Author :
McHenry, Kenton ; Ponce, Jean ; Forsyth, David
Author_Institution :
Beckman Inst., Illinois Univ., Urbana, IL, USA
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.
Keywords :
edge detection; feature extraction; glass; image classification; image texture; object detection; edge detection; glass object detection; image contour; image texture; real images; systematic distortion; visual cues; Computed tomography; Computer science; Detectors; Displays; Glass; Image edge detection; Object detection; Shape; Surface texture; Switches;
Conference_Titel :
Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference on
Print_ISBN :
0-7695-2372-2
DOI :
10.1109/CVPR.2005.161
