Beyond straight lines — Object detection using curvature

We present an approach that directly uses curvature cues in a discriminative way to perform object recognition. We show that integrating curvature information substantially improves detection results over descriptors that solely rely upon histograms of orientated gradients (HoG). The pro- posed approach is generic in that it can be easily integrated into state-of-the-art object detection systems. Results on two challenging datasets are presented: ETHZ Shape Dataset and INRIA horses Dataset, improving state-of the-art results using HoG by 7.6% and 12.3% in average precision (AP), respectively. In particular, we achieve higher recall at lower false positive rates.