The Image Torque Operator for Contour Processing
This addresses the problem of contour processing for computer vision researchers, but it appears incremental as it builds on Gestaltism ideas to enhance existing methods.
The paper tackles the challenging problem of detecting and localizing boundary contours in images by introducing a new mid-level image operator called the Torque operator, which measures how well edges align to form closed convex contours and is experimentally shown to improve existing techniques in applications like edge detection and segmentation.
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.