Direct inference on compressive measurements using convolutional neural networks

Suhas Lohit, Kuldeep Kulkarni, Pavan Turaga

Research output: Chapter in Book/Report/Conference proceedingConference contribution

15 Citations (Scopus)

Abstract

Compressive imagers, e.g. the single-pixel camera (SPC), acquire measurements in the form of random projections of the scene instead of pixel intensities. Compressive Sensing (CS) theory allows accurate reconstruction of the image even from a small number of such projections. However, in practice, most reconstruction algorithms perform poorly at low measurement rates and are computationally very expensive. But perfect reconstruction is not the goal of high-level computer vision applications. Instead, we are interested in only determining certain properties of the image. Recent work has shown that effective inference is possible directly from the compressive measurements, without reconstruction, using correlational features. In this paper, we show that convolutional neural networks (CNNs) can be employed to extract discriminative non-linear features directly from CS measurements. Using these features, we demonstrate that effective high-level inference can be performed. Experimentally, using hand written digit recognition (MNIST dataset) and image recognition (ImageNet) as examples, we show that recognition is possible even at low measurement rates of about 0.1.

Original languageEnglish (US)
Title of host publication2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings
PublisherIEEE Computer Society
Pages1913-1917
Number of pages5
Volume2016-August
ISBN (Electronic)9781467399616
DOIs
StatePublished - Aug 3 2016
Event23rd IEEE International Conference on Image Processing, ICIP 2016 - Phoenix, United States
Duration: Sep 25 2016Sep 28 2016

Other

Other23rd IEEE International Conference on Image Processing, ICIP 2016
CountryUnited States
CityPhoenix
Period9/25/169/28/16

Fingerprint

Neural networks
Pixels
Image recognition
Image sensors
Computer vision
Cameras

Keywords

  • Compressive sensing
  • Neural networks

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Signal Processing

Cite this

Lohit, S., Kulkarni, K., & Turaga, P. (2016). Direct inference on compressive measurements using convolutional neural networks. In 2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings (Vol. 2016-August, pp. 1913-1917). [7532691] IEEE Computer Society. https://doi.org/10.1109/ICIP.2016.7532691

Direct inference on compressive measurements using convolutional neural networks. / Lohit, Suhas; Kulkarni, Kuldeep; Turaga, Pavan.

2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings. Vol. 2016-August IEEE Computer Society, 2016. p. 1913-1917 7532691.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Lohit, S, Kulkarni, K & Turaga, P 2016, Direct inference on compressive measurements using convolutional neural networks. in 2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings. vol. 2016-August, 7532691, IEEE Computer Society, pp. 1913-1917, 23rd IEEE International Conference on Image Processing, ICIP 2016, Phoenix, United States, 9/25/16. https://doi.org/10.1109/ICIP.2016.7532691
Lohit S, Kulkarni K, Turaga P. Direct inference on compressive measurements using convolutional neural networks. In 2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings. Vol. 2016-August. IEEE Computer Society. 2016. p. 1913-1917. 7532691 https://doi.org/10.1109/ICIP.2016.7532691
Lohit, Suhas ; Kulkarni, Kuldeep ; Turaga, Pavan. / Direct inference on compressive measurements using convolutional neural networks. 2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings. Vol. 2016-August IEEE Computer Society, 2016. pp. 1913-1917
@inproceedings{0480cd68fcda41508e363f486e9ef078,
title = "Direct inference on compressive measurements using convolutional neural networks",
abstract = "Compressive imagers, e.g. the single-pixel camera (SPC), acquire measurements in the form of random projections of the scene instead of pixel intensities. Compressive Sensing (CS) theory allows accurate reconstruction of the image even from a small number of such projections. However, in practice, most reconstruction algorithms perform poorly at low measurement rates and are computationally very expensive. But perfect reconstruction is not the goal of high-level computer vision applications. Instead, we are interested in only determining certain properties of the image. Recent work has shown that effective inference is possible directly from the compressive measurements, without reconstruction, using correlational features. In this paper, we show that convolutional neural networks (CNNs) can be employed to extract discriminative non-linear features directly from CS measurements. Using these features, we demonstrate that effective high-level inference can be performed. Experimentally, using hand written digit recognition (MNIST dataset) and image recognition (ImageNet) as examples, we show that recognition is possible even at low measurement rates of about 0.1.",
keywords = "Compressive sensing, Neural networks",
author = "Suhas Lohit and Kuldeep Kulkarni and Pavan Turaga",
year = "2016",
month = "8",
day = "3",
doi = "10.1109/ICIP.2016.7532691",
language = "English (US)",
volume = "2016-August",
pages = "1913--1917",
booktitle = "2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings",
publisher = "IEEE Computer Society",
address = "United States",

}

TY - GEN

T1 - Direct inference on compressive measurements using convolutional neural networks

AU - Lohit, Suhas

AU - Kulkarni, Kuldeep

AU - Turaga, Pavan

PY - 2016/8/3

Y1 - 2016/8/3

N2 - Compressive imagers, e.g. the single-pixel camera (SPC), acquire measurements in the form of random projections of the scene instead of pixel intensities. Compressive Sensing (CS) theory allows accurate reconstruction of the image even from a small number of such projections. However, in practice, most reconstruction algorithms perform poorly at low measurement rates and are computationally very expensive. But perfect reconstruction is not the goal of high-level computer vision applications. Instead, we are interested in only determining certain properties of the image. Recent work has shown that effective inference is possible directly from the compressive measurements, without reconstruction, using correlational features. In this paper, we show that convolutional neural networks (CNNs) can be employed to extract discriminative non-linear features directly from CS measurements. Using these features, we demonstrate that effective high-level inference can be performed. Experimentally, using hand written digit recognition (MNIST dataset) and image recognition (ImageNet) as examples, we show that recognition is possible even at low measurement rates of about 0.1.

AB - Compressive imagers, e.g. the single-pixel camera (SPC), acquire measurements in the form of random projections of the scene instead of pixel intensities. Compressive Sensing (CS) theory allows accurate reconstruction of the image even from a small number of such projections. However, in practice, most reconstruction algorithms perform poorly at low measurement rates and are computationally very expensive. But perfect reconstruction is not the goal of high-level computer vision applications. Instead, we are interested in only determining certain properties of the image. Recent work has shown that effective inference is possible directly from the compressive measurements, without reconstruction, using correlational features. In this paper, we show that convolutional neural networks (CNNs) can be employed to extract discriminative non-linear features directly from CS measurements. Using these features, we demonstrate that effective high-level inference can be performed. Experimentally, using hand written digit recognition (MNIST dataset) and image recognition (ImageNet) as examples, we show that recognition is possible even at low measurement rates of about 0.1.

KW - Compressive sensing

KW - Neural networks

UR - http://www.scopus.com/inward/record.url?scp=85006837039&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85006837039&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2016.7532691

DO - 10.1109/ICIP.2016.7532691

M3 - Conference contribution

VL - 2016-August

SP - 1913

EP - 1917

BT - 2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings

PB - IEEE Computer Society

ER -