Abstract
This paper introduces mesostructure roughness as an effective cue in image segmentation. Mesostructure roughness corresponds to small-scale bumps on the macrostructure (i.e., geometry) of objects. Specifically, the focus is on the texture that is created by the projection of the mesostructure roughness on the camera plane. Three intrinsic images are derived: reflectance, smooth-surface shading and mesostructure roughness shading (meta-texture 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. We develop an algorithm for segmentation of an image into patches that share salient mesostructure roughness. Finally, segmentation by line-based boundary-detection is proposed and results are provided and compared to known algorithms.
Similar content being viewed by others
References
Adelson, E. H., Li, Y., & Sharan, L. (2004). Image statistics for material perception. Journal of Vision, 4(8), 123 abstract.
Arbelaez, P. (2006). Boundary extraction in Natural images using ultrametric contour maps. In Workshop on perceptual organization in computer vision.
Barrow, H. G., & Tenenbaum, J. M. (1978). Recovering intrinsic scene characteristics from images. In A. Hanson & E. Riseman (Eds.), Computer vision systems (pp. 3–26). New York: Academic Press.
Chen, J., Pappas, T. N., Mojsilovic, A., & Rogowitz, B. E. (2005). Adaptive perceptual color-texture image segmentation. IEEE Transactions on Image Processing, 14, 1524–1536.
Chen, T., Goesele, M., & Seidel, H. P. (2006). Mesostructure from specularity. In IEEE Conference on Computer Vision and Pattern Recognition (pp. 1825–1832).
Cour, T., Benezit, F., & Shi, J. (2005). Spectral segmentation with multiscale graph decomposition. In IEEE Conference on Computer Vision and Pattern Recognition (pp. 1124–1131).
Cula, O., & Dana, K. J. (2004). 3D Texture recognition using bidirectional feature histograms. International Journal of Computer Vision, 59(1), 33–60.
Dana, K. J., van Ginneken, B., Nayar, S. K., & Koenderink, J. J. (1999). Reflectance and texture of real world surfaces. ACM Transactions on Graphics, 18(1), 1–34.
Finlayson, G. D., Drew, M. S., & Lu, C. (2004). Intrinsic images by entropy minimization. In European Conference on Computer Vision (pp. 582–595).
Horprasert, T., Harwood, D., & Davis, L. S. (1999). A statistical approach for real-time robust background subtraction and shadow detection. In International Conference on Computer Vision FRAME-RATE Workshop.
Koenderink, J. J., & van Doorn, A. J. (1996). Illuminance texture due to surface mesostructure. Journal of the Optical Society of America A, 13(3), 452–463.
Land, E. H., & McCann, J. J. (1971). Lightness and retinex theory. Journal of Optical Society of America, 61, 1–11.
Leung, T., & Malik, J. (2001). Representing and recognizing the visual appearance of materials using three-dimensional textons. International Journal of Computer Vision, 43(1), 29–44.
Liu, X., Yu, Y., & Shum, H. (2001). Synthesizing bidirectional texture functions for real-world surfaces. In SIGGRAPH (pp. 970–106).
Lundberg, A. J., Wolff, L. B., & Socolinsky, D. A. (2001). New perspectives on geometric reflection theory from rough surfaces. In International Conference on Computer Vision (Vol. 1, pp. 225–232).
Maenpaa, T., & Pietikainen, M. (2004). Classification with color and texture: jointly or separately? Pattern Recognition, 37(8), 1629–1640.
Manjunath, B. S., & Ma, W. Y. (1996). Texture features for browsing and retrieval of image data. IEEE Transactions on Pattern Analysis and Machine Intelligence, 18(8), 837–842.
Martin, D., Fowlkes, C., & Malik, J. (2004). Learning to detect natural image boundaries using local brightness, color and texture cues. IEEE Transactions on Pattern Analysis and Machine Intelligence, 26(5), 530–549.
Oren, M., & Nayar, S. K. (1995). Generalization of the Lambertian model and implications for machine vision. International Journal of Computer Vision, 14(3), 227–251.
Ragheb, H., & Hancock, E. R. (2003). Estimating surface characteristics using physical reflectance models. In IEEE Conference on Computer Vision and Pattern Recognition (pp. 177–184).
Tappen, M. F., Freeman, W. T., & Adelson, E. H. (2005). Recovering intrinsic images from a single image. IEEE Transactions on Pattern Analysis and Machine Intelligence, 27(9), 1459–1472.
Tappen, M. F., Freeman, W. T., & Adelson, E. H. (2006). Estimating intrinsic component images using non-linear regression. In IEEE Conference on Computer Vision and Pattern Recognition (pp. 1992–1999).
Torrance, K. , & Sparrow, E. (1967). Theory for off-specular refection from roughened surfaces. Journal of Optical Society of America, 57, 1105–1114.
Varma, M. , & Zisserman, A. (2002). Classifying images of materials: Achieving viewpoint and illumination independence. European Conference on Computer Vision (Vol. 3, pp. 255–271).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Yacoob, Y., Davis, L.S. Segmentation using Appearance of Mesostructure Roughness. Int J Comput Vis 83, 248–273 (2009). https://doi.org/10.1007/s11263-009-0224-2
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11263-009-0224-2