Fast Diffraction-pattern matching for object detection and recognition in digital holograms.

Abstract : A digital hologram is a 2-D recording of the diffraction fringes created by 3-D objects under coherent lighting. These fringes encode the shape and 3-D location information of the objects. By simulating re-lighting of the hologram, the 3-D wave field can be reconstructed and a volumetric image of the objects recovered. Rather than performing object detection and identification in this reconstructed volume, we consider direct recognition of diffraction-patterns in in-line holograms and show that it leads to superior performance. The huge variability of diffraction patterns with object shape and 3-D location makes diffraction-pattern matching computationally expensive. We suggest the use of a dimensionality reduction technique to circumvent this limitation and show good detection and recognition performance both on simulated and experimental holograms.
Complete list of metadatas

https://hal-ujm.archives-ouvertes.fr/ujm-00863143
Contributor : Corinne Fournier <>
Submitted on : Wednesday, September 18, 2013 - 12:06:19 PM
Last modification on : Wednesday, November 20, 2019 - 3:08:57 AM

Identifiers

  • HAL Id : ujm-00863143, version 1

Collections

Citation

Mozhdeh Seifi, Loïc Denis, Corinne Fournier. Fast Diffraction-pattern matching for object detection and recognition in digital holograms.. The 21st European Signal Processing Conference, Sep 2013, Marrakech, Morocco. pp.1569734797. ⟨ujm-00863143⟩

Share

Metrics

Record views

126