Automatic Semantic Labelling of Images by Their Content Using Non-Parametric Bayesian Machine Learning and Image Search Using Synthetically Generated Image Collages

Michael Niemeyer, Ognjen Arandjelovic

Abstract

In this paper, we describe a novel algorithm for fully unsupervised discovery of meaningful object categories in images, and their semantic labelling. Our approach works bottom-up, starting with superpixel segmentation and the representation of images as bags of quantized superpixel based visual words. Inference over these is achieved automatically using hierarchical non-parametric Bayesian learning. This visual learning process is built upon by the association of class labels using two complementary methods. The first of these is primarily suited for conventional object categories, whereas the second one, which employs a reverse image search using synthetically generated superpixel collages, is used for amorphous image content (such as 'grass', 'sky', etc.). The proposed algorithm does not rely on any dataset specific parameter tuning and (by exploiting auxiliary Google retrievable "big data"' in the wild) can be applied on any kind of corpora (no labelling, weak labelling, or fully annotated images).
BibTeX
@inproceedings{niemeyer2018automatic,
  author = {Michael Niemeyer and Ognjen Arandjelovic},
  title = {{Automatic Semantic Labelling of Images by Their Content Using Non-Parametric Bayesian Machine Learning and Image Search Using Synthetically Generated Image Collages}},
  booktitle = {DSAA},
  year = {2018},
  doi = {10.1109/dsaa.2018.00026},
}

Loading related content...

Figure