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

High-order image subsampling using feedforward artificial neural networks.

A Dumitras1, F Kossentini

  • 1AT&T Labs-Research, Middletown, NJ 07748, USA. adriand@ieee.org

IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
|February 6, 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 fast PNN design algorithm for entropy-constrained residual vector quantization.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2008
Same author

Semi-fixed-length motion vector coding for H.263-based low bit rate video compression.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2008
Same author

On RD optimized progressive image coding using JPEG.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2008
Same author

An efficient computation-constrained block-based motion estimation algorithm for low bit rate video coding.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2008
Same author

Rate-distortion-constrained subband video coding.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2008
Same author

Reconstruction of baseline JPEG coded images in error prone environments.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2008
Same journal

Change-Prior-Guided Unsupervised Change Detection of Heterogeneous Remote Sensing Images.

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

AgonicDreamer: Enhancing Multi-View Consistency in Text-to-3D Generation via Rectified Score Distillation.

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

BiCM-Prompt: Bidirectional Cross-Modal Prompt Tuning for Class-Incremental Learning on Multisource Remote Sensing Images.

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

GoP-based Quality Enhancement on Video Compression.

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

Align then Tensorize: Multi-Level Consistent Anchor Graph Learning for Scalable Multi-View Clustering.

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

Beyond Fidelity: Diverse Image Synthesis via Retrieval-Augmented Diffusion.

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

This study introduces a novel high-order image subsampling method using feedforward artificial neural networks (FANNs). The approach enhances image quality and processing speed compared to traditional techniques.

Area of Science:

  • Computer Vision
  • Image Processing
  • Artificial Intelligence

Background:

  • Traditional image subsampling methods often struggle with preserving details in both smooth and high-detail areas.
  • Lowpass filtering and basic subsampling techniques can lead to information loss and artifacts.

Purpose of the Study:

  • To develop an advanced image subsampling technique utilizing feedforward artificial neural networks (FANNs).
  • To improve the speed-performance tradeoff in high-order image subsampling.

Main Methods:

  • Decomposing high-order subsampling into sequential first-order stages.
  • Employing a tridiagonally symmetrical FANN in the first stage, designed using the Dumitras and Kossentini algorithm.
  • Utilizing a fully connected FANN in the second stage.

Related Experiment Videos

  • Training FANNs with local edge information extracted via pattern matching.

    • Main Results:

    • The proposed multistage FANN method effectively subsamples both high-detail and smooth image regions.
    • Achieves superior subjective and objective performance over traditional lowpass filtering and subsampling methods.
    • Demonstrates excellent speed-performance tradeoffs.

    Conclusions:

    • The novel FANN-based multistage subsampling method offers a significant improvement over existing techniques.
    • This approach provides a robust solution for high-quality image subsampling with enhanced efficiency.