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

Shape from focus using multilayer feedforward neural networks.

M Asif1, T S Choi

  • 1Signal and Image Processing Laboratory, Department of Mechatronics, Kwangju Institute of Science and Technology, Kwangju, Korea. asif@sipl.kjist.ac.kr

IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
|February 8, 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

Tailoring high-field energy storage and dual-mode electrocaloric response in relaxor ferroelectric thin film.

RSC advances·2026
Same author

Author Correction: Development and life cycle assessment (LCA) of super-oleophobic (under water) and super-hydrophilic (in-air) mesh membrane for oily water treatment.

Scientific reports·2025
Same author

Venesection and resolution of erythrocytosis are not associated with reduced thrombotic risk in secondary and idiopathic polycythaemia: Results from a dual centre, 5-year retrospective study.

British journal of haematology·2025
Same author

Nonlinear dynamic wave properties of travelling wave solutions in in (3+1)-dimensional mKdV-ZK model.

PloS one·2025
Same author

Fungal Planet description sheets: 1614-1696.

Fungal systematics and evolution·2024
Same author

Development and life cycle assessment (LCA) of super-oleophobic (under water) and super-hydrophilic (in-air) mesh membrane for oily water treatment.

Scientific reports·2024
Same journal

Hyperbolic Cycle Alignment for Infrared-Visible Image Fusion.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same journal

Learning Gaze Synthesizer via 3D-eye Controlled Diffusion and Cross-domain Feature Alignment.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same journal

Underlying Semantic Diffusion for Effective and Efficient In-Context Learning.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same journal

DiffRES: Unleashing Text-to-Image Diffusion Models for Generative Referring Expression Segmentation without Information Leakage.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same journal

Location Matters: Frequency-Spatial Dual Space Adaptation for Cross-Domain Few-Shot Segmentation.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same journal

BayeTopo: Bayesian-based Topology-guided Learning for Vascular Imaging Segmentation.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
See all related articles

This study introduces a novel shape-from-focus (SFF) method using neural networks to represent the focused image surface (FIS). This approach overcomes limitations of traditional methods, improving 3-D surface accuracy.

Area of Science:

  • Computer Vision
  • Computational Imaging
  • Machine Learning

Background:

  • Conventional shape-from-focus (SFF) techniques often yield inaccurate 3-D reconstructions.
  • This inaccuracy stems from the piecewise constant approximation of the focused image surface (FIS).

Purpose of the Study:

  • To develop an advanced SFF method that enhances the accuracy of 3-D FIS reconstruction.
  • To leverage neural networks for a more precise representation of the focused image surface.

Main Methods:

  • Proposed a novel SFF scheme utilizing neural network weights to represent the three-dimensional (3-D) FIS.
  • Trained neural networks to learn the FIS shape that optimizes the focus measure.

Main Results:

Related Experiment Videos

  • The neural network-based approach offers a more accurate representation of the focused image surface compared to traditional methods.
  • This method effectively overcomes the limitations associated with piecewise constant approximations in SFF.

    • Conclusions:

    • Representing 3-D FIS using neural network weights presents a promising advancement in shape-from-focus technology.
    • This neural network-driven SFF method enhances reconstruction accuracy and broadens potential applications in 3-D imaging.