Sciweavers

Free Online Productivity Tools i2Speak i2Symbol i2OCR iTex2Img iWeb2Print iWeb2Shot i2Type iPdf2Split iPdf2Merge i2Bopomofo i2Arabic i2Style i2Image i2PDF iLatex2Rtf Sci2ools

13

CVPR
2005
IEEE

favoriteEmaildiscussreport

173views Computer Vision» more CVPR 2005»

Finding Glass

14 years 6 months ago

Download www-cvr.ai.uiuc.edu

Abstract. This paper addresses the problem of finding glass objects in images. Visual cues obtained by combining the systematic distortions in background texture occurring at the boundaries of transparent objects with the strong highlights typical of glass surfaces are used to train a hierarchy of classifiers, identify glass edges, and find consistent support regions for these edges. Qualitative and quantitative experiments involving a number of different classifiers and real images are presented.

Kenton McHenry, Jean Ponce, David A. Forsyth

Real-time Traffic

Computer Vision | Consistent Support Regions | CVPR 2005 | Glass Edges | Glass Objects | Glass Surfaces | Transparent Objects |

claim paper

Related Content

» Inspections Some Surprising Findings

» A Geodesic Active Contour Framework for Finding Glass

» Good Ideas through the Looking Glass

» CourseRank A ClosedCommunity Social System through the Magnifying Glass

» Through the looking glass game worlds as representations and views from elsewhere

» Reliable and Fast Eye Finding in Closeup Images

» Using Specularities for Recognition

» Finding Intrinsic and Extrinsic Viewing Parameters from a Single Realist Painting

» An assessment of systems and software engineering scholars and institutions 20002004

Post Info
More Details (n/a)

Added	12 Oct 2009
Updated	12 Oct 2009
Type	Conference
Year	2005
Where	CVPR
Authors	Kenton McHenry, Jean Ponce, David A. Forsyth

Comments (0)