Speckle-learning-based object recognition through scattering media
- 23 December 2015
- journal article
- research article
- Published by Optica Publishing Group in Optics Express
- Vol. 23 (26) , 33902-33910
Abstract
We experimentally demonstrated object recognition through scattering media based on direct machine learning of a number of speckle intensity images. In the experiments, speckle intensity images of amplitude or phase objects on a spatial light modulator between scattering plates were captured by a camera. We used the support vector machine for binary classification of the captured speckle intensity images of face and non-face data. The experimental results showed that speckles are sufficient for machine learning.Keywords
This publication has 22 references indexed in Scilit:
- Noncontact optical sensor for bone fracture diagnosticsBiomedical Optics Express, 2015
- Non-invasive single-shot imaging through scattering layers and around corners via speckle correlationsNature Photonics, 2014
- Imaging With Nature: Compressive Imaging Using a Multiply Scattering MediumScientific Reports, 2014
- The biospeckle method for the investigation of agricultural crops: A reviewOptics and Lasers in Engineering, 2014
- Non-invasive imaging through opaque scattering layersNature, 2012
- Controlling waves in space and time for imaging and focusing in complex mediaNature Photonics, 2012
- Simultaneous remote extraction of multiple speech sources and heart beats from secondary speckles patternOptics Express, 2009
- Fast separation of direct and global components of a scene using high frequency illuminationACM Transactions on Graphics, 2006
- Polarization-based vision through hazeApplied Optics, 2003
- Improvement of Underwater Visibility by Reduction of Backscatter with a Circular Polarization TechniqueApplied Optics, 1967