Classification-Driven Feature Space Reduction for Semantic-based Neuroimage Retrieval - Robotics Institute Carnegie Mellon University

Classification-Driven Feature Space Reduction for Semantic-based Neuroimage Retrieval

Y. Liu, N. A. Lazar, W. E. Rothfus, M. Buzoianu, and Takeo Kanade
Workshop Paper, MICCAI '01 VISIM Workshop on Information Retrieval and Exploration in Large Medical Image Collections (VISIM '01), October, 2001

Abstract

This paper summarizes our work on volumetric pathological neuroimage retrieval under the framework of classification-driven feature selection. The main effort concerns image feature space reduction for the purposes of reducing computational cost during image retrieval as well as improving image indexing feature discriminating power.

BibTeX

@workshop{Liu-2001-8317,
author = {Y. Liu and N. A. Lazar and W. E. Rothfus and M. Buzoianu and Takeo Kanade},
title = {Classification-Driven Feature Space Reduction for Semantic-based Neuroimage Retrieval},
booktitle = {Proceedings of MICCAI '01 VISIM Workshop on Information Retrieval and Exploration in Large Medical Image Collections (VISIM '01)},
year = {2001},
month = {October},
keywords = {feature selection, image retrieval, medical image analysis,semantic-based},
}