THE IMAGE TORQUE OPERATOR FOR MID-LEVEL VISION: THEORY AND EXPERIMENT

Simple item page
dc.contributor.advisorAloimonos, Yiannisen_US
dc.contributor.advisorFermuller, Corneliaen_US
dc.contributor.authorNishigaki, Morimichien_US
dc.contributor.departmentComputer Scienceen_US
dc.contributor.publisherDigital Repository at the University of Marylanden_US
dc.contributor.publisherUniversity of Maryland (College Park, Md.)en_US
dc.date.accessioned2013-02-07T06:48:56Z
dc.date.available2013-02-07T06:48:56Z
dc.date.issued2012en_US
dc.description.abstractA problem central to visual scene understanding and computer vision is to extract semantically meaningful parts of images. A visual scene consists of objects, and the objects and parts of objects are delineated from their surrounding by closed contours. In this thesis a new bottom-up visual operator, called the <italic>Torque</italic> operator, which captures the concept of closed contours is introduced. Its computation is inspired by the mechanical definition of torque or moment of force, and applied to image edges. It 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. The torque operator is by definition scale independent, and can be seen as an operator of mid-level vision that captures the organizational concept of 'closure' and grouping mechanism of edges. In this thesis, fundamental properties of the torque measure are studied, and experiments are performed to demonstrate and verify that it can be made a useful tool for a variety of applications, including visual attention, segmentation, and boundary edge detection.en_US
dc.identifier.urihttp://hdl.handle.net/1903/13611
dc.subject.pqcontrolledComputer scienceen_US
dc.subject.pqcontrolledComputer engineeringen_US
dc.subject.pquncontrolledBoundary edge detectionen_US
dc.subject.pquncontrolledImage operatoren_US
dc.subject.pquncontrolledImage segmentationen_US
dc.subject.pquncontrolledMid-level visionen_US
dc.subject.pquncontrolledVisual attentionen_US
dc.titleTHE IMAGE TORQUE OPERATOR FOR MID-LEVEL VISION: THEORY AND EXPERIMENTen_US
dc.typeDissertationen_US

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Nishigaki_umd_0117E_13756.pdf
Size:
12.83 MB
Format:
Adobe Portable Document Format
Download

Collections

UMD Theses and Dissertations
Computer Science Theses and Dissertations