A multi-focus image fusion method and system based on semi-smooth Newton method

By modeling the multifocal image fusion problem as a variational optimization problem and employing a semi-smooth Newton method combined with deep network unfolding techniques, the problems of insufficient feature extraction and artifacts in multifocal image fusion are solved, achieving efficient and interpretable multifocal image reconstruction and improving imaging quality and efficiency.

CN122415352APending Publication Date: 2026-07-17HUAQIAO UNIVERSITY +1
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
HUAQIAO UNIVERSITY
Filing Date
2026-06-09
Publication Date
2026-07-17

AI Technical Summary

Technical Problem

Existing multi-focus image fusion techniques suffer from insufficient extraction of local focus features, difficulty in maintaining global consistency, and susceptibility to artifacts at depth boundaries. Furthermore, deep learning methods are insufficient in terms of computational efficiency and model interpretability, making it difficult to meet the imaging requirements of high precision and high real-time performance.

Method used

The multi-focus image fusion problem is modeled as a variational optimization problem with non-smooth regularization constraints. A semi-smooth Newton method is used, and the optimization algorithm is mapped to a learnable deep network through deep expansion technology. By combining Lagrange dual variables and generalized Jacobian matrices, a multi-focus image fusion system is constructed, which includes the steps of problem modeling, problem solving and optimization, network expansion and image reconstruction.

Benefits of technology

It achieves high-precision full-focus image reconstruction, improves imaging clarity and information integrity, significantly accelerates algorithm convergence speed, enhances the global focusing performance and detail restoration capability of fused images, and improves visual quality and computational efficiency.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122415352A_ABST
    Figure CN122415352A_ABST
Patent Text Reader

Abstract

The application discloses a multi-focus image fusion method and system based on a semi-smooth Newton method, and belongs to the technical field of image processing. The semi-smooth Newton algorithm is used for solving, a proximal operator and a generalized Jacobian matrix are introduced, and the optimization solving process is expanded into a deep network. An adaptive feature iterative reconstruction unit is designed, auxiliary variable updating, a learnable edge convolution, focus gradient perception and a multi-scale frequency enhancement structure are integrated, and iterative optimization is realized in combination with a feature reconstruction block, a multiplier updating module and a matrix updating module. The second-order optimization algorithm is introduced into multi-focus image fusion for the first time, has physical interpretability and strong feature learning capability, and has better fusion effect than existing methods, and has important application value in high-precision imaging fields such as microscopy and remote sensing.
Need to check novelty before this filing date? Find Prior Art