Owen Carmichael, Ph.D.
Associate Professor and Director of Biomedical Imaging
Associate Professor and Director of Biomedical Imaging
The Wiry Object Recognition Database (WORD) is a collection of labeled images of “wiry” objects such as chairs, ladders, and carts, along with some software utilities for use in. Wiry objects are distinguished by a prevalence of very thin, elongated, stick-like components; examples include tables, chairs, bicycles, and desk lamps. They are difficult to recognize because their shapes are complex and they tend to lack distinctive color or texture characteristics. Recognizing them in images is important in a number of problem areas because they are relatively common.
This database provides benchmark image sets with ground truth for evaluating shape-based object recognition and tracking algorithms. In most image sets, the ground truth consists of binary detected edges, each of which has been hand-labeled as corresponding to an object of interest, or to clutter. In other image sets, the ground truth consists of a set of polygonal regions that map onto the object.