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

Analog soft-pattern-matching classifier using floating-gate MOS technology.

T Yamasaki1, T Shibata

  • 1Dept. of Electron. Eng., Univ. of Tokyo, Japan.

IEEE Transactions on Neural Networks
|February 5, 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

Bleomycin but not its derivatives inhibits the in vivo shedding of a rat tumor-associated antigen.

Anti-cancer drugs·1992
Same author

[SceI: an endonuclease with multiple cutting sites induces homologous genetic recombination].

Seikagaku. The Journal of Japanese Biochemical Society·1992
Same author

A restriction enzyme, BpuI is an isoschizomer of BanII.

Nucleic acids research·1992
Same author

Benign osteoblastoma in the vertebral body of the thoracic spine. A case report.

Spine·1992
Same author

Protective effects of a prostaglandin E1 oligomer on taurocholate-induced rat pancreatitis.

Journal of gastroenterology and hepatology·1992
Same author

[The effects of potassium concentration in reperfusion solution upon myocardial protection].

[Zasshi] [Journal]. Nihon Kyobu Geka Gakkai·1992
Same journal

Universal perceptron and DNA-like learning algorithm for binary neural networks: LSBF and PBF implementations.

IEEE transactions on neural networks·2013
Same journal

Guest editorial: special section on white box nonlinear prediction models.

IEEE transactions on neural networks·2011
Same journal

Data-based fault-tolerant control of high-speed trains with traction/braking notch nonlinearities and actuator failures.

IEEE transactions on neural networks·2011
Same journal

Guest editorial: special section on data-based control, modeling, and optimization.

IEEE transactions on neural networks·2011
Same journal

Neural network-based multiple robot simultaneous localization and mapping.

IEEE transactions on neural networks·2011
Same journal

Data-driven model-free adaptive control for a class of MIMO nonlinear discrete-time systems.

IEEE transactions on neural networks·2011
See all related articles

A novel flexible analog pattern-matching classifier was developed using floating-gate MOS technology. This system, combined with the projected principal-edge distribution (PPED) algorithm, successfully recognizes handwritten patterns and separates overlapping images.

Area of Science:

  • Electronics
  • Computer Vision
  • Artificial Intelligence

Background:

  • Developing efficient and flexible pattern-matching classifiers is crucial for image recognition tasks.
  • Existing methods often lack adaptability in similarity evaluation, limiting their performance with complex or overlapping patterns.
  • Floating-gate Metal-Oxide-Semiconductor (MOS) technology offers potential for tunable analog circuit functionalities.

Purpose of the Study:

  • To develop a flexible analog pattern-matching classifier.
  • To integrate this classifier with a robust image representation algorithm, projected principal-edge distribution (PPED).
  • To demonstrate the system's capability in recognizing handwritten patterns and classifying overlapping images.

Main Methods:

  • Development of a tunable analog pattern-matching circuit using floating-gate MOS technology.

Related Experiment Videos

  • Implementation of the projected principal-edge distribution (PPED) algorithm for image representation and coding.
  • Fabrication of a test chip using 0.6-/spl mu/m complementary metal-oxide semiconductor (CMOS) technology.
  • Experimental application of the system to recognize handwritten patterns and Arabic numerals.

    • Main Results:

    • The developed analog classifier demonstrated tunable similarity evaluation (peak position, height, sharpness).
    • The system successfully recognized simple handwritten patterns and Arabic numerals when using the PPED algorithm.
    • Experimental results confirmed the capability to separate and classify overlapping patterns.

    Conclusions:

    • The flexible analog pattern-matching classifier, integrated with PPED, offers a viable approach for robust image recognition.
    • Floating-gate MOS technology enables tunable matching functions, enhancing classifier adaptability.
    • The demonstrated performance in recognizing handwritten and overlapping patterns highlights the system's practical potential.