Related Experiment Video
Updated: Jul 17, 2026
14:08
Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
Published on: April 13, 2013
Multilevel Medical Image Fusion using Segmented Image by Level Set Evolution with Region Competition
Shruti Garg1, K Ushah Kiran, Ram Mohan
1Indian Institute of Information Technology, Allahabad
Summary
This study introduces a novel region-based image fusion method using wavelet transform. The technique effectively merges image regions to enhance detail and improve fused image quality for various image types.
Area of Science:
- Computer Vision
- Image Processing
- Signal Processing
Background:
- Image fusion combines multiple images into a single, more informative image.
- Existing methods may struggle with preserving fine details and regional information.
Purpose of the Study:
- To develop and analyze a region-level image fusion technique using wavelet transform.
- To improve the quality of fused images by effectively extracting and utilizing regional features.
Main Methods:
- A region-based image representation approach is employed.
- A novel segmentation algorithm is proposed for effective region extraction.
- Multi-level decomposition using wavelet transform is applied for fusion.
Main Results:
- The proposed method significantly enhances fused image quality.
- Finer details are extracted by analyzing images at multiple decomposition levels.
- Performance is validated using Mutual Information criteria for normal and multifocused images.
Conclusions:
- The region-level wavelet-based image fusion technique offers superior performance.
- The method effectively captures and integrates regional information for improved fusion.
- This approach provides a significant advancement in image fusion quality.
