The Image Torque Operator: A New Tool for Mid-level Vision

被引：0

作者：

Nishigaki, Morimichi ^{[1
]}

Fermueller, Cornelia ^{[2
]}

DeMenthon, Daniel ^{[3
]}

机构：

[1] Univ Maryland, Dept Comp Sci, College Pk, MD 20742 USA

[2] Univ Maryland, UMIACS, College Pk, MD 20742 USA

[3] Johns Hopkins Univ Laurel, Appl Phys Lab, Laurel, MD 20723 USA

来源：

2012 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) | 2012年

基金：

美国国家科学基金会;

关键词：

ATTENTION;

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Contours are a powerful cue for semantic image understanding. Objects and parts of objects in the image are delineated from their surrounding by closed contours which make up their boundary. In this paper we introduce a new bottom-up visual operator to capture the concept of closed contours, which we call the 'Torque' operator. Its computation is inspired by the mechanical definition of torque or moment of force, and applied to image edges. The torque operator takes as input edges and computes over regions of different size a measure of how well the edges are aligned to form a closed, convex contour. We explore fundamental properties of this measure and demonstrate that it can be made a useful tool for visual attention, segmentation, and boundary edge detection by verifying its benefits on these applications.

引用

页码：502 / 509

页数：8