The appearance of an object depends on both the viewpoint from which it is observed and the light sources by which it is illuminated. If the appearance of two objects is never iden...
In this paper, we propose a novel image denoising method by incorporating the dual-tree complex wavelets into the ordinary ridgelet transform. The approximate shift invariant prop...
In this paper, we propose a robust incremental learning framework for accurate skin region segmentation in real-life images. The proposed framework is able to automatically learn ...
— Image keypoints are broadly used in robotics for different purposes, ranging from recognition to 3D reconstruction, passing by SLAM and visual servoing. Robust keypoint matchin...
We introduce a new causal hierarchical belief network for image segmentation. Contrary to classical tree structured (or pyramidal) models, the factor graph of the network contains...