Abstract
When interpreting a shaded surface image the observer must infer a three-dimensional shape from a two-dimensional image. The principal monocular cues used in this process are surface orientation and apparent depth. Four shading algorithms were compared, ranging from pure depth to pure surface orientation with two intermediates. Eight observers assessed these algorithms using 40 sets of images showing test objects derived from emission computed axial tomograms, X-ray computed tomograms and simulated data. The results demonstrated a highly significant preference (p less than 0.01) for surface orientation over depth information for all observers and both imaging modalities. The coefficient of concordance showed that the observers were in good agreement as to the rank order of the algorithms, with significant agreement (p less than 0.05) for 37 of the 40 sets of images. The overall preferred algorithm was based on a local polynomial fitting procedure and contained primarily surface information. This shading algorithm was extended to include colour, which was used both as an arbitrary surface property to identify parts of a complex object and as a means of conveying temporal information. Further extension of the algorithm to the display of transparent surfaces was facilitated by an illumination model based on purely isotropic light. This enabled even irregular surfaces to be displayed as transparent objects, and was combined with opaque shading for displaying nested surfaces in nuclear magnetic resonance data.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call