与图像内容无关的聚焦程度评价方法

夏晓华; 柴玉琳; 岳鹏举; 杨治; 秦绪芳

doi:10.7652/xjtuxb202501011

您当前的位置：

首页 >

文章列表页 >

与图像内容无关的聚焦程度评价方法

更新时间：2026-01-06

- 与图像内容无关的聚焦程度评价方法
- Focus Evaluation Method with Independent of Image Content
- 西安交通大学学报 2025年59卷第1期页码：116-124
- 作者机构：
  
  长安大学道路施工技术与装备教育部重点实验室， 710000，西安
- 作者简介：
  
  夏晓华（1987—），男，副教授，博士生导师。
- 基金信息：
  
  国家自然科学基金资助项目(61901056);陕西省重点研发计划资助项目(2024GX-YBXM-197)
- DOI：10.7652/xjtuxb202501011
  中图分类号： TP399
- 收稿：2024-05-12，
  
  网络首发：2024-09-10，
  
  纸质出版：2025-01-10
- 稿件说明：
移动端阅览
夏晓华, 柴玉琳, 岳鹏举, 等. 与图像内容无关的聚焦程度评价方法[J]. 西安交通大学学报, 2025,59(1):116-124.

XIA Xiaohua, CHAI Yulin, YUE Pengju, et al. Focus Evaluation Method with Independent of Image Content[J]. Journal of Xi’an Jiaotong University, 2025, 59(1): 116-124.
夏晓华, 柴玉琳, 岳鹏举, 等. 与图像内容无关的聚焦程度评价方法[J]. 西安交通大学学报, 2025,59(1):116-124. DOI： 10.7652/xjtuxb202501011.

XIA Xiaohua, CHAI Yulin, YUE Pengju, et al. Focus Evaluation Method with Independent of Image Content[J]. Journal of Xi’an Jiaotong University, 2025, 59(1): 116-124. DOI： 10.7652/xjtuxb202501011.

摘要

针对现有的聚焦程度评价方法在图像场景内容改变时不能正确评价图像聚焦程度的问题，基于“分类+拟合”的思想，提出了一种与高斯模糊标准差完全等价的图像聚焦程度评价方法。首先，建立了以有限高斯模糊标准差为标记的图像聚焦程度分类数据集；然后，构建了用于提取图像高斯模糊标准差分类分数的非对称核卷积神经网络（AKC-net）；最后，采用三次样条插值函数拟合AKC-net全连接层输出的分类分数以及对应的高斯模糊标准差，以最大分数对应的标准差作为图像的聚焦程度评价结果，并在Waterloo数据集和实际拍摄图像上分别进行仿真实验和实拍实验。结果表明：所提方法在不同聚焦图像上分类的平均准确率可达到97.7%，得到的评价结果与高斯模糊标准差真值的均方根误差和平均绝对误差均小于0.07，且实际拍摄图像的聚焦测度值与图像内容无关，实现了图像聚焦程度的绝对评价。

Abstract

In response to the challenge where current focus evaluation methods struggle to accurately assess image focus amidst fluctuations in image scene content

a focus evaluation method

fully equivalent to Gaussian blur standard deviation

is introduced based on the “classification + fitting” concept. Firstly

a dataset for image focus classification

annotated with finite Gaussian blur standard deviations

is established. Subsequently

an asymmetric kernel convolution neural network (AKC-net) is developed to derive image Gaussian blur standard deviation classification scores. Finally

a cubic spline interpolation function is applied to fit the classification score of the AKC-net fully connected layer output and the corresponding Gaussian blur standard deviation

using the standard deviation linked to the maximum score as the focus evaluation for the images. Simulation experiments and real shooting experiment are carried out on the Waterloo dataset and real shooting images respectively. The experimental findings indicate that the proposed method achieves an average classification accuracy of up to 97.7% across various focus images. The root mean square error and mean absolute error between the obtained evaluation results and the true Gaussian blur standard deviation values are less than 0.07. Furthermore

the focus measurement values derived from real shooting images are independent of the image content

enabling the absolute evaluation of the image focus.

关键词

Keywords

references

HELMY I , CHOI W . Machine learning-based automatic focusing for high magnification systems [J ] . Engineering Applications of Artificial Intelligence , 2023 , 118 : 105648 .

杨梦雪 , 李祝莲 , 李荣旺 , 等 . 基于1.2 m望远镜系统实时自动调焦的清晰度评价算法 [J ] . 光学学报 , 2023 , 43 ( 6 ): 0612006 .

YANG Mengxue , LI Zhulian , LI Rongwang , et al . Sharpness evaluation algorithm based on real-time automatic focusing of 1.2 m telescope system [J ] . Acta Optica Sinica , 2023 , 43 ( 6 ): 0612006 .

蒋留兵 , 张点 , 潘波 , 等 . 基于生成对抗网络的多聚焦图像融合 [J ] . 计算机辅助设计与图形学学报 , 2021 , 33 ( 11 ): 1715 - 1725 .

JIANG Liubing , ZHANG Dian , PAN Bo , et al . Multi-focus image fusion based on generative adversarial network [J ] . Journal of Computer-Aided Design & Computer Graphics , 2021 , 33 ( 11 ): 1715 - 1725 .

TANG Han , XIAO Bin , LI Weisheng , et al . Pixel convolutional neural network for multi-focus image fusion [J ] . Information Sciences , 2018 , 433-434 : 125 - 141 .

韦号 , 崔海华 , 程筱胜 , 等 . 一种用于评价聚焦形貌恢复算法的图像离焦仿真技术 [J ] . 光学学报 , 2019 , 39 ( 11 ): 1111001 .

WEI Hao , CUI Haihua , CHENG Xiaosheng , et al . Image defocus simulation technology applied to evaluation of focused morphology recovery algorithm [J ] . Acta Optica Sinica , 2019 , 39 ( 11 ): 1111001 .

XIA Xiaohua , YIN Lijuan , YAO Yunshi , et al . Combining two focus measures to improve performance [J ] . Measurement Science and Technology , 2017 , 28 ( 10 ): 105401 .

LI Qiaoyue , LI Leida , LU Zhaolin , et al . No-reference sharpness index for scanning electron microscopy images based on dark channel prior [J ] . KSII Transactions on Internet and Information Systems , 2019 , 13 ( 5 ): 2529 - 2543 .

周汶 , 李旦 , 张建秋 . 评价彩色图像自动聚焦清晰度的互补色小波测度 [J ] . 自动化学报 , 2020 , 46 ( 8 ): 1615 - 1627 .

ZHOU Wen , LI Dan , ZHANG Jianqiu . A complementary color wavelet-based measure on color image sharpness assessment for autofocus [J ] . Acta Automatica Sinica , 2020 , 46 ( 8 ): 1615 - 1627 .

BAHRAMI K , KOT A C . Efficient image sharpness assessment based on content aware total variation [J ] . IEEE Transactions on Multimedia , 2016 , 18 ( 8 ): 1568 - 1578 .

ZHAN Yibing , ZHANG Rong . No-reference image sharpness assessment based on maximum gradient and variability of gradients [J ] . IEEE Transactions on Multimedia , 2018 , 20 ( 7 ): 1796 - 1808 .

LIU Zhaoyang , HONG Huajie , GAN Zihao , et al . An improved method for evaluating image sharpness based on edge information [J ] . Applied Sciences , 2022 , 12 ( 13 ): 6712 .

LIU Yu , CHEN Xun , PENG Hu , et al . Multi-focus image fusion with a deep convolutional neural network [J ] . Information Fusion , 2017 , 36 : 191 - 207 .

LI Dingquan , JIANG Tingting , LIN Weisi , et al . Which has better visual quality: the clear blue sky or a blurry animal? [J ] . IEEE Transactions on Multimedia , 2019 , 21 ( 5 ): 1221 - 1234 .

DING Xiaohan , GUO Yuchen , DING Guiguang , et al . ACNet: strengthening the kernel skeletons for powerful CNN via asymmetric convolution blocks [C ] // 2019 IEEE/CVF International Conference on Computer Vision (ICCV) . Piscataway, NJ, USA : IEEE , 2019 : 1911 - 1920 .

MA Kede , DUANMU Zhengfang , WU Qingbo , et al . Waterloo exploration database: new challenges for image quality assessment models [J ] . IEEE Transactions on Image Processing , 2017 , 26 ( 2 ): 1004 - 1016 .

SHEIKH H R , SABIR M F , BOVIK A C . A statistical evaluation of recent full reference image quality assessment algorithms [J ] . IEEE Transactions on Image Processing , 2006 , 15 ( 11 ): 3440 - 3451 .

PONOMARENKO N . TID2008-a database for evaluation of full-reference visual quality assessment metrics [J ] . Adv Modern Radioelectron , 2009 , 10 ( 4 ): 30 - 45 .

KRIZHEVSKY A , SUTSKEVER I , HINTON G E . ImageNet classification with deep convolutional neural networks [J ] . Communications of the ACM , 2017 , 60 ( 6 ): 84 - 90 .

SIMONYAN K , ZISSERMAN A . Very deep convolutional networks for large-scale image recognition [EB/OL ] . ( 2015-04-10 ) [ 2022-02-04 ] . https://arxiv.org/abs/1409.1556 https://arxiv.org/abs/1409.1556 .

SZEGEDY C , LIU Wei , JIA Yangqing , et al . Going deeper with convolutions [C ] // 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway, NJ, USA : IEEE , 2015 : 1 - 9 .

HE Kaiming , ZHANG Xiangyu , REN Shaoqing , et al . Deep residual learning for image recognition [C ] // 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway, NJ, USA : IEEE , 2016 : 770 - 778 .

IANDOLA F N , HAN Song , MOSKEWICZ M W , et al . SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5 MB model size [EB/OL ] . ( 2016-11-04 ) [ 2024-05-01 ] . https://arxiv.org/abs/1602.07360 https://arxiv.org/abs/1602.07360 .

HOWARD A G , ZHU Menglong , CHEN Bo , et al . MobileNets: efficient convolutional neural networks for mobile vision applications [EB/OL ] . ( 2017-04-17 ) [ 2024-05-01 ] . https://arxiv.org/abs/1704.04861 https://arxiv.org/abs/1704.04861 .

LIU Ze , LIN Yutong , CAO Yue , et al . Swin transformer: hierarchical vision transformer using shifted windows [C ] // 2021 IEEE/CVF International Conference on Computer Vision (ICCV) . Piscataway, NJ, USA : IEEE , 2021 : 9992 - 10002 .

LIU Zhuang , MAO Hanzi , WU Chaoyuan , et al . A ConvNet for the 2020s [C ] // 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway, NJ, USA : IEEE , 2022 : 11966 - 11976 .

FEICHTENHOFER C , FASSOLD H , SCHALLAUER P . A perceptual image sharpness metric based on local edge gradient analysis [J ] . IEEE Signal Processing Letters , 2013 , 20 ( 4 ): 379 - 382 .

SUBBARAO M , SURYA G . Depth from defocus: a spatial domain approach [J ] . International Journal of Computer Vision , 1994 , 13 ( 3 ): 271 - 294 .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

语义区分和子图整合驱动的知识图谱表示学习方法

结构-语义-残差协同的图像压缩框架：面向隐私保护与高保真重建

采用试验设计方法的第三代CO2气体箔轴承箔片几何参数敏感性分析

超临界二氧化碳向心透平轮背间隙内风阻损失及流动特性研究

扇贝仿生密封腔室内超临界二氧化碳泄漏流湍动能耗散机理研究