Closed-loop active object recognition with constrained illumination power

Conference Paper (2022)
Author(s)

J. Noom (TU Delft - Team Michel Verhaegen)

Oleg Soloviev (TU Delft - Team Michel Verhaegen, Flexible Optical B.V.)

S Smith (TU Delft - ImPhys/Computational Imaging, TU Delft - Team Carlas Smith)

M. Verhaegen (TU Delft - Team Michel Verhaegen)

Research Group
Team Michel Verhaegen
Copyright
© 2022 J. Noom, O.A. Soloviev, C.S. Smith, M.H.G. Verhaegen
DOI related publication
https://doi.org/10.1117/12.2618750
More Info
expand_more
Publication Year
2022
Language
English
Copyright
© 2022 J. Noom, O.A. Soloviev, C.S. Smith, M.H.G. Verhaegen
Research Group
Team Michel Verhaegen
ISBN (electronic)
9781510650800
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

Some applications require high level of image-based classification certainty while keeping the total illumination energy as low as possible. Examples are minimally invasive visual inspection in Industry 4.0, and medical imaging systems such as computed tomography, in which the radiation dose should be kept “as low as is reasonably achievable”. We introduce a sequential object recognition scheme aimed at minimizing phototoxicity or bleaching while achieving a predefined level of decision accuracy. The novel online procedure relies on approximate weighted Bhattacharyya coefficients for determination of future inputs. Simulation results on the MNIST handwritten digit database show how the total illumination energy is decreased with respect to a detection scheme using constant illumination.

Files

1210203.pdf
(pdf | 0.722 Mb)
License info not available