深度学习及课题研究杂谈(一)
2015-06-24 22:59
288 查看
what is feature representation?
no matter what learning and analytical architecture you adopt, the initial procedure refers to getting the basic feature expressions from the training datasets which has a large scale than the test datasets, and then try the proposed linear or non-linear
algorithms to combine the basic featrues to get the possible result near to the final to-be-represent images or other formats objects, and the feedback part could also be set to adjust the parameters of the learning algorithms to repair the gotted result.
静脉思路:
静脉纹路其实是一种比较简单的纹路结构,所以可以引入稀疏编码的思路,设置尽可能多的训练集,通过算法设计训练得到稀疏编码中的基特征,随后对输入的静脉特征进行feature representation,将特征表示中的各基特征对应的系数作为该静脉特征表示,结合图像检索思路进行身份匹配;
另外一种思路是将上述的基特征用基本的直方图分布代替,将直方图组合作为特征表示;
no matter what learning and analytical architecture you adopt, the initial procedure refers to getting the basic feature expressions from the training datasets which has a large scale than the test datasets, and then try the proposed linear or non-linear
algorithms to combine the basic featrues to get the possible result near to the final to-be-represent images or other formats objects, and the feedback part could also be set to adjust the parameters of the learning algorithms to repair the gotted result.
静脉思路:
静脉纹路其实是一种比较简单的纹路结构,所以可以引入稀疏编码的思路,设置尽可能多的训练集,通过算法设计训练得到稀疏编码中的基特征,随后对输入的静脉特征进行feature representation,将特征表示中的各基特征对应的系数作为该静脉特征表示,结合图像检索思路进行身份匹配;
另外一种思路是将上述的基特征用基本的直方图分布代替,将直方图组合作为特征表示;
相关文章推荐
- 实验三:数字滤波器的设计
- 算法——链表问题集锦
- 使用超链接实现企业QQ在线客服
- 手斧Linux – 从LFS到Funtoo (41)
- char* 类型使用总结
- How to decide on the correct number of clusters?
- android 滑动返回
- 元素距离页面的绝对距离
- 手斧Linux – 从LFS到Funtoo (40)
- u-boot2010.03 分析篇(二)-----lowlevel.init.S
- 深入浅出Java回调机制
- 算法——递归思想解决排列组合问题
- 手斧Linux – 从LFS到Funtoo (39)
- 免密码登录服务器python脚本
- VB中错误处理On Error的应用
- 正则表达式在iOS中的运用
- 数据结构——Stack和Queue的互相实现
- ios 在UITableViewController上添加悬浮视图
- 手斧Linux – 从LFS到Funtoo (38)
- DayDayUP_Linux运维学习_mysql安装(源码编译安装)