Foveated Manifold Sensing for object recognition

We present a novel method, Foveated Manifold Sensing, for the adaptive and efficient sensing of the visual world. The method is based on algorithms that learn manifolds of increasing but low dimensionality for representative data. As opposed to Manifold Sensing, the new foveated version senses only the most salient areas of a scene. This leads to an efficient sensing strategy that requires only a small number of sensing actions. The method is adaptive because during the sensing process, every new sensing action depends on the previously acquired sensing values. Finally, we propose a hybrid sensing scheme that starts with Manifold Sensing and proceeds with Foveated Manifold Sensing. This sensing scheme needs even less sensing actions for the considered recognition tasks. We apply the proposed algorithms to object recognition on the UMIST and ALOI datasets. We show that, for both databases, we reach a 100% recognition rate with only 10 sensing values.

[1]  E.J. Candes,et al.  An Introduction To Compressive Sampling , 2008, IEEE Signal Processing Magazine.

[2]  Antonio Torralba,et al.  Modeling the Shape of the Scene: A Holistic Representation of the Spatial Envelope , 2001, International Journal of Computer Vision.

[3]  E. Barth,et al.  On the Uniqueness of Curvature Features 1 , 2000 .

[4]  Bernhard Schölkopf,et al.  A kernel view of the dimensionality reduction of manifolds , 2004, ICML.

[5]  M. Naderi.  Think globally... , 2004, HIV prevention plus!.

[6]  Florian Steinke,et al.  Bayesian Inference and Optimal Design in the Sparse Linear Model , 2007, AISTATS.

[7]  Erhardt Barth.  The Minors of the Structure Tensor , 2000, DAGM-Symposium.

[8]  Gerhard Krieger,et al.  Investigation of a sensorimotor system for saccadic scene analysis: an integrated approach , 1998 .

[9]  Thomas Martinetz,et al.  An adaptive hierarchical sensing scheme for sparse signals , 2014, Electronic Imaging.

[10]  Axthonv G. Oettinger,et al.  IEEE Transactions on Information Theory , 1998 .

[11]  D. Field,et al.  Natural image statistics and efficient coding. , 1996, Network.

[12]  S T Roweis,et al.  Nonlinear dimensionality reduction by locally linear embedding. , 2000, Science.

[13]  E. Barth,et al.  On the Uniqueness of Curvature Features 1 2 , 2000 .

[14]  Lawrence K. Saul,et al.  Think Globally, Fit Locally: Unsupervised Learning of Low Dimensional Manifold , 2003, J. Mach. Learn. Res..

[15]  IEEE International Black Sea Conference on Communications and Networking, BlackSeaCom 2015, Constanta, Romania, May 18-21, 2015 , 2015, BlackSeaCom.

[16]  Thomas Martinetz,et al.  Visual manifold sensing , 2014, Electronic Imaging.

[17]  Leon Hirsch.  Handbook Of Computer Vision And Applications , 2016 .

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

[19]  Thomas Martinetz,et al.  Intrinsic Dimensionality Predicts the Saliency of Natural Dynamic Scenes , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[20]  Arnold W. M. Smeulders,et al.  The Amsterdam Library of Object Images , 2004, International Journal of Computer Vision.