General neural network approach to compressive feature extraction.

Computer vision with a single-pixel camera is currently limited by a trade-off between reconstruction capability and image classification accuracy. If random projections are used to sample the scene, then reconstruction is possible but classification accuracy suffers, especially in cases with significant background signal. If data-driven projections are used, then classification accuracy improves and the effect of the background is diminished, but image recovery is not possible. Here, we employ a shallow neural network to nonlinearly convert from measurements acquired with random patterns to measurements acquired with data-driven patterns. The results demonstrate that this improves classification accuracy while still allowing for full reconstruction.

[1]  Chinmay Hegde,et al.  Compressive image acquisition and classification via secant projections , 2015 .

[2]  Chinmay Hegde,et al.  NuMax: A Convex Approach for Learning Near-Isometric Linear Embeddings , 2015, IEEE Transactions on Signal Processing.

[3]  Richard G. Baraniuk,et al.  The STOne Transform: Multi-Resolution Image Enhancement and Compressive Video , 2015, IEEE Transactions on Image Processing.

[4]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[5]  J. Tropp,et al.  CoSaMP: Iterative signal recovery from incomplete and inaccurate samples , 2008, Commun. ACM.

[6]  M. Elad,et al.  Compressed Learning for Image Classification: A Deep Neural Network Approach , 2018 .

[7]  Richard G. Baraniuk,et al.  The smashed filter for compressive classification and target recognition , 2007, Electronic Imaging.

[8]  R. DeVore,et al.  A Simple Proof of the Restricted Isometry Property for Random Matrices , 2008 .

[9]  Jian Wang,et al.  Reconstruction-free inference on compressive measurements , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[10]  Richard G. Baraniuk,et al.  BM3D-AMP: A new image recovery algorithm based on BM3D denoising , 2015, 2015 IEEE International Conference on Image Processing (ICIP).

[11]  Aswin C. Sankaranarayanan,et al.  Realization of hybrid compressive imaging strategies. , 2014, Journal of the Optical Society of America. A, Optics, image science, and vision.

[12]  Chinmay Hegde,et al.  Near-isometric linear embeddings of manifolds , 2012, 2012 IEEE Statistical Signal Processing Workshop (SSP).

[13]  R.G. Baraniuk,et al.  Compressive Sensing [Lecture Notes] , 2007, IEEE Signal Processing Magazine.

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

[15]  Kilian Q. Weinberger,et al.  Unsupervised Learning of Image Manifolds by Semidefinite Programming , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..

[16]  Richard G. Baraniuk,et al.  Sparse Signal Detection from Incoherent Projections , 2006, 2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings.

[17]  Aswin C. Sankaranarayanan,et al.  Video Compressive Sensing for Spatial Multiplexing Cameras Using Motion-Flow Models , 2015, SIAM J. Imaging Sci..