Does a Plane Imitate a Bird? Does Computer Vision Have to Follow Biological Paradigms?

TL;DR

This paper proposes a new paradigm for image processing that separates top-down information extraction from interpretation, challenging traditional bottom-up models inspired by biological vision, supported by human attention studies and complexity theory.

Contribution

It introduces a two-part paradigm for image processing, emphasizing independent top-down extraction and separate interpretation, offering a plausible alternative to existing models.

Findings

Supports the new paradigm with human attention studies

Incorporates Kolmogorov's complexity theory insights

Argues for separate image interpretation processes

Abstract

We posit a new paradigm for image information processing. For the last 25 years, this task was usually approached in the frame of Treisman's two-stage paradigm [1]. The latter supposes an unsupervised, bottom-up directed process of preliminary information pieces gathering at the lower processing stages and a supervised, top-down directed process of information pieces binding and grouping at the higher stages. It is acknowledged that these sub-processes interact and intervene between them in a tricky and a complicated manner. Notwithstanding the prevalence of this paradigm in biological and computer vision, we nevertheless propose to replace it with a new one, which we would like to designate as a two-part paradigm. In it, information contained in an image is initially extracted in an independent top-down manner by one part of the system, and then it is examined and interpreted by another, separate system part. We argue that the new paradigm seems to be more plausible than its forerunner. We provide evidence from human attention vision studies and insights of Kolmogorov's complexity theory to support our arguments. We also provide some reasons in favor of separate image interpretation issues.