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

Hough transform network: learning conoidal structures in a connectionist framework.

J Basak¹, A Das

¹Machine Intelligence Unit, Indian Stat. Inst., Calcutta.

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

Search for large extra dimensions via single photon plus missing energy final states at sqrt s = 1.96 TeV.

Physical review letters·2008

Same author

An evaluation of four different phenotypic techniques for detection of metallo-beta-lactamase producing Pseudomonas aeruginosa.

Indian journal of medical microbiology·2008

Same author

Cardiac botryomycosis: an autopsy report.

Journal of clinical pathology·2008

Same author

Monitoring dopants by Raman scattering in an electrochemically top-gated graphene transistor.

Nature nanotechnology·2008

Same author

Search for scalar neutrino superpartners in e+mu final states in pp collisions at sqrt[s]=1.96 TeV.

Physical review letters·2008

Same author

First study of the radiation-amplitude zero in Wgamma production and limits on anomalous WWgamma couplings at sqrt[s]=1.96 TeV.

Physical review letters·2008

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 neural network model efficiently learns conoidal shapes from image data. This adaptive method offers precise parameter representation, outperforming traditional Hough transform techniques.

Area of Science:

Computer Vision
Machine Learning
Pattern Recognition

Background:

Classical Hough Transform (HT) methods for shape detection require significant computational resources and can suffer from parameter precision limitations.
Efficient representation of visual information is crucial for advanced image analysis and pattern recognition tasks.
Conoidal shapes, including lines, circles, and ellipses, are fundamental geometric primitives in image understanding.

Purpose of the Study:

To develop a novel two-layer neural-network model for adaptive learning of conoidal shape parameters.
To achieve a more efficient representation of visual information compared to existing methods.
To enhance the precision of parameter representation for detected shapes.

Main Methods:

Related Experiment Videos

A two-layer neural network architecture was designed to accept image coordinates as input.

The model adaptively learns the parametric form of conoidal shapes (lines, circles, ellipses).

Visual information is encoded within the network's connection weights and processing element parameters.

Main Results:

The neural network model provides an efficient representation of visual information.
The proposed method significantly reduces the space requirements compared to the classical Hough transform (HT).
Higher precision in parameter representation was achieved, outperforming existing algorithms in multiple scenarios.

Conclusions:

The developed neural-network model offers a superior alternative for conoidal shape detection and representation.
The adaptive learning approach enhances efficiency and precision in visual information processing.
This methodology demonstrates significant advantages over traditional algorithms in terms of space and accuracy.