Search research articles

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

NDVI and Beyond: Vegetation Indices as Features for Crop Recognition and Segmentation in Hyperspectral Data.

Sensors (Basel, Switzerland)·2025

Same author

Lessons Learned From European Health Data Projects With Cancer Use Cases: Implementation of Health Standards and Internet of Things Semantic Interoperability.

Journal of medical Internet research·2025

Same author

A Review of CNN Applications in Smart Agriculture Using Multimodal Data.

Sensors (Basel, Switzerland)·2025

See all related 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 Video

Updated: Oct 22, 2025

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

Color Image Complexity versus Over-Segmentation: A Preliminary Study on the Correlation between Complexity Measures

Mihai Ivanovici¹, Radu-Mihai Coliban¹, Cosmin Hatfaludi¹

¹Electronics and Computers Department, Transilvania University of Braşov, 500036 Braşov, Romania.

Journal of Imaging

|August 30, 2021

Summary

This study differentiates image difficulty and complexity, finding that color entropy and fractal dimension can help predict segmentation difficulty. This aids in understanding and potentially automating image segmentation tasks.

Keywords:

JSEG color entropy color fractal dimension image complexity quasi-flat zones

More Related Videos

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Simultaneous Multicolor Imaging of Biological Structures with Fluorescence Photoactivation Localization Microscopy

Simultaneous Multicolor Imaging of Biological Structures with Fluorescence Photoactivation Localization Microscopy

Published on: December 9, 2013

Related Experiment Videos

Last Updated: Oct 22, 2025

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Simultaneous Multicolor Imaging of Biological Structures with Fluorescence Photoactivation Localization Microscopy

Simultaneous Multicolor Imaging of Biological Structures with Fluorescence Photoactivation Localization Microscopy

Published on: December 9, 2013

Area of Science:

Computer Vision
Image Processing
Computational Photography

Background:

Image segmentation is often considered a complex task.
Distinguishing between task difficulty and inherent image complexity is crucial.
Existing complexity measures may not fully capture segmentation challenges.

Purpose of the Study:

To investigate the correlation between color image complexity measures and segmentation results.
To explore the relationship between image complexity, over-segmentation, and prediction of segmentation difficulty.
To analyze color entropy and color fractal dimension as predictors for segmentation outcomes.

Main Methods:

Reduced image complexity using low-pass filtering.
Analyzed color entropy and color fractal dimension.
Correlated complexity metrics with the number of segments (quasi-flat zones and JSEG regions) on fractal and Berkeley datasets.

Main Results:

Observed evolution of complexity measures and segment counts as image complexity decreased.
Demonstrated a correlation between color entropy, fractal dimension, and segmentation results.
Provided experimental evidence for predicting segmentation difficulty.

Conclusions:

Color entropy and fractal dimension show potential for predicting color image segmentation difficulty.
Understanding complexity-image segmentation relationships can guide algorithm development.
Further research can refine these predictive models for practical applications.