Leveraging geometry and appearance cues for recognizing family photos

Analyzing social relations through image processing is an active and emerging research topic. Family is the basic unit of a society; recognizing and categorizing family photos is an essential step towards image-based social analysis. In this paper, we propose an approach that leverages a geometric model and an appearance model for family photo detection. The geometric feature captures scene-level information with fast computation and discriminative capability, while appearance model captures and quantifies pairwise relations between individuals in a photo. Each individual model performs well for family photo recognition, and a combined approach with both appearance and geometric features can outperform the state-of-the-art method.