Issue No. 05 - May (1998 vol. 20)
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/34.682189
<p><b>Abstract</b>—A new method for analyzing the <it>intrinsic dimensionality</it> (ID) of low-dimensional manifolds in high-dimensional feature spaces is presented. Compared to a previous approach by Fukunaga and Olsen, the method has only <it>linear instead of cubic time complexity</it> w.r.t. the dimensionality of the input space. Moreover, it is <it>less sensitive to noise</it> than the former approach. Experiments include ID estimation of synthetic data for comparison and illustration as well as ID estimation of an image sequence.</p>
Intrinsic dimensionality estimation, topology preservation, principal component analysis, vector quantization.
G. Sommer and J. Bruske, "Intrinsic Dimensionality Estimation With Optimally Topology Preserving Maps," in IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 20, no. , pp. 572-575, 1998.