SVHN

发表于

提供者：卢梦依

简介

SVHN数据来源于 Google 街景视图中房屋信息，它是一个真实世界的图像数据集，用于开发机器学习和对象识别算法，对数据预处理和格式化的要求最低。它跟MNIST相似，但是包含更多数量级的标签数据（超过60万个数字图像），并且来源更加多样，用来识别自然场景图像中的数字。

地址

http://ufldl.stanford.edu/housenumbers/

相关论文

[1]Shuai Li,Wenfeng Song,Hong Qin,Aimin Hao. Deep variance network: An iterative, improved CNN framework for unbalanced training datasets[J]. Pattern Recognition,2018,81.
[2]Andrey V. Savchenko,Natalya S. Belova. Unconstrained face identification using maximum likelihood of distances between deep off-the-shelf features[J]. Expert Systems With Applications,2018,108.
[3]Alistair Peter McGeorge. An Urban Partnership for Inner Sydney Social Inclusion, Health and Well-being[J]. International Journal of Integrated Care,2017,17(3).