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

Content-based image retrieval system using neural networks.

T Ikeda1, M Hagiwara

  • 1Department of Information and Computer Science, Faculty of Science and Technology, Keio University, Yokohama, Japan.

International Journal of Neural Systems
|February 24, 2001
PubMed
Summary

This study introduces a novel image retrieval system using neural networks (NNs) for fast and accurate sketch-based image retrieval. The system learns image features and improves performance through continuous learning from user sketches.

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

Prognostic factors and treatment response in HER2-positive gastric cancer patients receiving trastuzumab deruxtecan: secondary analysis of the EN-DEAVOR study.

ESMO gastrointestinal oncology·2026
Same author

Photoemission Orbital Tomography Using a Robust Sparse PhaseLift.

The journal of physical chemistry. A·2024
Same author

Differentiation of Jugular Foramen Paragangliomas versus Schwannomas Using Golden-Angle Radial Sparse Parallel Dynamic Contrast-Enhanced MRI.

AJNR. American journal of neuroradiology·2021
Same author

E_{8} Spectra of Quasi-One-Dimensional Antiferromagnet BaCo_{2}V_{2}O_{8} under Transverse Field.

Physical review letters·2021
Same author

Therapeutics potentiating microglial p21-Nrf2 axis can rescue neurodegeneration caused by neuroinflammation.

Science advances·2020
Same author

Dynamic Contrast-Enhanced MRI to Differentiate Parotid Neoplasms Using Golden-Angle Radial Sparse Parallel Imaging.

AJNR. American journal of neuroradiology·2019

Area of Science:

  • Computer Science
  • Artificial Intelligence
  • Image Processing

Background:

  • Traditional image retrieval systems often struggle with sketch-based queries.
  • Neural networks (NNs) offer powerful pattern recognition and association capabilities.

Purpose of the Study:

  • To develop an effective image retrieval system utilizing neural networks (NNs).
  • To enable fast and accurate retrieval of images based on user-drawn sketches.

Main Methods:

  • Utilized multilayer NNs as matching engines to calculate similarities between sketches and stored images.
  • Implemented a learning phase where NNs memorize pixel information of image thumbnails.
  • Developed a retrieval phase where NNs process sketch pixel information to identify candidate images.

Related Experiment Videos

Main Results:

  • The system demonstrates quick and correct retrieval of candidate images.
  • The system incorporates a learning capability to extract sketch features and enhance performance.
  • Implemented software with graphical user interfaces has been tested.

Conclusions:

  • The proposed neural network-based system provides an effective solution for sketch-based image retrieval.
  • The system's parallelism and association abilities contribute to its efficiency and accuracy.
  • Experimental tests confirm the effectiveness of the developed image retrieval system.