|
|
| ||||||
Publications
DISCLAIMER: These materials are presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder
Manuscripts under review
Peer-reviewed journals and conferences
Conference abstracts
Technical reports
Theses
Issued, United States Patents
This method uses spatial frequency analysis to construct a feature vector for every pixel, including: frequency spectrum, power spectrum, and angles of dominant powers, then integrates the information to segment regions of similar texture.
This method rapidly and accurately estimates the orientation of an N-D object by processing the patterns in its spatial frequency transform using a non-linear scaling and Hough-line finding.
This algorithm precisely estimates the dimensions of an object by processing projected, accumulated intensity profiles using an edge attribute score function.
This method refines a given, rough geometric description of an object using a hierarchical estimation of object feature dimensions and projected, accumulated intensity profiles.
This algorithm reliably estimates of the width of a group of similar objects using an adaptive, multi-resolution strategy to fit a positional tolerance signature to all object edges simultaneously.