SSKSRIF: Scale and Rotation Invariant Features Based on Spatial Space of Keypoints for Camera-Based Information Spotting

In this paper, we propose a new method to build a scale and rotation invariant descriptor for camera-based heterogeneous contents document image retrieval and spotting systems based on spatial information of keypoints. The descriptor is not only efficient to compute but also has low dimensionality. First, keypoints are extracted from an image using one of the dedicated detectors. And then, stable keypoints are sampled in order to compute descriptors based on geometric invariant from local organizations of the sampled keypoints via Delaunay triangulation graph. For sampling stable keypoints, we propose an approach which can deal with different scale level from scale space. The experimental results show that the proposed descriptor is promising for document image retrieval and spotting systems.