurements , 2018, IEEE Transactions on Image Processing.

[2]  Gary A. Shaw,et al.  Spectral Imaging for Remote Sensing , 2003 .

[3]  S. Frick,et al.  Compressed Sensing , 2014, Computer Vision, A Reference Guide.

[4]  Ting Liu,et al.  Recent advances in convolutional neural networks , 2015, Pattern Recognit..

[5]  Shahram Shirani,et al.  Compressive Sensing Image Sensors-Hardware Implementation , 2013, Sensors.

[6]  Henry Arguello,et al.  Compressive Coded Aperture Spectral Imaging: An Introduction , 2014, IEEE Signal Processing Magazine.

[7]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[8]  Guolan Lu,et al.  Medical hyperspectral imaging: a review , 2014, Journal of biomedical optics.

[9]  Qionghai Dai,et al.  Supplementary Document : Spatial-spectral Encoded Compressive Hyperspectral Imaging , 2014 .

[10]  Nitish Srivastava,et al.  Improving neural networks by preventing co-adaptation of feature detectors , 2012, ArXiv.

[11]  Qionghai Dai,et al.  Dual-coded compressive hyperspectral imaging. , 2014, Optics letters.

[12]  Jürgen Schmidhuber,et al.  Deep learning in neural networks: An overview , 2014, Neural Networks.

[13]  Keiron O'Shea,et al.  An Introduction to Convolutional Neural Networks , 2015, ArXiv.

[14]  Ashwin A. Wagadarikar,et al.  Single disperser design for coded aperture snapshot spectral imaging. , 2008, Applied optics.

[15]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[16]  Dimitris G. Manolakis,et al.  Detection algorithms for hyperspectral imaging applications , 2002, IEEE Signal Process. Mag..

[17]  Mário A. T. Figueiredo,et al.  Gradient Projection for Sparse Reconstruction: Application to Compressed Sensing and Other Inverse Problems , 2007, IEEE Journal of Selected Topics in Signal Processing.

[18]  Henry Arguello,et al.  Single Pixel Spectral Image Fusion with Side Information from a Grayscale Sensor , 2018, 2018 IEEE 1st Colombian Conference on Applications in Computational Intelligence (ColCACI).

[19]  Ting Sun,et al.  Single-pixel imaging via compressive sampling , 2008, IEEE Signal Process. Mag..

[20]  Da-Wen Sun,et al.  Hyperspectral imaging for food quality analysis and control , 2010 .

[21]  Takashi Matsubara,et al.  RICAP: Random Image Cropping and Patching Data Augmentation for Deep CNNs , 2018, ACML.

[22]  Jorge Bacca,et al.  Coupled deep learning coded aperture design for compressive image classification. , 2020, Optics express.