TABLE OF CONTENTS Data mining is about finding patterns that were previously unknown or patterns that depart from the norm. The stock market analyst looks for any pattern of variables that may predict a future change in price or earnings. The marketing analyst is interested in perceiving trends and patterns in a customer database. Seeing a pattern can often lead to a key insight, and this is the most compelling reason for visualization.
Here are some of the perceptual questions addressed in this chapter: What does it take for us to see a group? How can 2D space be divided into perceptually distinct regions? Under what conditions are two patterns recognized as similar? When do different elements in a display appear to be related? Answers to these questions are central to visualization, because most data displays are two-dimensional and pattern perception deals with the extraction of structure from 2D space.
Object perception is generally thought of as occurring in several stages (illustrated in Figure 6.1). At the early feature abstraction stages, the visual image is analyzed in terms of primitive elements of form, motion, color, and stereo depth. At the next 2D pattern perception stage, the contours forming the boundaries of objects are discovered and the visual world is segmented into distinct regions, based on these same primitives. Next, the structures of objects and scenes are discovered using information about the connections between component parts, shape-from-shading information, and so on. Finally, objects are identified by means of a process that matches them...
