Appearance-based object recognition using optimal feature transforms

摘要

In this paper we discuss and compare different approaches to appearance-based object recognition and pose estimation. Images are considered as high-dimensional feature vectors which are transformed in various manners: we use different types of non-linear image-to-image transforms composed with linear mappings to reduce the feature dimensions and to beat the curse of dimensionality. The transforms are selected such that special objective functions are optimized and available image data provide some invariance properties. The paper mainly concentrates on the comparison of preprocessing operations combined with different linear projections in the context of appearance-based object recognition. The experimental evaluation provides recognition rates and pose estimation accuracy.