Reconstruction-Free Inference on Compressive Measurements

Suhas Lohit, Kuldeep Kulkarni, Pavan Turaga, Jian Wang, Aswin C. Sankaranarayanan; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2015, pp. 16-24


Spatial-multiplexing cameras have emerged as a promising alternative to classical imaging devices, often enabling acquisition of `more for less'. One popular architecture for spatial multiplexing is the so called single-pixel camera, which acquires coded measurements of the scene with pseudo-random spatial masks. Significant theoretical developments over the past few years provide a means for reconstruction of the original imagery with sub-Nyquist sampling. Yet, accurate reconstruction generally requires high measurement rates and high signal-to-noise ratios. In this paper, we enquire if one can perform high-level visual inference problems (e.g. face recognition or action recognition) from compressive cameras without the need for signal reconstruction. This is an interesting question since in many practical scenarios, our goals extend beyond signal reconstruction. However, most inference tasks often require non-linear features and it is not clear how to extract such features directly from compressed measurements. In this paper, we show that one can extract non-trivial correlational features directly without reconstruction of the imagery. As a specific example, we consider the problem of face recognition beyond the visible spectrum e.g in the short-wave infra-red region (SWIR) -- where pixels are expensive. We base our framework on {\em smashed filters} which suggests that inner-products between high-dimensional signals can be computed in the compressive domain to a high degree of accuracy. We show that one can indeed perform reconstruction-free inference with a very small loss of accuracy at very high compression ratios of 100 and more.

Related Material

author = {Lohit, Suhas and Kulkarni, Kuldeep and Turaga, Pavan and Wang, Jian and Sankaranarayanan, Aswin C.},
title = {Reconstruction-Free Inference on Compressive Measurements},
booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
month = {June},
year = {2015}