聂茜茜,
肖斌^,,
毕秀丽,
李伟生
重庆邮电大学计算智能重庆市重点实验室 重庆 400065
基金项目:国家重点研发计划(2016YFC1000307-3)，国家自然科学基金(61976031, 61806032)

详细信息

作者简介:聂茜茜：女，1992年生，博士，研究方向为图像处理、深度学习
肖斌：男，1982年生，教授，研究方向为图像处理、模式识别和数字水印
毕秀丽：女，1982年生，副教授，研究方向为图像处理、多媒体安全和图像取证
李伟生：男，1975年生，教授，研究方向为智能信息处理与模式识别

通讯作者:肖斌　xiaobin@cqupt.edu.cn

¹⁾ Cifar-10: <http://www.cs.toronto.edu/~kriz/cifar.html>²⁾ Lytro: <https://github.com/xudif/Multi-focus-Image-Fusion-Dataset>
¹⁾ 融合示例：<https://github.com/sametaymaz/Multi-focus-Image-Fusion-Dataset>
中图分类号:TN911.73; TP751

计量

文章访问数:623
HTML全文浏览量:212
PDF下载量:99
被引次数:0

出版历程

收稿日期:2019-12-30
修回日期:2020-10-28
网络出版日期:2020-12-12
刊出日期:2021-04-20

Multi-focus Image Fusion Algorithm Based on Super Pixel Level Convolutional Neural Network

Xixi NIE,
Bin XIAO^,,
Xiuli BI,
Weisheng LI
Chongqing Key Laboratory of Computational Intelligence, Chongqing University of Posts and Telecommunications, Chongqing 400065, China
Funds:The National Key Research and Development Project of China (2016YFC1000307-3), The National Natural Science Foundation of China (61976031, 61806032)


摘要
摘要:该文提出了基于超像素级卷积神经网络(sp-CNN)的多聚焦图像融合算法。该方法首先对源图像进行多尺度超像素分割，将获取的超像素输入sp-CNN，并对输出的初始分类映射图进行连通域操作得到初始决策图；然后根据多幅初始决策图的异同获得不确定区域，并利用空间频率对其再分类，得到阶段决策图；最后利用形态学对阶段决策图进行后处理，并根据所得的最终决策图融合图像。该文算法直接利用超像素分割块进行图像融合，其相较以往利用重叠块的融合算法可达到降低时间复杂度的目的，同时可获得较好的融合效果。
关键词:多聚焦图像融合/
卷积神经网络/
超像素分割/
空间金字塔池化
Abstract:This paper proposes a multi-focus image fusion algorithm based on super pixel-level Convolutional Neural Network (sp-CNN). In this method, multi-scale super pixel segmentation is firstly applied to the source image to obtain the super pixels. Secondly, the sp-CNN is proposed to acquire the initial decision maps. Thirdly, according to the similarities and differences of the multiple initial decision maps, the uncertain region is reclassified by spatial frequency to obtain the phase decision map. At last, the final decision map is achieved to fuse the source images by post-processing the phase decision graph with morphology. Experimental results show that the proposed method achieves the goal of reducing time complexity and attains better fusion effect compared with the state-of-the-art fusion methods which utilize overlapping blocks.
Key words:Multi-focus image fusion/
Convolutional Neural Network (CNN)/
Super pixel segmentation/
Spatial pyramid pooling
注释:
1) ¹⁾ Cifar-10: <http://www.cs.toronto.edu/~kriz/cifar.html>²⁾ Lytro: <https://github.com/xudif/Multi-focus-Image-Fusion-Dataset>
2) ¹⁾ 融合示例：<https://github.com/sametaymaz/Multi-focus-Image-Fusion-Dataset>



PDF全文下载地址:

https://jeit.ac.cn/article/exportPdf?id=adb79d8b-8438-492d-87ff-170b9805e2f6