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

Eigenface-domain super-resolution for face recognition.

Bahadir K Gunturk1, Aziz U Batur, Yucel Altunbasak

  • 1Sch. of Electr. and Comput. Eng., Georgia Inst. of Technol., Atlanta, GA 30332-0250, USA. bahadir@ece.gatech.edu

IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
|February 2, 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 Dual-input deep learning architecture for classification and latency estimation in ABR signals.

Frontiers in medicine·2025
Same author

Spatial and Angular Resolution Enhancement of Light Fields Using Convolutional Neural Networks.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2018
Same author

Approximation and compression with sparse orthonormal transforms.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2015
Same author

Distance estimation using a single computational camera with dual off-axis color filtered apertures.

Optics express·2013
Same author

Joint framework for motion validity and estimation using block overlap.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2012
Same author

Multi-transmitter aperture synthesis with Zernike based aberration correction.

Optics express·2012
Same journal

Style-Aware Contrastive Test-Time Adaptation: A Dual-Cache Model for Robust Vision-Language Alignment.

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

Semantic Frame Interpolation.

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

Physics-Guided Cross-Modal Decoupling with Test-Time Adaptation for Hyperspectral Image Restoration.

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

This study introduces face-space super-resolution to enhance low-resolution surveillance images for face recognition. This method reduces computational cost and improves robustness compared to traditional pixel-domain approaches.

Area of Science:

  • Computer Vision
  • Biometrics
  • Image Processing

Background:

  • Low-resolution face images from surveillance cameras hinder face recognition accuracy.
  • Existing super-resolution methods preprocess images in the pixel domain, increasing computational load.
  • State-of-the-art face recognition often employs dimensionality reduction.

Purpose of the Study:

  • To develop a novel super-resolution technique operating in a lower-dimensional face space.
  • To reduce the computational complexity of super-resolution for surveillance face images.
  • To enhance the robustness of super-resolution against noise and registration errors.

Main Methods:

  • Proposed transferring super-resolution reconstruction from the pixel domain to a lower-dimensional face space.

Related Experiment Videos

  • Developed a reconstruction algorithm to directly generate recognition-relevant information in the low-dimensional domain.
  • Incorporated model-based constraints to improve robustness.

    • Main Results:

    • Achieved a significant decrease in computational complexity for super-resolution reconstruction.
    • Demonstrated that face-space super-resolution is more robust to registration errors and noise than pixel-domain methods.
    • Reconstructed information directly for recognition without generating high-quality visual images.

    Conclusions:

    • Face-space super-resolution offers a computationally efficient and robust alternative for enhancing surveillance face images.
    • This approach bypasses the need for high-resolution image generation, focusing on recognition requirements.
    • The proposed method shows promise for improving the performance of face recognition systems dealing with low-quality imagery.