A summary statistic representation in peripheral vision explains visual search

Ruth Rosenholtz, Jun Huang, A. Raj, Benjamin Balas, Lucian Ilie

Journal of Vision · 2012 · 397 citations · 80 references

DOIFull text

Open access

Concepts

TL;DR

Visual search, a process of actively moving the eyes to locate targets among distractors, is generally faster when target–distractor discriminability is high, yet many exceptions—such as configuration or conjunction effects and asymmetries—have spurred extensive research over the past three decades. The authors contend that the central challenge in visual search lies in how peripheral image patches are processed using summary statistics over large pooling regions. They quantify these peripheral summary statistics to predict classic search outcomes and peripheral discriminability of crowded patches in search displays.

Abstract

Vision is an active process: We repeatedly move our eyes to seek out objects of interest and explore our environment. Visual search experiments capture aspects of this process, by having subjects look for a target within a background of distractors. Search speed often correlates with target–distractor discriminability; search is faster when the target and distractors look quite different. However, there are notable exceptions. A given discriminability can yield efficient searches (where the target seems to "pop-out") as well as inefficient ones (where additional distractors make search significantly slower and more difficult). Search is often more difficult when finding the target requires distinguishing a particular configuration or conjunction of features. Search asymmetries abound. These puzzling results have fueled three decades of theoretical and experimental studies. We argue that the key issue in search is the processing of image patches in the periphery, where visual representation is characterized by summary statistics computed over a sizable pooling region. By quantifying these statistics, we predict a set of classic search results, as well as peripheral discriminability of crowded patches such as those found in search displays.

References

80