Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Videos

An image representation algorithm compatible with neural-associative-processor-based hardware recognition systems.

M Yagi¹, T Shibata

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

IEEE Transactions on Neural Networks

|February 5, 2008

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

Risk factors in patients treated with surgical drainage for rhinogenic intracranial complications: a nationwide study.

Rhinology·2025

Same author

Energy-selective confinement of fusion-born alpha particles during internal relaxations in a tokamak plasma.

Nature communications·2022

Same author

Indications for partial parotidectomy using retrograde dissection of the marginal mandibular branch of the facial nerve for benign tumours of the parotid gland.

The British journal of oral & maxillofacial surgery·2018

Same author

Dendritic cells cross-talk with tumour antigen-specific CD8<sup>+</sup> T cells, Vγ9γδT cells and Vα24NKT cells in patients with glioblastoma multiforme and in healthy donors.

Clinical and experimental immunology·2018

Same author

The 67P/Churyumov-Gerasimenko observation campaign in support of the Rosetta mission.

Philosophical transactions. Series A, Mathematical, physical, and engineering sciences·2017

Same author

SU-E-T-294: Maximizing the Availability of Positron Emitting Nuclei for Proton Therapy Verification Using Different Beam Irradiation Sequences.

Medical physics·2017

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 Projected Principal-Edge Distribution (PPED) algorithm creates compact image feature vectors for robust recognition. This method achieves expert-level accuracy in medical radiograph analysis, enabling efficient hardware implementation.

Area of Science:

Computer Vision
Image Processing
Machine Learning

Background:

Developing efficient image representation algorithms is crucial for real-time image recognition systems.
Existing methods often struggle with high dimensionality and preserving perceptual similarity.
VLSI-matching-engine systems require compatible and computationally inexpensive image representations.

Purpose of the Study:

To develop a robust image representation algorithm compatible with VLSI-matching-engine systems.
To achieve significant dimensionality reduction while preserving essential image information.
To validate the algorithm's effectiveness in medical radiograph analysis.

Main Methods:

The Projected Principal-Edge Distribution (PPED) algorithm codes spatial distributions of four-principal-direction edges in grayscale images.

Related Experiment Videos

A 64x64 grayscale image is reduced to a 64-dimension feature vector by projecting edge information.

Dedicated VLSI circuits were developed for PPED vector generation and a hardware recognition system was constructed.

Main Results:

PPED vectors effectively preserve human perception of image similarity.
The algorithm achieved substantial dimensionality reduction of image data.
Medical radiograph analysis using the PPED algorithm yielded results comparable to expert diagnoses.
A hardware system demonstrated successful medical radiograph analysis with low-power operation.

Conclusions:

The PPED representation is a robust and efficient method for image recognition.
The developed algorithm and hardware system are suitable for practical applications, including medical imaging.
The system demonstrates feasibility for low-power, high-performance image analysis.