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

Image identification system based on an optical broadcast neural network processor.

Marta Ruiz-Llata1, Horacio Lamela-Rivera

  • 1Grupo de Optoelectrónica y Tecnología Láser, Universidad Carlos III de Madrid, C/Butarque 15, 28911 Leganés, Madrid, Spain. mruizl@ing.uc3m.es

Applied Optics
|May 3, 2005
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

Palladium Porphyrin-Modified Fibrin Hydrogel for Oxygen Sensing in Engineered Skin Tissue Applications.

ACS omega·2026
Same author

Sub-ppm-Level Ammonia Detection Using Photoacoustic Spectroscopy with an Optical Microphone Based on a Phase Interferometer.

Sensors (Basel, Switzerland)·2019
Same author

Detection of Partial Discharge Sources Using UHF Sensors and Blind Signal Separation.

Sensors (Basel, Switzerland)·2017
Same author

Laser range finder approach based on a fieldable electro-optic dual optical frequency comb: a proof of concept.

Applied optics·2017
Same author

Remote diffuse reflectance spectroscopy sensor for tissue engineering monitoring based on blind signal separation.

Biomedical optics express·2014
Same author

High resolution (<1nm) interferometric fiber-optic sensor of vibrations in high-power transformers.

Optics express·2009

This study presents a novel vision system using a hardware neural processor. The system efficiently classifies images by combining optics and electronics for high-speed, scalable performance.

Area of Science:

  • Optoelectronics
  • Computer Vision
  • Artificial Neural Networks

Background:

  • Traditional vision systems face limitations in processing speed and scalability.
  • Integrating optical and electronic components offers potential for enhanced computational power.
  • Neural network architectures are well-suited for complex pattern recognition tasks.

Purpose of the Study:

  • To implement and evaluate a vision system leveraging a hardware neural processor.
  • To optimize the architecture for efficient computation and signal communication.
  • To adapt the system for image classification using a complementary metal-oxide semiconductor sensor.

Main Methods:

  • Designed a neural network processor architecture combining electronic computation and optical signal broadcast.

Related Experiment Videos

  • Built a prototype vision system using discrete optical and optoelectronic devices.
  • Adapted the system as a Hamming classifier for 128 x 128 image data.

    • Main Results:

    • Demonstrated a functional image classification system based on the optoelectronic neural processor.
    • Characterized the performance and scalability of the vision system.
    • Analyzed the potential for future improvements in size and speed.

    Conclusions:

    • The implemented vision system shows promise for efficient image classification.
    • The hybrid optoelectronic neural processor architecture is scalable and offers performance advantages.
    • Further development of optoelectronic neural processors can lead to significant advancements in vision systems.