Combining multiple neural nets for visual feature selection and classification
Gunther Heidemann · 1999
We present a system for object recognition in real images employing three dierent types of neural networks, which accomplish feature extraction and-classication. The main advantages of the method are its portability to dierent object domains without extensive parameter adjustments or changes in the feature extraction, and the low computational eort. This is achieved using a combination of vector quantization, principal component analysis and a network for nonlinear classication tasks. 1 Introduction Object recognition is one of the major problems in computer vision. It requires memorizing object specic knowledge and algorithms to compare this knowledge with an unknown image region. One way to store the required knowledge is to use explicit object models, e.g. using semantic networks. However, this requires extensive modelling by human programmers. Moreover, explicit models are mainly geometric, so many object properties which strongly determine their appearance like surface re...