The Image Torque Operator for Contour Processing

TL;DR

The paper introduces the Torque operator, a new mid-level image processing tool inspired by Gestalt principles, to improve contour detection, segmentation, and object recognition in images through bottom-up processing.

Contribution

It presents the novel Torque operator for contour grouping, demonstrating its effectiveness in edge detection, visual attention, and segmentation tasks, and discusses its potential for broader applications.

Findings

Enhances boundary contour detection accuracy

Improves segmentation and visual attention results

Demonstrates utility in object recognition tasks

Abstract

Contours are salient features for image description, but the detection and localization of boundary contours is still considered a challenging problem. This paper introduces a new tool for edge processing implementing the Gestaltism idea of edge grouping. This tool is a mid-level image operator, called the Torque operator, that is designed to help detect closed contours in images. The torque operator takes as input the raw image and creates an image map by computing from the image gradients within regions of multiple sizes a measure of how well the edges are aligned to form closed convex contours. Fundamental properties of the torque are explored and illustrated through examples. Then it is applied in pure bottom-up processing in a variety of applications, including edge detection, visual attention and segmentation and experimentally demonstrated a useful tool that can improve existing techniques. Finally, its extension as a more general grouping mechanism and application in object recognition is discussed.