M. Tapaswi, C.C. Corez, M. Bäuml, H.K. Ekenel, R. Stiefelhagen
International Conference on Image Processing (ICIP), October 2014
[paper]
[bib]
Automatic person identification in TV series has gained popularity over the years. While most of the works rely on using face-based recognition, errors during tracking such as false positive face tracks are typically ignored. We propose a variety of methods to remove false positive face tracks and categorize the methods into confidence- and context-based. We evaluate our methods on a large TV series data set and show that up to 75% of the false positive face tracks are removed at the cost of 3.6% true positive tracks. We further show that the proposed method is general and applicable to other detectors or trackers.