The existing methods for offline training of cascade classifiers take a greedy search to optimize individual classifiers in the cascade, leading inefficient overall performance. W...
Detecting and segmenting free-form objects from cluttered backgrounds is a challenging problem in computer vision. Signature detection in document images is one classic example an...
Guangyu Zhu, Yefeng Zheng, David S. Doermann, Stef...
Constrained local models (CLMs) have recently demonstrated good performance in non-rigid object alignment/tracking in comparison to leading holistic approaches (e.g., AAMs). A maj...
Most algorithms for real-time tracking of deformable shapes provide sub-optimal solutions for a suitable energy minimization task: The search space is typically considered too lar...
We present a practical, stratified autocalibration algorithm with theoretical guarantees of global optimality. Given a projective reconstruction, the first stage of the algorithm ...