Learning invariant face recognition from examples.
Learning invariant face recognition from examples.
复制标题
DOI：
10.1016/j.neunet.2012.07.006
复制
发表时间：
2013-05
期刊：
影响因子：
--
通讯作者：
Marco K. Müller;Michael Tremer;Christian Bodenstein;R. Würtz
中科院分区：
文献类型：
--
作者：
Marco K. Müller;Michael Tremer;Christian Bodenstein;R. Würtz
自主学习表现为生物在其视觉体验中学习视觉不变性。标准的神经网络模型没有表现出这种学习。在不同情况下的人脸识别的例子中，我们提出了一个学习过程，将学习不变性从学习新的个体实例中分离出来。不变性是通过一组称为模型的示例来学习的，其中包含所有情况的实例。新的实例与这些排名列表的基础上进行比较，这允许跨情况的泛化。结果也被实现为一个尖峰时间为基础的神经网络，这是对干扰的鲁棒性。通过在一组标准人脸数据库上的识别实验证明了该学习能力。
Autonomous learning is demonstrated by living beings that learn visual invariances during their visual experience. Standard neural network models do not show this sort of learning. On the example of face recognition in different situations we propose a learning process that separates learning of the invariance proper from learning new instances of individuals. The invariance is learned by a set of examples called model, which contains instances of all situations. New instances are compared with these on the basis of rank lists, which allow generalization across situations. The result is also implemented as a spike-time-based neural network, which is shown to be robust against disturbances. The learning capability is demonstrated by recognition experiments on a set of standard face databases.