Search research articles

Search research articles

Related Experiment Videos

Multiple contour extraction from graylevel images using an artificial neural network.

Y V Venkatesh¹, S Kumar Raja, N Ramya

¹Department of Electrical and Computer Engineering, Faculty of Engineering, National University of Singapore, Singapore 117576. eleyvv@nus.edu.sg

IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society

|April 4, 2006

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

Stagnation-point flow of a Sisko nanofluid over a stretching surface with heat generation and nano-transport phenomena.

Scientific reports·2025

Same author

Coping strategies among professional social work trainees - A cross-sectional study from India's capital city.

Journal of education and health promotion·2024

Same author

Two new species of tribe Agalliini (Hemiptera: Cicadellidae: Megophthalminae) with note on intraspecific variations.

Zootaxa·2018

Same author

A study on coping patterns of junior college students.

Indian journal of psychological medicine·2011

Same author

On the application of a modified self-organizing neural network to estimate stereo disparity.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2007

Same author

Encoded pattern classification using constructive learning algorithms based on learning vector quantization.

Neural networks : the official journal of the International Neural Network Society·2003

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

We introduce the batch-SOM (BSOM), a novel self-organizing map (SOM) approach for active contour modeling (ACM). This method effectively extracts object contours from images, outperforming existing techniques.

Area of Science:

Computer Vision
Image Processing
Machine Learning

Background:

Active contour modeling (ACM) is crucial for image segmentation.
Existing snake-based ACMs rely on explicit energy functionals, which can be sensitive to image noise and weak edges.
Self-organizing map (SOM)-based ACMs offer an alternative but may lack robustness in certain scenarios.

Purpose of the Study:

To propose a novel SOM-based active contour model, the batch-SOM (BSOM).
To integrate the strengths of SOM and snake-based ACMs for robust contour extraction.
To extend the BSOM for segmenting multiple objects within an image.

Main Methods:

The batch-SOM (BSOM) utilizes feature points from edge maps to guide contour evolution.
It incorporates local gradient and intensity variations to prevent contour leakage, even with imperfect feature points.

Related Experiment Videos

Unlike snake models, BSOM avoids explicit energy functional minimization for contour control.

An extended BSOM version handles multi-object segmentation by splitting contours.

Main Results:

The BSOM demonstrates superior performance in extracting contours from synthetic and real-world images.
It effectively handles images with single and multiple objects, including those with convex and nonconvex boundaries.
The extended BSOM successfully segments multiple objects by adaptive contour splitting.

Conclusions:

The BSOM offers a robust and effective alternative to traditional snake-based ACMs.
Its ability to integrate feature points with local image properties enhances contour extraction accuracy.
The extended BSOM provides a viable solution for multi-object segmentation tasks.