A Real-Time High-Resolution Multi-Focus Image Fusion Algorithm Based on Multi-Scale Feature Aggregation

In microscopic imaging, the key to obtaining a fully clear image lies in effectively extracting and fusing the sharp regions from different focal planes. However, traditional multi-focus image fusion algorithms have high computational complexity, making it difficult to achieve real-time processing o...

Full description

Saved in:
Bibliographic Details
Main Authors: Huawei Chen, Xingkai Du, Hongchuan Huang, Tingyu Zhao
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/13/6967
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849319836297986048
author Huawei Chen
Xingkai Du
Hongchuan Huang
Tingyu Zhao
author_facet Huawei Chen
Xingkai Du
Hongchuan Huang
Tingyu Zhao
author_sort Huawei Chen
collection DOAJ
description In microscopic imaging, the key to obtaining a fully clear image lies in effectively extracting and fusing the sharp regions from different focal planes. However, traditional multi-focus image fusion algorithms have high computational complexity, making it difficult to achieve real-time processing on embedded devices. We propose an efficient high-resolution real-time multi-focus image fusion algorithm based on multi-aggregation. we use a difference of Gaussians image and a Laplacian pyramid for focused region detection. Additionally, the image is down-sampled before the focused region detection, and up-sampling is applied at the output end of the decision map, thereby reducing 75% of the computational data volume. The experimental results show that the proposed algorithm excels in both focused region extraction and computational efficiency evaluation. It achieves comparable image fusion quality to other algorithms while significantly improving processing efficiency. The average time for multi-focus image fusion with a 4K resolution image on embedded devices is 0.586 s. Compared with traditional algorithms, the proposed method achieves a 94.09% efficiency improvement on embedded devices and a 21.17% efficiency gain on desktop computing platforms.
format Article
id doaj-art-2f95c598c6cb4358bc50cd3eae3010a7
institution Kabale University
issn 2076-3417
language English
publishDate 2025-06-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-2f95c598c6cb4358bc50cd3eae3010a72025-08-20T03:50:17ZengMDPI AGApplied Sciences2076-34172025-06-011513696710.3390/app15136967A Real-Time High-Resolution Multi-Focus Image Fusion Algorithm Based on Multi-Scale Feature AggregationHuawei Chen0Xingkai Du1Hongchuan Huang2Tingyu Zhao3Zhejiang Key Laboratory of Quantum State Control and Optical Field Manipulation, Department of Physics, Zhejiang Sci-Tech University, Hangzhou 310018, ChinaZhejiang Key Laboratory of Quantum State Control and Optical Field Manipulation, Department of Physics, Zhejiang Sci-Tech University, Hangzhou 310018, ChinaZhejiang Key Laboratory of Quantum State Control and Optical Field Manipulation, Department of Physics, Zhejiang Sci-Tech University, Hangzhou 310018, ChinaZhejiang Key Laboratory of Quantum State Control and Optical Field Manipulation, Department of Physics, Zhejiang Sci-Tech University, Hangzhou 310018, ChinaIn microscopic imaging, the key to obtaining a fully clear image lies in effectively extracting and fusing the sharp regions from different focal planes. However, traditional multi-focus image fusion algorithms have high computational complexity, making it difficult to achieve real-time processing on embedded devices. We propose an efficient high-resolution real-time multi-focus image fusion algorithm based on multi-aggregation. we use a difference of Gaussians image and a Laplacian pyramid for focused region detection. Additionally, the image is down-sampled before the focused region detection, and up-sampling is applied at the output end of the decision map, thereby reducing 75% of the computational data volume. The experimental results show that the proposed algorithm excels in both focused region extraction and computational efficiency evaluation. It achieves comparable image fusion quality to other algorithms while significantly improving processing efficiency. The average time for multi-focus image fusion with a 4K resolution image on embedded devices is 0.586 s. Compared with traditional algorithms, the proposed method achieves a 94.09% efficiency improvement on embedded devices and a 21.17% efficiency gain on desktop computing platforms.https://www.mdpi.com/2076-3417/15/13/6967multi-focus image fusionLaplacian pyramidembedded devicedown-samplingreal-time processing
spellingShingle Huawei Chen
Xingkai Du
Hongchuan Huang
Tingyu Zhao
A Real-Time High-Resolution Multi-Focus Image Fusion Algorithm Based on Multi-Scale Feature Aggregation
Applied Sciences
multi-focus image fusion
Laplacian pyramid
embedded device
down-sampling
real-time processing
title A Real-Time High-Resolution Multi-Focus Image Fusion Algorithm Based on Multi-Scale Feature Aggregation
title_full A Real-Time High-Resolution Multi-Focus Image Fusion Algorithm Based on Multi-Scale Feature Aggregation
title_fullStr A Real-Time High-Resolution Multi-Focus Image Fusion Algorithm Based on Multi-Scale Feature Aggregation
title_full_unstemmed A Real-Time High-Resolution Multi-Focus Image Fusion Algorithm Based on Multi-Scale Feature Aggregation
title_short A Real-Time High-Resolution Multi-Focus Image Fusion Algorithm Based on Multi-Scale Feature Aggregation
title_sort real time high resolution multi focus image fusion algorithm based on multi scale feature aggregation
topic multi-focus image fusion
Laplacian pyramid
embedded device
down-sampling
real-time processing
url https://www.mdpi.com/2076-3417/15/13/6967
work_keys_str_mv AT huaweichen arealtimehighresolutionmultifocusimagefusionalgorithmbasedonmultiscalefeatureaggregation
AT xingkaidu arealtimehighresolutionmultifocusimagefusionalgorithmbasedonmultiscalefeatureaggregation
AT hongchuanhuang arealtimehighresolutionmultifocusimagefusionalgorithmbasedonmultiscalefeatureaggregation
AT tingyuzhao arealtimehighresolutionmultifocusimagefusionalgorithmbasedonmultiscalefeatureaggregation
AT huaweichen realtimehighresolutionmultifocusimagefusionalgorithmbasedonmultiscalefeatureaggregation
AT xingkaidu realtimehighresolutionmultifocusimagefusionalgorithmbasedonmultiscalefeatureaggregation
AT hongchuanhuang realtimehighresolutionmultifocusimagefusionalgorithmbasedonmultiscalefeatureaggregation
AT tingyuzhao realtimehighresolutionmultifocusimagefusionalgorithmbasedonmultiscalefeatureaggregation