Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Adaptive feature-specific imaging: a face recognition example.

Pawan K Baheti1, Mark A Neifeld

  • 1Department of Electrical and Computer Engineering, University of Arizona, Tucson, Arizona 85721, USA. baheti@ece.arizona.edu

Applied Optics
|April 3, 2008
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

A single shot coherent Ising machine based on a network of injection-locked multicore fiber lasers.

Nature communications·2019
Same author

Nonlinear optical components for all-optical probabilistic graphical model.

Nature communications·2018
Same author

Detection with polychromatic x-ray pencil beam illumination: information-theoretic bounds.

Applied optics·2018
Same author

Face recognition with non-greedy information-optimal adaptive compressive imaging.

Applied optics·2016
Same author

RF-subcarrier-assisted four-state continuous-variable QKD based on coherent detection.

Optics letters·2016
Same author

Multiple spatial modes based QKD over marine free-space optical channels in the presence of atmospheric turbulence.

Optics express·2016
Same journal

Multifunctional reconfigurable terahertz metasurface based on vanadium dioxide phase transition: achieving broadband absorption and efficient polarization conversion.

Applied optics·2026
Same journal

High-Q-factor electromagnetically induced transparency utilizing quasi-bound states in the continuum in an all-dielectric terahertz metasurface.

Applied optics·2026
Same journal

Automated stitching interferometry for high-precision metrology of X-ray mirrors.

Applied optics·2026
Same journal

Experimental demonstration of an approach to designing a metal-dielectric DBR resonant cavity structure.

Applied optics·2026
Same journal

High-precision wavefront reconstruction from a single-shot interferogram using a physics-driven hybrid feature calibration network.

Applied optics·2026
Same journal

Ultra-high-Q Fano resonance based on coupled topological corner states in Kagome photonic crystals.

Applied optics·2026
See all related articles

We developed an adaptive feature-specific imaging (AFSI) system for face recognition. AFSI significantly reduces measurements needed, especially at low signal-to-noise ratios, outperforming conventional methods.

Area of Science:

  • Computer Vision
  • Image Processing
  • Machine Learning

Background:

  • Adaptive imaging systems can improve efficiency in tasks like face recognition.
  • Conventional imaging methods may struggle in low signal-to-noise ratio (SNR) environments.

Purpose of the Study:

  • To introduce and evaluate an adaptive feature-specific imaging (AFSI) system for face recognition.
  • To compare AFSI's performance against static-FSI (SFSI) and conventional imaging techniques.

Main Methods:

  • Utilizing sequential hypothesis testing to compare imaging methods.
  • Adapting the projection basis at each step based on previous measurements.
  • Evaluating performance based on the number of measurements for a specified probability of misclassification (Pe).

Related Experiment Videos

Main Results:

  • AFSI demonstrated significant improvements over SFSI and conventional imaging, particularly at low SNR.
  • For M=4 hypotheses and Pe=10(-2), AFSI required 100 times fewer measurements than adaptive conventional imaging at SNR=-20 dB.
  • A trade-off between measurement SNR and adaptation advantage was identified, leading to an optimal integration time.

Conclusions:

  • The proposed AFSI system offers substantial gains in measurement efficiency for face recognition.
  • AFSI is particularly advantageous in low SNR conditions, outperforming existing methods.
  • Optimizing integration time per measurement is crucial for balancing SNR and adaptation benefits.