Ik Soo Lim

Learn More
This article addresses 2-dimensional layout of high-dimensional biomedical datasets, which is useful for browsing them efficiently. We employ the Isomap technique, which is based on classical MDS (multi-dimensional scaling) but seeks to preserve the intrinsic geometry of the data, as captured in the geodesic manifold distances between all pairs of data(More)
This article addresses visualization of deformation or shape differences between bones while conventional visualization techniques are often about a single bone such as its 3D reconstruction. Given a pair of bones with a set of corresponding anatomical landmarks, we compute displacement vectors describing the deformation from one bone to the other at the(More)
We present a method for improving robustness in feature-based tracking of human motion. Motion flows of features estimated by a standard tracker are modified to be coherent with neighboring ones. This coherence constraint is computed based on a smooth approximation to initial motion flows computed by the tracker. With this tracking results, we demonstrate(More)
This paper addresses an issue of solving customers' problems when applying evolutionary computation. Rather than the seemingly more impressive approach of wow-it-all-evolved-from-nothing, tinkering with exisiting models can be a more pragmatic approach in doing so. Using interactive evolution, we experimentally validate this point on setting parameters of a(More)
We approach the problem of example-based motion synthesis by transforming motion data into a vector space representation. This allows many techniques successful for stationary object synthesis applicable to that of motion. Especially, by separating generation of motion into a time-consuming preprocess and a fast process, it lets on-the-fly motion synthesis(More)
This article describes an approach based on hierarchical radial basis functions to reconstruction and modification of motion / image data, which are formulated as problems of scattered data interpolation. Assuming little about the data and choosing highly scalable / well adjustable basis functions , the approach can handle both the reconstruction and the(More)
The aim of this work is to identify the depth cues that provide intuitive depth-ordering when used to visualize abstract data. In particular we focus on the depth cues that are effective on a high-dynamic-range (HDR) display: contrast and brightness. In an experiment participants were shown a visualization of the volume layers at different depths with a(More)