The human ability to learn difficult object categories from just a few views is often explained by an extensive use of knowledge from related classes. In this work we study the use...
Most image segmentation algorithms optimize some mathematical similarity criterion derived from several low-level image features. One possible way of combining different types of f...
We present a method for the detection of instances of an
object class, such as cars or pedestrians, in natural images.
Similarly to some previous works, this is accomplished via
...
Texture boundaries or edges are useful information for segmenting a texture image. We propose a texture edge detection algorithm using a bank of 1-D multi-channel, multiresolution...
In this paper, we propose a new paradigm to reconstruct 3D volume from histology slices guided by NURBS spline-based feature curves. Histology slices are first scanned into compu...