Related Experiment Video
Updated: Mar 12, 2026
10:39
A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment
Published on: May 24, 2022
2.8K
Active Contours Using Additive Local and Global Intensity Fitting Models for Intensity Inhomogeneous Image
Shafiullah Soomro1, Farhan Akram2, Jeong Heon Kim3
1Department of Computer Science and Engineering, Chung-Ang University, Seoul 156-756, Republic of Korea.
Computational and Mathematical Methods in Medicine
|November 2, 2016
Summary
This study presents an improved active contour model using level sets for image segmentation. The new method enhances object boundary detection, especially in images with uneven lighting, outperforming existing techniques.
Area of Science:
- Computer Vision
- Image Processing
- Computational Imaging
Background:
- Image segmentation is crucial for analyzing visual data.
- Existing methods like the Chan-Vese (CV) model struggle with images exhibiting intensity inhomogeneity.
- Active contour models offer a promising approach but require refinement for complex scenarios.
Purpose of the Study:
- To introduce an advanced region-based active contour method for robust image segmentation.
- To develop an energy functional that effectively handles intensity variations within images.
- To improve upon the limitations of current segmentation techniques, particularly the CV model.
Main Methods:
- A level set formulation is employed for the active contour model.
- An energy functional is proposed, integrating both local and global intensity fitting terms.
- The global intensity fitting term utilizes a global division algorithm for enhanced image information capture.
- Local and global terms are combined to address intensity inhomogeneity.
Main Results:
- The proposed method demonstrates superior performance in segmenting images with intensity inhomogeneity.
- Qualitative and quantitative experimental results show improvements over state-of-the-art methods.
- The integrated local and global fitting terms effectively guide contour evolution.
Conclusions:
- The developed active contour method offers a significant advancement in image segmentation.
- The approach effectively segments images with challenging intensity variations.
- This method provides a more accurate and reliable tool for image analysis tasks.
