Improving "bag-of-keypoints" image categorisation: Generative Models and PDF-Kernels

Abstract

In this paper we propose two distinct enhancements to the basic ''bag-of-keypoints" image categorisation scheme proposed in [4]. In this approach images are represented as a variable sized set of local image features (keypoints). Thus, we require machine learning tools which can operate on sets of vectors. In [4] this is achieved by representing the set as a histogram over bins found by k-means. We show how this approach can be improved and generalised using Gaussian Mixture Models (GMMs). Alternatively, the set of keypoints can be represented directly as a probability density function, over which a kernel can be de ned. This approach is shown to give state of the art categorisation performance.