Performance evaluation of two optical architectures for task-specific compressive classification

Redman, Brian J.; Dagel, Amber L.; Galiardi, Meghan A.; LaCasse, Charles F.; Quach, Tu-Thach; Birch, Gabriel C.

doi:10.1117/1.OE.59.5.051404

Performance evaluation of two optical architectures for task-specific compressive classification

Journal Article · Mon Jan 13 23:00:00 EST 2020 · Optical Engineering

DOI:https://doi.org/10.1117/1.OE.59.5.051404· OSTI ID:1595428

Redman, Brian J. ^[1]; Dagel, Amber L. ^[2]; Galiardi, Meghan A. ^[2]; LaCasse, Charles F. ^[2]; Quach, Tu-Thach ^[2]; Birch, Gabriel C. ^[2]

Sandia National Lab. (SNL-NM), Albuquerque, NM (United States); Univ. of Arizona, Tucson, AZ (United States)
Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)

Many optical systems are used for specific tasks such as classification. Of these systems, the majority are designed to maximize image quality for human observers. However, machine learning classification algorithms do not require the same data representation used by humans. We investigate the compressive optical systems optimized for a specific machine sensing task. Two compressive optical architectures are examined: an array of prisms and neutral density filters where each prism and neutral density filter pair realizes one datum from an optimized compressive sensing matrix, and another architecture using conventional optics to image the aperture onto the detector, a prism array to divide the aperture, and a pixelated attenuation mask in the intermediate image plane. We discuss the design, simulation, and trade-offs of these systems built for compressed classification of the Modified National Institute of Standards and Technology dataset. Both architectures achieve classification accuracies within 3% of the optimized sensing matrix for compression ranging from 98.85% to 99.87%. The performance of the systems with 98.85% compression were between an F/2 and F/4 imaging system in the presence of noise.

View Accepted Manuscript (DOE)

Research Organization:: Sandia National Laboratories (SNL-NM), Albuquerque, NM (United States)

Sponsoring Organization:: USDOE National Nuclear Security Administration (NNSA)

Grant/Contract Number:: AC04-94AL85000; NA0003525

OSTI ID:: 1595428

Report Number(s):: SAND--2020-0102J; 681873

Journal Information:: Optical Engineering, Journal Name: Optical Engineering Journal Issue: 05 Vol. 59; ISSN 0091-3286

Publisher:: SPIECopyright Statement

Country of Publication:: United States

Language:: English

References (21)

Multi-column deep neural network for traffic sign classification Cireşan, Dan; Meier, Ueli; Masci, Jonathan Neural Networks, Vol. 32 https://doi.org/10.1016/j.neunet.2012.02.023	journal	August 2012
Random Forests Breiman, Leo Machine Learning, Vol. 45, Issue 1, p. 5-32 https://doi.org/10.1023/A:1010933404324	journal	January 2001
Direct inference on compressive measurements using convolutional neural networks Lohit, Suhas; Kulkarni, Kuldeep; Turaga, Pavan 2016 IEEE International Conference on Image Processing (ICIP) https://doi.org/10.1109/ICIP.2016.7532691	conference	September 2016
An Ensemble of Fine-Tuned Convolutional Neural Networks for Medical Image Classification Kumar, Ashnil; Kim, Jinman; Lyndon, David IEEE Journal of Biomedical and Health Informatics, Vol. 21, Issue 1 https://doi.org/10.1109/JBHI.2016.2635663	journal	January 2017
Distributed Compressed Estimation Based on Compressive Sensing Xu, Songcen; de Lamare, Rodrigo C.; Poor, H. Vincent IEEE Signal Processing Letters, Vol. 22, Issue 9 https://doi.org/10.1109/LSP.2015.2400372	journal	September 2015
Compressive Sensing [Lecture Notes] Baraniuk, Richard G. IEEE Signal Processing Magazine, Vol. 24, Issue 4, p. 118-121 https://doi.org/10.1109/MSP.2007.4286571	journal	August 2007
Single-pixel imaging via compressive sampling Duarte, Marco F.; Davenport, Mark A.; Takhar, Dharmpal IEEE Signal Processing Magazine, Vol. 25, Issue 2, p. 83-91 https://doi.org/10.1109/MSP.2007.914730	journal	March 2008
Unsupervised Deep Feature Extraction for Remote Sensing Image Classification Romero, Adriana; Gatta, Carlo; Camps-Valls, Gustau IEEE Transactions on Geoscience and Remote Sensing, Vol. 54, Issue 3 https://doi.org/10.1109/TGRS.2015.2478379	journal	March 2016
Convolutional Neural Networks for Large-Scale Remote-Sensing Image Classification Maggiori, Emmanuel; Tarabalka, Yuliya; Charpiat, Guillaume IEEE Transactions on Geoscience and Remote Sensing, Vol. 55, Issue 2 https://doi.org/10.1109/TGRS.2016.2612821	journal	February 2017
Learning to Sense Sparse Signals: Simultaneous Sensing Matrix and Sparsifying Dictionary Optimization Duarte-Carvajalino, J. M.; Sapiro, G. IEEE Transactions on Image Processing, Vol. 18, Issue 7 https://doi.org/10.1109/TIP.2009.2022459	journal	July 2009
On the mean accuracy of statistical pattern recognizers Hughes, G. IEEE Transactions on Information Theory, Vol. 14, Issue 1 https://doi.org/10.1109/TIT.1968.1054102	journal	January 1968
Optimized Projections for Compressed Sensing Elad, M. IEEE Transactions on Signal Processing, Vol. 55, Issue 12 https://doi.org/10.1109/TSP.2007.900760	journal	December 2007
On Projection Matrix Optimization for Compressive Sensing Systems Li, Gang; Zhu, Zhihui; Yang, Dehui IEEE Transactions on Signal Processing, Vol. 61, Issue 11 https://doi.org/10.1109/TSP.2013.2253776	journal	June 2013
Optical systems for task-specific compressive classification Birch, Gabriel C.; Quach, Tu-Thach; Galiardi, Meghan Optics and Photonics for Information Processing XII https://doi.org/10.1117/12.2321331	conference	September 2018
Design and evaluation of task-specific compressive optical systems Redman, Brian J.; Birch, Gabriel C.; LaCasse, Charles F. Computational Imaging IV https://doi.org/10.1117/12.2520187	conference	May 2019
The smashed filter for compressive classification and target recognition Davenport, Mark A.; Duarte, Marco F.; Wakin, Michael B. Electronic Imaging 2007, SPIE Proceedings https://doi.org/10.1117/12.714460	conference	February 2007
Optimized Projection Matrix for Compressive Sensing Xu, Jianping; Pi, Yiming; Cao, Zongjie EURASIP Journal on Advances in Signal Processing, Vol. 2010, Issue 1 https://doi.org/10.1155/2010/560349	journal	July 2010
Optical architectures for compressive imaging Neifeld, Mark A.; Ke, Jun Applied Optics, Vol. 46, Issue 22 https://doi.org/10.1364/AO.46.005293	journal	January 2007
Compressive imaging system design using task-specific information Ashok, Amit; Baheti, Pawan K.; Neifeld, Mark A. Applied Optics, Vol. 47, Issue 25 https://doi.org/10.1364/AO.47.004457	journal	January 2008
Task-specific information for imaging system analysis Neifeld, Mark A.; Ashok, Amit; Baheti, Pawan K. Journal of the Optical Society of America A, Vol. 24, Issue 12 https://doi.org/10.1364/JOSAA.24.000B25	journal	January 2007
Compressive sampling Candès, Emmanuel J. Proceedings of the International Congress of Mathematicians Madrid, August 22–30, 2006, 1433-1452 https://doi.org/10.4171/022-3/69	book	May 2007

Similar Records

Task-specific sensor optical designs

Patent · Tue Oct 01 00:00:00 EDT 2024 · OSTI ID:2542673

Cognition at the Point of Sensing

Technical Report · Tue Sep 29 00:00:00 EDT 2020 · OSTI ID:1668459

A Comparison of Neuromorphic Classification Tasks

Conference · Sun Jul 01 00:00:00 EDT 2018 · OSTI ID:1462845

Related Subjects

47 OTHER INSTRUMENTATION
MNIST
compressive classification
compressive sensing
task-specific

Performance evaluation of two optical architectures for task-specific compressive classification

Citation Formats

References (21)

Similar Records

Related Subjects