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

Fast and high performance image subsampling using feedforward neural networks.

A Dumitraş, F Kossentini

    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

    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 presents a novel image subsampling technique utilizing feedforward artificial neural networks (FANNs). The FANN-based method achieves superior performance and efficiency compared to traditional lowpass filtering approaches for image downscaling.

    Area of Science:

    • Computer Vision
    • Artificial Intelligence
    • Image Processing

    Background:

    • Traditional image subsampling often relies on lowpass filtering, which can lead to information loss and computational inefficiency.
    • Developing high-performance and computationally efficient image subsampling methods is crucial for real-time applications and large-scale data processing.

    Discussion:

    • This research introduces a novel image subsampling technique leveraging feedforward artificial neural networks (FANNs).
    • The method incorporates a pattern matching approach to extract local edge information, guiding the FANN's supervised training for optimal output selection.
    • Evaluations demonstrate that this FANN-based subsampling method surpasses conventional lowpass filtering techniques in both subjective and objective assessments.

    Key Insights:

    Related Experiment Videos

  • Feedforward artificial neural networks (FANNs) offer a powerful alternative for image subsampling tasks.
  • Edge information extraction via pattern matching enhances the accuracy and performance of neural network-based subsampling.
  • The proposed method provides a computationally less intensive yet high-performance solution for image downscaling.

    • Outlook:

    • Further research could explore advanced neural network architectures for even greater subsampling accuracy.
    • Integration of this method into real-time video processing pipelines could significantly improve efficiency.
    • Investigating adaptive training strategies for FANNs could broaden the applicability across diverse image types and content.