Enhancing Noise Robustness in Focus Measure Using Tight Framelet Features

Yan-Ran Li; Junwei Liu; Zhangtao Ye; Lixin Shen; Xiaosheng Zhuang

doi:10.1109/LSP.2025.3553425

Enhancing Noise Robustness in Focus Measure Using Tight Framelet Features

Yan-Ran Li, Junwei Liu, Zhangtao Ye, Lixin Shen, Xiaosheng Zhuang^*

^*Corresponding author for this work

Department of Mathematics

Research output: Journal Publications and Reviews › RGC 21 - Publication in refereed journal › peer-review

Abstract

Focus measures are widely used to assess image clarity in various fields, such as photography and computer vision. However, many existing focus measures face challenges in balancing noise robustness and measurement capability. In this letter, a novel focus measure called Variance of Tight Framelet Feature (VTFF) is proposed to address this challenge. VTFF leverages the advantages of tight framelet features and variance information in feature maps to provide a robust and accurate assessment of image focus. Experimental results on both synthetic and real-world data demonstrate its superior performance compared to recent focus measures in measurement capability, noise robustness, and real-time performance.

© 2025 IEEE. All rights reserved, including rights for text and data mining, and training of artificial intelligence and similar technologies. Personal use is permitted, but republication/redistribution requires IEEE permission.

Original language	English
Pages (from-to)	1435-1439
Journal	IEEE Signal Processing Letters
Volume	32
Online published	20 Mar 2025
DOIs	https://doi.org/10.1109/LSP.2025.3553425
Publication status	Published - 2025

Funding

The work of Yan-Ran Li was supported in part by the National Natural Science Foundation of China under Grant 12471400 and in part by the Shenzhen Science and Technology Program under Grant JCYJ20230808105610021. The work of Lixin Shen was supported in part by the National Science Foundation under Grant DMS-1913039 and Grant DMS-2208385, and in part by Syracuse CUSE. The work of Xiaosheng Zhuang was supported in part by the Research Grants Council of Hong Kong under Grant CityU 11309122, Grant CityU 11302023, and Grant CityU 11301224 and in part by the Innovation and Technology Commission of Hong Kong under Grant MHP/054/22.

Research Keywords

Focus measure
noise robustness
tight framelet features

Access Output

10.1109/LSP.2025.3553425

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@article{97bb0a4f9ed34509ab748eec4526fc19,

title = "Enhancing Noise Robustness in Focus Measure Using Tight Framelet Features",

abstract = "Focus measures are widely used to assess image clarity in various fields, such as photography and computer vision. However, many existing focus measures face challenges in balancing noise robustness and measurement capability. In this letter, a novel focus measure called Variance of Tight Framelet Feature (VTFF) is proposed to address this challenge. VTFF leverages the advantages of tight framelet features and variance information in feature maps to provide a robust and accurate assessment of image focus. Experimental results on both synthetic and real-world data demonstrate its superior performance compared to recent focus measures in measurement capability, noise robustness, and real-time performance. {\textcopyright} 2025 IEEE. All rights reserved, including rights for text and data mining, and training of artificial intelligence and similar technologies. Personal use is permitted, but republication/redistribution requires IEEE permission.",

keywords = "Focus measure, noise robustness, tight framelet features",

author = "Yan-Ran Li and Junwei Liu and Zhangtao Ye and Lixin Shen and Xiaosheng Zhuang",

year = "2025",

doi = "10.1109/LSP.2025.3553425",

language = "English",

volume = "32",

pages = "1435--1439",

journal = "IEEE Signal Processing Letters",

issn = "1070-9908",

publisher = "IEEE",

}

TY - JOUR

T1 - Enhancing Noise Robustness in Focus Measure Using Tight Framelet Features

AU - Li, Yan-Ran

AU - Liu, Junwei

AU - Ye, Zhangtao

AU - Shen, Lixin

AU - Zhuang, Xiaosheng

PY - 2025

Y1 - 2025

N2 - Focus measures are widely used to assess image clarity in various fields, such as photography and computer vision. However, many existing focus measures face challenges in balancing noise robustness and measurement capability. In this letter, a novel focus measure called Variance of Tight Framelet Feature (VTFF) is proposed to address this challenge. VTFF leverages the advantages of tight framelet features and variance information in feature maps to provide a robust and accurate assessment of image focus. Experimental results on both synthetic and real-world data demonstrate its superior performance compared to recent focus measures in measurement capability, noise robustness, and real-time performance. © 2025 IEEE. All rights reserved, including rights for text and data mining, and training of artificial intelligence and similar technologies. Personal use is permitted, but republication/redistribution requires IEEE permission.

AB - Focus measures are widely used to assess image clarity in various fields, such as photography and computer vision. However, many existing focus measures face challenges in balancing noise robustness and measurement capability. In this letter, a novel focus measure called Variance of Tight Framelet Feature (VTFF) is proposed to address this challenge. VTFF leverages the advantages of tight framelet features and variance information in feature maps to provide a robust and accurate assessment of image focus. Experimental results on both synthetic and real-world data demonstrate its superior performance compared to recent focus measures in measurement capability, noise robustness, and real-time performance. © 2025 IEEE. All rights reserved, including rights for text and data mining, and training of artificial intelligence and similar technologies. Personal use is permitted, but republication/redistribution requires IEEE permission.

KW - Focus measure

KW - noise robustness

KW - tight framelet features

UR - http://www.scopus.com/inward/record.url?scp=105001194536&partnerID=8YFLogxK

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-105001194536&origin=recordpage

U2 - 10.1109/LSP.2025.3553425

DO - 10.1109/LSP.2025.3553425

M3 - RGC 21 - Publication in refereed journal

SN - 1070-9908

VL - 32

SP - 1435

EP - 1439

JO - IEEE Signal Processing Letters

JF - IEEE Signal Processing Letters

ER -

Enhancing Noise Robustness in Focus Measure Using Tight Framelet Features

Abstract

Funding

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

GRF: Graph Framelets for Graph Deep Learning: Homophily and Heterophily

ITF: Artificial Intelligence Methods and Applications for Breast Cancer Diagnosis and Treatment in Clinical Trials

GRF: Framelets for Geometric Deep Learning: Spheres, Graphs, and Neural Networks

Cite this

Enhancing Noise Robustness in Focus Measure Using Tight Framelet Features

Abstract

Funding

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Projects

GRF: Graph Framelets for Graph Deep Learning: Homophily and Heterophily

ITF: Artificial Intelligence Methods and Applications for Breast Cancer Diagnosis and Treatment in Clinical Trials

GRF: Framelets for Geometric Deep Learning: Spheres, Graphs, and Neural Networks

Cite this