Data-driven Fingertip Appearance for Interactive Hand Simulation

Abstract

Contact on a finger pad results in deformation that redistributes blood within the fingertip tissue in a manner correlated to the pressure. We build a data-driven model that relates contact information to the visible changes of the finger nail and surrounding tissue on the back of the finger tip. Our data analysis and model construction makes use of the space of hemoglobin concentrations, as opposed to an RGB color space, which permits the model to be transferred across different fingers and different people. We use principal component analysis to build a compact model which maps well to graphics hardware with an efficient fragment program implementation. We provide a validation of our model, and a demonstration of a grasping controller running in a physically based simulation, where grip strength is visible in both hand posture and the appearance of color changes at the fingertips.

Anticipatory balance control and dimension reduction

“…Many researchers in computer graphics, robotics, computer vision, machine learning, and biomechanics have discussed and explored the applications of dimensionality reduction techniques so as to help in modeling and processing of motion [28][29][30][31][32][33][34][35] . We also exploit dimension reduction to permit an efficient computation of CMRTs.…”