Machine recognition of hand-filled forms is a challenging task. Form processing involves many activities including form field location, field frame boundary removal and data image...
Human-nameable visual attributes offer many advantages when used as mid-level features for object recognition, but existing techniques to gather relevant attributes can be ineffici...
We propose a dense local region detector to extract features suitable for image matching and object recognition tasks. Whereas traditional local interest operators rely on repeata...
In real-world applications, “what you saw” during training is often not “what you get” during deployment: the distribution and even the type and dimensionality of features...
—We study the problem of actively searching for an object in a 3D environment under the constraint of a maximum search time, using a visually guided humanoid robot with twentysix...
Alexander Andreopoulos, Stephan Hasler, Heiko Wers...