Sample Selection, Category Specific Features and Reasoning
Eugene Mbanya, Sebastian Gerke, Hentschel, C., Patrick Ndjiki-Nya · 2022
Abstract. In this paper we present our approach to the 2011 ImageClef PhotoAnnotation task, which is based on the well known bag-of-words model. We investigated an approach for selecting the most informative training samples per concept for classification and the impact of fus-ing the OpponentSIFT feature with the GIST feature which calculates global image statistics, on scene-based concepts. We also incorporated a post-classification processing step, which refined classification results based on rules of inference and exclusion between concepts. The different approaches provided classification gains when compared to the standard bag-of-words model using only the OpponentSIFT feature. 1