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

Automatic eyeglasses removal from face images.

Chenyu Wu1, Ce Liu, Heung-Yueng Shum

  • 1Robotics Institute, Carnegie Mellon University, 5000 Forbes Avenue, Pittsburgh, PA 15213, USA. chenyuwu@cmu.edu

IEEE Transactions on Pattern Analysis and Machine Intelligence
|September 21, 2004
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

Absolute configurations and anti-bacterial activity of two century-old maleidrides.

Natural product research·2026
Same author

Association between residential physical environmental exposures and multidimensional successful ageing in the UK biobank.

BMC public health·2026
Same author

Smarter Data: Rethinking Data Generation for Machine Learning Potentials in Heterogeneous Catalysis.

JACS Au·2026
Same author

Development of a gene signature related to phospholipid metabolism for prognosis and therapeutic Prediction in Osteosarcoma: Focus on VAC14.

Gene·2026
Same author

Impact of incorporating Chinese cultural elements into product attributes on purchase intentions via multiple mediating roles of cultural identity: Evidence from the Forbidden City.

Acta psychologica·2026
Same author

Tumor organoids as a revolutionary platform for advancing cancer nanomedicine.

Molecular cancer·2026

This study introduces an intelligent system for automatic eyeglasses removal from face images. The novel approach effectively removes eyeglasses and synthesizes realistic facial details for improved image editing.

Area of Science:

  • Computer Vision
  • Image Processing
  • Artificial Intelligence

Background:

  • Manual removal of eyeglasses in digital images is challenging due to the difficulty of realistically filling the occluded facial region.
  • Existing pixel-level editing tools struggle to accurately reconstruct the underlying facial features after removing eyeglasses.

Purpose of the Study:

  • To develop an intelligent system for automatic eyeglasses removal and face synthesis.
  • To address the limitations of conventional image editing by providing an object-level removal and inpainting solution.

Main Methods:

  • Utilized an eye region detector for initial eyeglasses localization.
  • Employed a Markov-chain Monte Carlo method for precise key point localization on eyeglass frames.
  • Developed a novel sample-based synthesis approach using statistical analysis to reconstruct the face without eyeglasses.

Related Experiment Videos

Main Results:

  • The system successfully detects, localizes, and removes eyeglasses from input frontal face images.
  • The proposed method effectively synthesizes the occluded facial region, creating a seamless result.
  • Extensive experiments validated the system's effectiveness in eyeglasses removal.

Conclusions:

  • The intelligent image editing system offers an effective solution for automatic eyeglasses removal.
  • The object-level approach and novel synthesis technique overcome challenges in realistic facial reconstruction.
  • This research advances automated face editing capabilities in computer vision.