Carnegie Mellon Robotics Institute
Yanxi Liu and Frank Dellaert
CVPR'98, June, 1998, pp. 800 - 805.
| Download |
|
| Abstract |
| We present a principled method of obtaining a weighted similarity metric for 3D image retrieval, firmly rooted in Bayes decision theory. The basic idea is to determine a set of most discriminative features by evaluating how well they perform on the task of classifying images according to predefined semantic categories. We propose this indirect method as a rigorous way to solve the difficult feature selection problem that comes up in most content based image retrieval tasks. The method is applied to normal and pathological neuroradiological CT images, where we take advantage of the fact that normal human brains present an approximate bilateral symmetry which is often absent in pathological brains. The quantitative evaluation of the retrieval system shows promising results. the semantics of an image. This domain also provides |
| Notes |
Associated Center(s) / Consortia:
Vision and Autonomous Systems Center and Medical Robotics Technology Center Associated Lab(s) / Group(s):
Medical Robotics and Computer Assisted Surgery, Computational Symmetry, Biomedical Image Analysis Associated Project(s):
A Statistical Quantification of Human Brain Asymmetry Number of pages: 6 |
| Text Reference |
| Yanxi Liu and Frank Dellaert, "A Classification Based Similarity Metric for 3D Image Retrieval," CVPR'98, June, 1998, pp. 800 - 805. |
| BibTeX Reference |
|
@inproceedings{Liu_1998_574, author = "Yanxi Liu and Frank Dellaert", title = "A Classification Based Similarity Metric for 3D Image Retrieval", booktitle = "CVPR'98", pages = "800 - 805", month = "June", year = "1998", } |
| The Robotics Institute is part of the School of Computer Science, Carnegie Mellon University. Contact Us |