Segmentation using Meta-texture Saliency

9 years 7 months ago
Segmentation using Meta-texture Saliency
We address segmentation of an image into patches that have an underlying salient surface-roughness. Three intrinsic images are derived: reflectance, shading and metatexture images. A constructive approach is proposed for computing a meta-texture image by preserving, equalizing and enhancing the underlying surface-roughness across color, brightness and illumination variations. We evaluate the performance on sample images and illustrate quantitatively that different patches of the same material, in an image, are normalized in their statistics despite variations in color, brightness and illumination. Finally, segmentation by line-based boundary-detection is proposed and results are provided and compared to known algorithms.
Yaser Yacoob, Larry S. Davis
Added 14 Oct 2009
Updated 14 Oct 2009
Type Conference
Year 2007
Where ICCV
Authors Yaser Yacoob, Larry S. Davis
Comments (0)