发明名称 |
Unsupervised learning of object categories from cluttered images |
摘要 |
Unsupervised learning of object category from images is carried out by using an automatic image recognition system. A plurality of training images are automatically analyzed using an interest operator which produces an indication of features. Those features are clustered using a vector guantizer. The model is learned from the features using expectation maximization to assess a joint probability of which features are most relevant.
|
申请公布号 |
US7280697(B2) |
申请公布日期 |
2007.10.09 |
申请号 |
US20020066318 |
申请日期 |
2002.02.01 |
申请人 |
CALIFORNIA INSTITUTE OF TECHNOLOGY |
发明人 |
PERONA PIETRO;WEBER MARKUS;WELLING MAX |
分类号 |
G06K9/62;G06K9/46;G06K9/66 |
主分类号 |
G06K9/62 |
代理机构 |
|
代理人 |
|
主权项 |
|
地址 |
|