Finding Glass
- 27 July 2005
- proceedings article
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2, 973-979
- https://doi.org/10.1109/cvpr.2005.161
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
This publication has 14 references indexed in Scilit:
- Learning to segment images using region-based perceptual featuresPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2004
- Segmentation using multiscale cuesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2004
- Using specularities for recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- What does motion reveal about transparency?Published by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Polarization-based transparent surface modeling from two viewsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Surface shape reconstruction of an undulating transparent objectPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Layer extraction from multiple images containing reflections and transparencyPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Surface reflection: physical and geometrical perspectivesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1991
- A physical approach to color image understandingInternational Journal of Computer Vision, 1990
- Snakes: Active contour modelsInternational Journal of Computer Vision, 1988