Fast and accurate 3D object recognition directly from digital holograms

Mozhdeh Seifi (1) , Loic Denis (1) , Corinne Fournier (1)

1 LHC - Laboratoire Hubert Curien

Pattern recognition methods can be used in the context of digital holography to perform the task of object detection, classification, and position extraction directly from the hologram rather than from the reconstructed optical field. These approaches may exploit the differences between the holographic signatures of objects coming from distinct object classes and/or different depth positions. Direct matching of diffraction patterns, however, becomes computationally intractable with increasing variability of objects due to the very high dimensionality of the dictionary of all reference diffraction patterns. We show that most of the diffraction pattern variability can be captured in a lower dimensional space. Good performance for object recognition and localization is demonstrated at a reduced computational cost using a low-dimensional dictionary. The principle of the method is illustrated on a digit recognition problem and on a video of experimental holograms of particles.

Keywords: Digital holography; Image reconstruction techniques; Inverse problems; Singular Value Decomposition; Pattern recognition

Domains: Image Processing [eess.IV]

Mozhdeh Seifi, Loic Denis, Corinne Fournier. Fast and accurate 3D object recognition directly from digital holograms. Journal of the Optical Society of America. A Optics, Image Science, and Vision, 2013, 30 (11), pp.2216-2224. ⟨10.1364/JOSAA.30.002216⟩. ⟨ujm-00985394v2⟩