| | |
Summary: Perceptual Interpretation of Ink Annotations on Line Charts
Nicholas Kong
University of California, Berkeley
514 Soda Hall
Berkeley, CA 94720-1776
nkong@cs.berkeley.edu
Maneesh Agrawala
University of California, Berkeley
635 Soda Hall, Mail Code #1776
Berkeley, CA 94720-1776
maneesh@cs.berkeley.edu
ABSTRACT
Asynchronous collaborators often use freeform ink annota-
tions to point to visually salient perceptual features of line
charts such as peaks or humps, valleys, rising slopes and
declining slopes. We present a set of techniques for inter-
preting such annotations to algorithmically identify the cor-
responding perceptual parts. Our approach is to first apply
a parts-based segmentation algorithm that identifies the vi-
sually salient perceptual parts in the chart. Our system then
|
