【图像融合学习笔记003】图像融合数据集，图像融合数据库（有了新的会更新）

一、论文中常用的网址：

http://www.imagefusion.org  （论文中经常引用，但是目前打不开）

二、多聚焦图像：

1、Toet A. TNO Image fusion dataset[J]. Figshare. data, 2014.

https://figshare.com/articles/TN_Image_Fusion_Dataset/1008029

2、http://www.pxleyes.com/photography-contest/19726

3、Lytro Multi-focus Dataset（常用）

“ This dataset contains 20 pairs of color multi-focus images of size 520×520 pixels and four series of multi-focus images with three sources.

Please cite the following paper if you use this dataset:

M. Nejati, S. Samavi, and S. Shirani, "Multi-focus Image Fusion Using Dictionary-Based Sparse Representation", Information Fusion, vol. 25, Sept. 2015, pp. 72-84.

网址：https://mansournejati.ece.iut.ac.ir/content/lytro-multi-focus-dataset

4、Paper：Slavica Savic, "Multifocus Image Fusion Based on Empirical Mode Decomposition", Twentieth International Electrotechnical and Computer Science Conference, ERK 2011.

网站内提供27对多聚焦图像。

网址：http://dsp.etfbl.net/mif/

5、“The dataset which includes 150 different images is created to use in Multi-focus Image Fusion algorithms. This dataset is different from other datasets in this area. The new dataset includes more than two images to fuse. And this propoerty is very important for this dataset.The dataset is prepared by Samet Aymaz.”（包含150张图像，21.3M）

https://github.com/sametaymaz/Multi-focus-Image-Fusion-Dataset

6、https://ww2.mathworks.cn/matlabcentral/fileexchange/45992-standard-images-for-multifocus-image-fusion?s_tid=FX_rc3_behav

该网页也提供了一些多聚焦图像素材。

三、红外与可见光图像

1、TNO Image Fusion Dataset(117.03 MB)——图像序列

网址：https://figshare.com/articles/TN_Image_Fusion_Dataset/1008029

（内容很丰富，常用的图像都是从该库里挑出来的。论文中也常引用该网址。）

简介：

"The TNO Image Fusion Dataset contains multispectral (intensified visual, near-infrared, and longwave infrared or thermal) nighttime imagery of different military relevant scenerios, registered with different multiband camnera systems."

2、OTCBVS Benchmark Dataset Collection

网址：http://vcipl-okstate.org/pbvs/bench/

网站内的简介：

" This is a publicly available benchmark dataset for testing and evaluating novel and state-of-the-art computer vision algorithms. Several researchers and students have requested a benchmark of non-visible (e.g., infrared) images and videos. The benchmark contains videos and images recorded in and beyond the visible spectrum and is available for free to all researchers in the international computer vision communities. Also it will allow a large spectrum of IEEE and SPIE vision conference and workshop participants to explore the benefits of the non-visible spectrum in real-world applications, contribute to the OTCBVS workshop series, and boost this research field significantly. This effort was initiated by Dr. Riad I. Hammoud in 2004. It was hosted at Ohio State University and managed by Dr. James W. David until 2013. It is currently managed by Dr. Guoliang Fan at Oklahoma State University.

This benchmark is to be used for educational and research purposes only, and this benchmark must be acknowledged by the users.

其中通常使用第三个数据集——Dataset 03: OSU Color-Thermal Database

引用：IEEE OTCBVS WS Series Bench; J. Davis and V. Sharma, "Background-Subtraction using Contour-based Fusion of Thermal and Visible Imagery," Computer Vision and Image Understanding, Vol 106, No. 2-3, 2007, pp. 162-182.

3、DATA SET 3: Bristol Eden Project Multi-Sensor Data Set

http://www.cis.rit.edu/pelz/scanpaths/data/bristol-eden.htm

4、Visible-Infrared Database

http://www02.smt.ufrj.br/~fusion/

5、https://www.goes.noaa.gov

6、RGB-NIR Scene Dataset（大约1GB）（EPFL 2015 EPFL database）

网址：https://ivrl.epfl.ch/research-2/research-downloads/supplementary_material-cvpr11-index-html/

网站内的简介：

“This dataset consists of 477 images in 9 categories captured in RGB and Near-infrared (NIR). The images were captured using separate exposures from modified SLR cameras, using visible and NIR filters. For more info on NIR photography, see the references below. The scene categories are: country, field, forest, indoor, mountain, oldbuilding, street, urban, water.”

四、医学图像：

www.med.harvard.edu/aanlib/home.html
 

五、真彩色图像

http://r0k.us/graphics/kodak/

最后：

Durga Prasad Bavirisetti提供了各种融合图像数据集（下面的网址），包含医学图像，多聚焦图像，多模态图像，多曝光图像，遥感图像。（该库里的图像与前面的链接里的图像会有重复）

网站：https://sites.google.com/view/durgaprasadbavirisetti/datasets

 
---------------------

原文：https://blog.csdn.net/shitao99/article/details/83994908