Compressive image acquisition and classification via secant projections

Given its importance in a wide variety of machine vision applications, extending high-speed object detection and recognition beyond the visible spectrum in a cost-effective manner presents a significant technological challenge. As a step in this direction, we developed a novel approach for target image classification using a compressive sensing architecture. Here we report the first implementation of this approach utilizing the compressive single-pixel camera system. The core of our approach rests on the design of new measurement patterns, or projections, that are tuned to objects of interest. Our measurement patterns are based on the notion of secant projections of image classes that are constructed using two different approaches. Both approaches show at least a twofold improvement in terms of the number of measurements over the conventional, data-oblivious compressive matched filter. As more noise is added to the image, the second method proves to be the most robust.

[1]  M E Gehm,et al.  Single-shot compressive spectral imaging with a dual-disperser architecture. , 2007, Optics express.

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

[3]  Guillermo Sapiro,et al.  Discriminative learned dictionaries for local image analysis , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[4]  Richard G. Baraniuk,et al.  A new compressive imaging camera architecture using optical-domain compression , 2006, Electronic Imaging.

[5]  David G. Lowe,et al.  Object recognition from local scale-invariant features , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[6]  David S. Broomhead,et al.  The Whitney Reduction Network: A Method for Computing Autoassociative Graphs , 2001, Neural Computation.

[7]  Kari Torkkola,et al.  Feature Extraction by Non-Parametric Mutual Information Maximization , 2003, J. Mach. Learn. Res..

[8]  David J. Kriegman,et al.  Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection , 1996, ECCV.

[9]  Jitendra Malik,et al.  Scale-Space and Edge Detection Using Anisotropic Diffusion , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[10]  Emmanuel J. Candès,et al.  Decoding by linear programming , 2005, IEEE Transactions on Information Theory.

[11]  Avinash C. Kak,et al.  PCA versus LDA , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[12]  A. Robert Calderbank,et al.  Communications Inspired Linear Discriminant Analysis , 2012, ICML.

[13]  Gabriela Csurka,et al.  Visual categorization with bags of keypoints , 2002, eccv 2004.

[14]  Rama Chellappa,et al.  Sparsity-motivated automatic target recognition. , 2011, Applied optics.

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

[16]  R. Fisher.  THE USE OF MULTIPLE MEASUREMENTS IN TAXONOMIC PROBLEMS , 1936 .

[17]  D. L. Donoho,et al.  Compressed sensing , 2006, IEEE Trans. Inf. Theory.

[18]  Guillermo Sapiro,et al.  Sparse Representation for Computer Vision and Pattern Recognition , 2010, Proceedings of the IEEE.

[19]  Yin Zhang,et al.  A Compressive Sensing and Unmixing Scheme for Hyperspectral Data Processing , 2012, IEEE Transactions on Image Processing.

[20]  Pablo A. Parrilo,et al.  Guaranteed Minimum-Rank Solutions of Linear Matrix Equations via Nuclear Norm Minimization , 2007, SIAM Rev..

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

[22]  Jari Lindberg,et al.  Mathematical concepts of optical superresolution , 2012 .