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

Perfect image segmentation using pulse coupled neural networks.

G Kuntimad¹, H S Ranganath

¹Rocketdyne Division, Boeing North American, Huntsville, AL 35806, USA.

IEEE Transactions on Neural Networks

|February 7, 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

Smart adaptive optic systems using spatial light modulators.

IEEE transactions on neural networks·2008

Same author

Object detection using pulse coupled neural networks.

IEEE transactions on neural networks·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

This study introduces a novel image segmentation method using pulse coupled neural networks (PCNNs). PCNNs effectively segment images with overlapping regions, enhanced by an inhibition receptive field for improved accuracy.

Area of Science:

Computer Vision
Artificial Intelligence
Computational Neuroscience

Background:

Image segmentation is crucial for image analysis.
Traditional methods struggle with overlapping intensity ranges in regions.
Pulse coupled neural networks (PCNNs) offer a biologically inspired approach.

Purpose of the Study:

To present a PCNN-based method for digital image segmentation.
To analyze the conditions for perfect image segmentation using PCNNs.
To investigate the impact of an inhibition receptive field on segmentation performance.

Main Methods:

Utilizing a modified Eckhorn's cortical neuron model for the pulse coupled neuron (PCN).
Implementing a single-layered, laterally connected PCNN architecture.

Related Experiment Videos

Introducing an inhibition receptive field to the PCN model.

Main Results:

The proposed PCNN method achieves perfect image segmentation, even with significant overlap in adjacent region intensity ranges.
Conditions for achieving perfect segmentation were mathematically derived.
The addition of an inhibition receptive field demonstrably increased the likelihood of perfect segmentation.

Conclusions:

PCNNs provide a robust solution for challenging image segmentation tasks.
The inhibition receptive field enhances PCNNs' ability to differentiate regions with similar intensities.
This method holds potential for various image processing applications requiring precise segmentation.