The ability to integrate information over time in order to come to a conclusion is a strength of a cognitive system. It allows the cognitive system to verify insecure observations: This is the case when the data is noisy or the conditions are non-optimal exploit general knowledge about spatio-temporal relations: This allows the system to use dynamics as well as to generate warnings when 'implausible' situations occur or to circumvent these altogether. We have studied the effectiveness of temporal integration for recognition purposes by using the face recognition as an example problem. Face recognition is a prominent problem and has been studied more extensively than almost any other recognition problem. An observation is that face recognition works well in ideal conditions. If those conditions, however, are not met, then all present algorithms break down disgracefully. This probelm appears to be general to all vision techniques that intend to extract visual information out of a low snr. image. It is exactly a strength of cognitive systems that they are able to cope with non-ideal situations. In this chapter we will present a techniques that allows to integrate visual information over time and we will use the face recognition problem as a study example. Probabilistic methods are attractive in this context as they allow a systematic handling of uncertainty and an elegant way for fusing temporal information.
|Titel||Cognitive Vision Systems|
|Forlag||IEEE Computer Society Press|
|Status||Udgivet - 2005|