Digital hologram for data augmentation in learning-based pattern classification.

This study proposes a novel data augmentation method based on numerical focusing of digital holography to boost the performance of learning-based pattern classification. To conduct digital holographic data augmentation (DHDA), a complex pattern diffraction approach is used to provide the least separation of confusion in the effective diffraction regime to access the full-field wavefront information of a target sample. By using DHDA, the accessible amount of labeled data is increased to complement the data manifold and to provide various three-dimensional diffraction characteristics for improving the performance of learning-based pattern classification. Experimental results demonstrated that overall accuracy of pattern classification with DHDA (95.1%) was higher than that without DHDA (90.9%).

[1]  Leonidas J. Guibas,et al.  Render for CNN: Viewpoint Estimation in Images Using CNNs Trained with Rendered 3D Model Views , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[2]  Yu-Chih Lin,et al.  Optically driven full-angle sample rotation for tomographic imaging in digital holographic microscopy. , 2017, Optics letters.

[3]  Ata Mahjoubfar,et al.  Deep Learning in Label-free Cell Classification , 2016, Scientific Reports.

[4]  Christian Depeursinge,et al.  Cell morphology and intracellular ionic homeostasis explored with a multimodal approach combining epifluorescence and digital holographic microscopy , 2010, Journal of biophotonics.

[5]  Bahram Javidi,et al.  Extended focused image in microscopy by digital Holography. , 2005, Optics express.

[6]  Wolfgang Osten,et al.  Recent advances in digital holography [invited]. , 2014, Applied optics.

[7]  Jian Sun,et al.  Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition , 2015, IEEE Trans. Pattern Anal. Mach. Intell..

[8]  P. Marquet,et al.  Marker-free phase nanoscopy , 2013, Nature Photonics.

[9]  Yu-Chih Lin,et al.  Tunable time-resolved tick-tock pulsed digital holographic microscopy for ultrafast events. , 2017, Optics letters.

[10]  Werner Jüptner,et al.  Digital recording and numerical reconstruction of holograms , 2002 .

[11]  Etienne Cuche,et al.  Extended depth-of-focus by digital holographic microscopy. , 2010, Optics letters.

[12]  Bahram Javidi,et al.  Sickle cell disease diagnosis based on spatio-temporal cell dynamics analysis using 3D printed shearing digital holographic microscopy. , 2018, Optics express.

[13]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[14]  Lawrence D. Jackel,et al.  Backpropagation Applied to Handwritten Zip Code Recognition , 1989, Neural Computation.

[15]  B. Javidi,et al.  Polarization imaging of a 3D object by use of on-axis phase-shifting digital holography. , 2007, Optics letters.